jp0317 commented on code in PR #36192:
URL: https://github.com/apache/arrow/pull/36192#discussion_r1242445314
##########
cpp/src/parquet/file_reader.cc:
##########
@@ -178,13 +179,15 @@ class SerializedRowGroup : public
RowGroupReader::Contents {
std::shared_ptr<::arrow::io::internal::ReadRangeCache>
cached_source,
int64_t source_size, FileMetaData* file_metadata,
int row_group_number, const ReaderProperties& props,
+ const std::unordered_set<int>& prebuffered_column_chunks,
Review Comment:
Done. Thanks!
##########
cpp/src/parquet/file_reader.cc:
##########
@@ -297,9 +302,17 @@ class SerializedFile : public ParquetFileReader::Contents {
}
std::shared_ptr<RowGroupReader> GetRowGroup(int i) override {
+ std::unordered_set<int> prebuffered_column_chunks;
+ // Avoid updating the map as this function can be called concurrently. The
map can
+ // only be updated within Prebuffer().
+ auto prebuffered_column_chunks_iter = prebuffered_column_chunks_.find(i);
+ if (prebuffered_column_chunks_iter != prebuffered_column_chunks_.end()) {
+ prebuffered_column_chunks = prebuffered_column_chunks_iter->second;
+ }
+
std::unique_ptr<SerializedRowGroup> contents =
std::make_unique<SerializedRowGroup>(
source_, cached_source_, source_size_, file_metadata_.get(), i,
properties_,
- file_decryptor_);
+ prebuffered_column_chunks, file_decryptor_);
Review Comment:
Done. Thanks!
--
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]