lidavidm commented on a change in pull request #9620:
URL: https://github.com/apache/arrow/pull/9620#discussion_r643133844
##########
File path: cpp/src/parquet/arrow/reader.cc
##########
@@ -968,6 +980,102 @@ Status FileReaderImpl::GetRecordBatchReader(const
std::vector<int>& row_groups,
return Status::OK();
}
+/// Given a file reader and a list of row groups, this is a generator of record
+/// batch generators (where each sub-generator is the contents of a single row
group).
+class RowGroupGenerator {
+ public:
+ using RecordBatchGenerator =
+ ::arrow::AsyncGenerator<std::shared_ptr<::arrow::RecordBatch>>;
+
+ explicit RowGroupGenerator(std::shared_ptr<FileReaderImpl> arrow_reader,
+ ::arrow::internal::Executor* executor,
+ std::vector<int> row_groups, std::vector<int>
column_indices)
+ : arrow_reader_(std::move(arrow_reader)),
+ executor_(executor),
+ row_groups_(std::move(row_groups)),
+ column_indices_(std::move(column_indices)),
+ index_(0) {}
+
+ ::arrow::Future<RecordBatchGenerator> operator()() {
+ if (index_ >= row_groups_.size()) {
+ return ::arrow::AsyncGeneratorEnd<RecordBatchGenerator>();
+ }
+ int row_group = row_groups_[index_++];
+ std::vector<int> column_indices = column_indices_;
+ auto reader = arrow_reader_;
+ if (!reader->properties().pre_buffer()) {
+ return SubmitRead(executor_, reader, row_group, column_indices);
+ }
+ auto ready = reader->parquet_reader()->WhenBuffered({row_group},
column_indices);
+ if (executor_) ready = executor_->Transfer(ready);
+ return ready.Then([=]() -> ::arrow::Result<RecordBatchGenerator> {
Review comment:
I filed ARROW-12916.
--
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]
