Skip to content

Commit 21599e4

Browse files
committed
chore: restore RowsIndex.partial
1 parent 3c67982 commit 21599e4

File tree

2 files changed

+4
-0
lines changed

2 files changed

+4
-0
lines changed

libs/libcommon/src/libcommon/parquet_utils.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -191,6 +191,7 @@ class ParquetIndexWithMetadata:
191191
features: Features
192192
httpfs: HTTPFileSystem
193193
max_arrow_data_in_memory: int
194+
partial: bool
194195
metadata_dir: Path
195196

196197
file_offsets: np.ndarray = field(init=False)
@@ -400,6 +401,7 @@ def from_parquet_metadata_items(
400401
if not parquet_file_metadata_items:
401402
raise EmptyParquetMetadataError("No parquet files found.")
402403

404+
partial = parquet_export_is_partial(parquet_file_metadata_items[0]["url"])
403405
metadata_dir = Path(parquet_metadata_directory)
404406

405407
with StepProfiler(
@@ -423,6 +425,7 @@ def from_parquet_metadata_items(
423425
features=features,
424426
httpfs=httpfs,
425427
max_arrow_data_in_memory=max_arrow_data_in_memory,
428+
partial=partial,
426429
metadata_dir=metadata_dir,
427430
)
428431

services/worker/tests/job_runners/config/test_parquet_metadata.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -404,6 +404,7 @@ def test_ParquetIndexWithMetadata_query(
404404
features=features,
405405
httpfs=httpfs,
406406
max_arrow_data_in_memory=999999999,
407+
partial=False,
407408
metadata_dir=metadata_dir,
408409
)
409410
with patch("libcommon.parquet_utils.HTTPFile", AuthenticatedHTTPFile):

0 commit comments

Comments
 (0)