Skip to content

Turn ObjectStoreLocationProvider off by default #1722

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kevinjqliu merged 2 commits into from
Feb 25, 2025
Merged

Turn ObjectStoreLocationProvider off by default #1722

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e59b87
ObjectStoreLocationProvider off by default
kevinjqliu Feb 25, 2025
0c4830b
fix integration tests
kevinjqliu Feb 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pyiceberg/table/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,7 @@ class TableProperties:
WRITE_PY_LOCATION_PROVIDER_IMPL = "write.py-location-provider.impl"

OBJECT_STORE_ENABLED = "write.object-storage.enabled"
OBJECT_STORE_ENABLED_DEFAULT = True
OBJECT_STORE_ENABLED_DEFAULT = False

WRITE_OBJECT_STORE_PARTITIONED_PATHS = "write.object-storage.partitioned-paths"
WRITE_OBJECT_STORE_PARTITIONED_PATHS_DEFAULT = True
Expand Down
9 changes: 5 additions & 4 deletions tests/integration/test_writes/test_partitioned_writes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,13 +294,14 @@ def test_object_storage_location_provider_excludes_partition_path(
PartitionField(source_id=nested_field.field_id, field_id=1001, transform=IdentityTransform(), name=part_col)
)

# write.object-storage.enabled and write.object-storage.partitioned-paths don't need to be specified as they're on by default
assert TableProperties.OBJECT_STORE_ENABLED_DEFAULT
assert TableProperties.WRITE_OBJECT_STORE_PARTITIONED_PATHS_DEFAULT
# Enable `write.object-storage.enabled` which is False by default
# `write.object-storage.partitioned-paths` is True by default
assert TableProperties.OBJECT_STORE_ENABLED_DEFAULT is False
assert TableProperties.WRITE_OBJECT_STORE_PARTITIONED_PATHS_DEFAULT is True
tbl = _create_table(
session_catalog=session_catalog,
identifier=f"default.arrow_table_v{format_version}_with_null_partitioned_on_col_{part_col}",
properties={"format-version": str(format_version)},
properties={"format-version": str(format_version), TableProperties.OBJECT_STORE_ENABLED: True},
data=[arrow_table_with_null],
partition_spec=partition_spec,
)
Expand Down
10 changes: 7 additions & 3 deletions tests/table/test_locations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ def test_custom_location_provider_not_found(caplog: Any) -> None:


def test_object_storage_no_partition() -> None:
provider = load_location_provider(table_location="table_location", table_properties=EMPTY_DICT)
provider = load_location_provider(table_location="table_location", table_properties={"write.object-storage.enabled": "true"})

location = provider.new_data_location("test.parquet")
parts = location.split("/")
Expand Down Expand Up @@ -111,6 +111,7 @@ def test_object_storage_partitioned_paths_disabled(partition_key: Optional[Parti
provider = load_location_provider(
table_location="table_location",
table_properties={
"write.object-storage.enabled": "true",
"write.object-storage.partitioned-paths": "false",
},
)
Expand All @@ -131,15 +132,18 @@ def test_object_storage_partitioned_paths_disabled(partition_key: Optional[Parti
],
)
def test_hash_injection(data_file_name: str, expected_hash: str) -> None:
provider = load_location_provider(table_location="table_location", table_properties=EMPTY_DICT)
provider = load_location_provider(table_location="table_location", table_properties={"write.object-storage.enabled": "true"})

assert provider.new_data_location(data_file_name) == f"table_location/data/{expected_hash}/{data_file_name}"


def test_object_location_provider_write_data_path() -> None:
provider = load_location_provider(
table_location="s3://table-location/table",
table_properties={TableProperties.WRITE_DATA_PATH: "s3://table-location/custom/data/path"},
table_properties={
"write.object-storage.enabled": "true",
TableProperties.WRITE_DATA_PATH: "s3://table-location/custom/data/path",
},
)

assert (
Expand Down