alamb commented on code in PR #20839:
URL: https://github.com/apache/datafusion/pull/20839#discussion_r2917342471
##########
datafusion/datasource-parquet/src/opener.rs:
##########
@@ -524,11 +475,27 @@ impl FileOpener for ParquetOpener {
}
if enable_bloom_filter && !row_groups.is_empty() {
+ // Use the existing reader for bloom filter I/O;
+ // replace with a fresh reader for decoding below.
+ let bf_reader = std::mem::replace(
+ &mut async_file_reader,
+ parquet_file_reader_factory.create_reader(
+ partition_index,
+ partitioned_file.clone(),
+ metadata_size_hint,
+ &metrics,
+ )?,
+ );
+ let mut bf_builder =
+ ParquetRecordBatchStreamBuilder::new_with_metadata(
Review Comment:
It turns out @ethe filed a very similar request here already:
- https://github.com/apache/arrow-rs/issues/9067
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
