steFaiz commented on code in PR #8846:
URL: https://github.com/apache/paimon/pull/8846#discussion_r3662455927
##########
paimon-python/pypaimon/read/scanner/chunk_shuffle_split_generator.py:
##########
@@ -225,13 +418,18 @@ def _chunk_to_split(self, chunk: _Chunk) -> Split:
# set_file_path is already done once per unique file in
# ChunkShuffleSplitGeneratorBase.create_splits.
+ data_deletion_files = self._get_deletion_files_for_split(
+ files,
+ chunk.partition,
+ chunk.bucket,
+ )
data_split = DataSplit(
files=files,
partition=chunk.partition,
bucket=chunk.bucket,
raw_convertible=True,
- data_deletion_files=None,
+ data_deletion_files=data_deletion_files,
Review Comment:
Nice catch! I've fixed this and added tests
##########
paimon-python/pypaimon/read/scanner/chunk_shuffle_split_generator.py:
##########
@@ -334,12 +562,17 @@ def _chunk_to_split(self, chunk: _Chunk) -> Split:
row_ranges.append(seg.row_range)
row_ranges.sort(key=lambda r: r.from_)
+ data_deletion_files = self._get_deletion_files_for_split(
+ all_files,
+ chunk.partition,
+ chunk.bucket,
+ )
data_split = DataSplit(
files=all_files,
partition=chunk.partition,
bucket=chunk.bucket,
raw_convertible=False,
- data_deletion_files=None,
+ data_deletion_files=data_deletion_files,
Review Comment:
Nice catch! I've fixed this and added tests
--
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]
