wgtmac commented on code in PR #36779:
URL: https://github.com/apache/arrow/pull/36779#discussion_r1270811098
##########
cpp/src/parquet/arrow/reader.h:
##########
@@ -249,6 +249,90 @@ class PARQUET_EXPORT FileReader {
virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
std::shared_ptr<::arrow::Table>* out)
= 0;
+ using AsyncBatchGenerator =
+ std::function<::arrow::Future<std::shared_ptr<::arrow::RecordBatch>>()>;
+
+ /// \brief Read a single row group from the file
+ ///
+ /// \see ReadRowGroupsAsync for operation details
+ ///
+ /// \param i the index of the row group to read
+ /// \param cpu_executor an executor to use to run CPU tasks
+ /// \param allow_sliced_batches if false, an error is raised if a batch has
too much
+ /// data for the given batch size. If true,
smaller
+ /// batches will be returned instead.
+ virtual AsyncBatchGenerator ReadRowGroupAsync(int i,
+ ::arrow::internal::Executor*
cpu_executor,
+ bool allow_sliced_batches =
false) = 0;
+ /// \brief Read some columns from a single row group from the file
+ ///
+ /// \see ReadRowGroupsAsync for operation details
+ /// \see ReadTable for details on how column indices are resolved
+ ///
+ /// \param i the index of the row group to read
+ /// \param column_indices leaf-indices of the columns to read
+ /// \param cpu_executor an executor to use to run CPU tasks
+ /// \param allow_sliced_batches if false, an error is raised if a batch has
too much
+ /// data for the given batch size. If true,
smaller
+ /// batches will be returned instead.
+ virtual AsyncBatchGenerator ReadRowGroupAsync(int i,
+ const std::vector<int>&
column_indices,
+ ::arrow::internal::Executor*
cpu_executor,
+ bool allow_sliced_batches =
false) = 0;
+
+ /// \brief Read row groups from the file
+ ///
+ /// \see ReadRowGroupsAsync for operation details
+ ///
+ /// \param row_groups indices of the row groups to read
+ /// \param cpu_executor an executor to use to run CPU tasks
+ /// \param allow_sliced_batches if false, an error is raised if a batch has
too much
Review Comment:
It does not hurt to add this option. So I am fine with keeping it.
--
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]
