lidavidm commented on a change in pull request #10482:
URL: https://github.com/apache/arrow/pull/10482#discussion_r649320187
##########
File path: cpp/src/parquet/arrow/reader.cc
##########
@@ -1024,31 +1027,32 @@ class RowGroupGenerator {
::arrow::internal::Executor* cpu_executor,
std::shared_ptr<FileReaderImpl> self,
const int row_group, const std::vector<int>& column_indices) {
if (!cpu_executor) {
- return Future<RecordBatchGenerator>::MakeFinished(
- ReadOneRowGroup(self, row_group, column_indices));
+ return ReadOneRowGroup(cpu_executor, self, row_group, column_indices);
}
// If we have an executor, then force transfer (even if I/O was complete)
- return ::arrow::DeferNotOk(
- cpu_executor->Submit(ReadOneRowGroup, self, row_group,
column_indices));
+ return ::arrow::DeferNotOk(cpu_executor->Submit(ReadOneRowGroup,
cpu_executor, self,
+ row_group,
column_indices));
}
- static ::arrow::Result<RecordBatchGenerator> ReadOneRowGroup(
- std::shared_ptr<FileReaderImpl> self, const int row_group,
- const std::vector<int>& column_indices) {
- std::shared_ptr<::arrow::Table> table;
+ static ::arrow::Future<RecordBatchGenerator> ReadOneRowGroup(
+ ::arrow::internal::Executor* cpu_executor,
std::shared_ptr<FileReaderImpl> self,
+ const int row_group, const std::vector<int>& column_indices) {
// Skips bound checks/pre-buffering, since we've done that already
- RETURN_NOT_OK(self->DecodeRowGroups({row_group}, column_indices, &table));
- auto table_reader = std::make_shared<::arrow::TableBatchReader>(*table);
- ::arrow::RecordBatchVector batches;
- while (true) {
- std::shared_ptr<::arrow::RecordBatch> batch;
- RETURN_NOT_OK(table_reader->ReadNext(&batch));
- if (!batch) {
- break;
- }
- batches.push_back(batch);
- }
- return ::arrow::MakeVectorGenerator(std::move(batches));
+ return self->DecodeRowGroups(self, {row_group}, column_indices,
cpu_executor)
+ .Then([](const std::shared_ptr<Table>& table)
+ -> ::arrow::Result<RecordBatchGenerator> {
Review comment:
There's not really a big difference, no, except that
MakeConcatenatedGenerator makes it easy to go from
`AsyncGenerator<AsyncGenerator<T>>` to `AsyncGenerator<T>` and we don't have
anything for `AsyncGenerator<vector<T>>`.
--
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:
[email protected]
