Skip to content

fix(table): reuse partition field IDs on v3 tables #4110

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

Open
porkedchop wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(table): reuse partition field IDs on v3 tables #4110

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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/update/spec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,7 +268,7 @@ def _add_new_field(
return PartitionSpec(*partition_fields, spec_id=new_spec_id)

def _partition_field(self, transform_key: tuple[int, Transform[Any, Any]], name: str | None) -> PartitionField:
if self._transaction.table_metadata.format_version == 2:
if self._transaction.table_metadata.format_version >= 2:
source_id, transform = transform_key
historical_fields = []
for spec in self._transaction.table_metadata.specs().values():
Expand Down
13 changes: 13 additions & 0 deletions tests/table/test_init.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1454,6 +1454,19 @@ def test_last_assigned_partition_id(table_v2: Table) -> None:
AssertLastAssignedPartitionId(last_assigned_partition_id=1).validate(base_metadata)


@pytest.mark.parametrize("table", [lf("table_v2"), lf("table_v3")])
def test_update_spec_reuses_removed_partition_field_id(table: Table) -> None:
txn = table.transaction()
txn.update_spec().remove_field("x").add_field("y", BucketTransform(16), "y_bucket").commit()
txn.update_spec().add_identity("x").commit()

assert txn.table_metadata.spec().fields == (
PartitionField(source_id=2, field_id=1001, transform=BucketTransform(16), name="y_bucket"),
PartitionField(source_id=1, field_id=1000, transform=IdentityTransform(), name="x"),
)
assert txn.table_metadata.last_partition_id == 1001


def test_assert_default_spec_id(table_v2: Table) -> None:
base_metadata = table_v2.metadata
AssertDefaultSpecId(default_spec_id=base_metadata.default_spec_id).validate(base_metadata)
Expand Down
Loading