mbutrovich commented on code in PR #2176:
URL: https://github.com/apache/iceberg-rust/pull/2176#discussion_r2896023561
##########
crates/iceberg/src/arrow/reader.rs:
##########
@@ -513,14 +522,51 @@ impl ArrowReader {
.with_preload_page_index(should_load_page_index);
if let Some(hint) = metadata_size_hint {
- parquet_file_reader =
parquet_file_reader.with_metadata_size_hint(hint);
+ reader = reader.with_metadata_size_hint(hint);
}
- // Create the record batch stream builder, which wraps the parquet
file reader
- let options = arrow_reader_options.unwrap_or_default();
- let record_batch_stream_builder =
-
ParquetRecordBatchStreamBuilder::new_with_options(parquet_file_reader,
options).await?;
- Ok(record_batch_stream_builder)
+ let arrow_metadata = ArrowReaderMetadata::load_async(&mut reader,
Default::default())
+ .await
+ .map_err(|e| {
+ Error::new(ErrorKind::Unexpected, "Failed to load Parquet
metadata").with_source(e)
+ })?;
+
+ Ok(Arc::clone(arrow_metadata.metadata()))
+ }
+
+ pub(crate) async fn create_parquet_record_batch_stream_builder(
+ data_file_path: &str,
+ file_io: FileIO,
+ should_load_page_index: bool,
+ arrow_reader_options: ArrowReaderOptions,
+ file_size_in_bytes: u64,
+ parquet_metadata: Arc<ParquetMetaData>,
+ ) -> Result<ParquetRecordBatchStreamBuilder<ArrowFileReader>> {
+ let arrow_reader_metadata =
+ ArrowReaderMetadata::try_new(parquet_metadata,
arrow_reader_options).map_err(|e| {
+ Error::new(
+ ErrorKind::Unexpected,
+ "Failed to create ArrowReaderMetadata from
ParquetMetaData",
+ )
+ .with_source(e)
+ })?;
+
+ let parquet_file = file_io.new_input(data_file_path)?;
+ let parquet_reader = parquet_file.reader().await?;
+ let parquet_file_reader = ArrowFileReader::new(
+ FileMetadata {
+ size: file_size_in_bytes,
+ },
+ parquet_reader,
+ )
+ .with_preload_column_index(true)
+ .with_preload_offset_index(true)
Review Comment:
These should now be encapsulated in defaults for `ParquetReadOptions` after
#2181, which just kept the values they were before. IIRC Column and Offset
Index should be written by default in Parquet in all modern implementations, so
preloading makes sense now.
--
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]
