Dandandan commented on code in PR #20857:
URL: https://github.com/apache/datafusion/pull/20857#discussion_r2914205152
##########
datafusion/datasource-parquet/src/metadata.rs:
##########
@@ -141,32 +130,65 @@ impl<'a> DFParquetMetadata<'a> {
return Ok(Arc::clone(cached_parquet.parquet_metadata()));
}
- let mut reader =
-
ParquetMetaDataReader::new().with_prefetch_hint(*metadata_size_hint);
+ let file_size = self.object_meta.size as u64;
+ let mut decoder = ParquetMetaDataPushDecoder::try_new(file_size)
+ .map_err(DataFusionError::from)?;
- #[cfg(feature = "parquet_encryption")]
- if let Some(decryption_properties) = decryption_properties {
- reader = reader
-
.with_decryption_properties(Some(Arc::clone(decryption_properties)));
- }
-
- if cache_metadata && file_metadata_cache.is_some() {
+ if cache_metadata && self.file_metadata_cache.is_some() {
// Need to retrieve the entire metadata for the caching to be
effective.
- reader = reader.with_page_index_policy(PageIndexPolicy::Optional);
+ decoder =
decoder.with_page_index_policy(PageIndexPolicy::Optional);
+ } else {
+ decoder = decoder.with_page_index_policy(PageIndexPolicy::Skip);
}
- let metadata = Arc::new(
- reader
- .load_and_finish(fetch, object_meta.size)
+ // If we have a size hint, prefetch that many bytes from the end of
the file
+ if let Some(hint) = self.metadata_size_hint {
+ let prefetch_start = file_size.saturating_sub(hint as u64);
+ let prefetch_range = prefetch_start..file_size;
+ let data = self
+ .store
+ .get_ranges(
Review Comment:
This and next requests can go on a queue.
--
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]
