westonpace commented on a change in pull request #9644:
URL: https://github.com/apache/arrow/pull/9644#discussion_r601756752
##########
File path: cpp/src/arrow/csv/reader.cc
##########
@@ -574,37 +585,41 @@ class BaseTableReader : public ReaderMixin, public
csv::TableReader {
class BaseStreamingReader : public ReaderMixin, public csv::StreamingReader {
public:
- using ReaderMixin::ReaderMixin;
+ BaseStreamingReader(io::IOContext io_context, Executor* cpu_executor,
+ std::shared_ptr<io::InputStream> input,
+ const ReadOptions& read_options, const ParseOptions&
parse_options,
+ const ConvertOptions& convert_options)
+ : ReaderMixin(io_context, std::move(input), read_options, parse_options,
+ convert_options),
+ cpu_executor_(cpu_executor) {}
- virtual Status Init() = 0;
+ virtual Future<std::shared_ptr<csv::StreamingReader>> Init() = 0;
std::shared_ptr<Schema> schema() const override { return schema_; }
Status ReadNext(std::shared_ptr<RecordBatch>* batch) override {
- do {
- RETURN_NOT_OK(ReadNext().Value(batch));
- } while (*batch != nullptr && (*batch)->num_rows() == 0);
+ auto next_fut = ReadNextAsync();
+ auto next_result = next_fut.result();
+ ARROW_ASSIGN_OR_RAISE(*batch, next_result);
return Status::OK();
Review comment:
Done. I had seen this used a few times but hadn't truly understood the
purpose. Now I think I get 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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
