QuakeWang commented on code in PR #193:
URL: https://github.com/apache/paimon-rust/pull/193#discussion_r3027950565
##########
crates/paimon/src/table/table_scan.rs:
##########
@@ -321,26 +370,52 @@ impl<'a> TableScan<'a> {
.as_ref()
.and_then(|map| map.get(&PartitionBucket::new(partition,
bucket)));
- let file_groups = split_for_batch(data_files, target_split_size,
open_file_cost);
- for file_group in file_groups {
- let data_deletion_files =
per_bucket_deletion_map.map(|per_bucket| {
- file_group
- .iter()
- .map(|f| per_bucket.get(&f.file_name).cloned())
- .collect::<Vec<Option<DeletionFile>>>()
- });
-
- let mut builder = DataSplitBuilder::new()
- .with_snapshot(snapshot_id)
- .with_partition(partition_row.clone())
- .with_bucket(bucket)
- .with_bucket_path(bucket_path.clone())
- .with_total_buckets(total_buckets)
- .with_data_files(file_group);
- if let Some(files) = data_deletion_files {
- builder = builder.with_data_deletion_files(files);
+ if data_evolution_enabled {
+ let file_groups = split_by_row_id(data_files);
Review Comment:
> Packaging different rowids together makes the implementation very complex,
which requires re grouping during read, which is not necessary for Rust.
OK, that makes sense to me.
--
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]
