fix(python): repair sync manifest path migration (#4422)

Fixes #4383

`LanceTable.migrate_v2_manifest_paths()` raised `AttributeError` because
it called a nonexistent `AsyncTable.migrate_v2_manifest_paths()` method.
Delegate to the existing async method, `migrate_manifest_paths_v2()`,
while preserving the public sync API.

Add a local regression test for tables starting with either v1 or v2
manifest paths. It checks repeated migration, v2 manifest filenames on
disk, and preservation of data and version history after reopening the
table.

Validation:
- Both new regression cases failed with the reported `AttributeError`
before the fix.
- `cd python && uv run --extra tests pytest
python/tests/test_table.py::test_migrate_v2_manifest_paths
python/tests/test_db.py::test_create_table_v2_manifest_paths_async -q` —
3 passed.
- Repository-wide `ruff check .` and `ruff format .` passed using Ruff
0.15.20 from `python/uv.lock`.
- `git diff --check` passed.

<!-- lance-gatekeeper-fix:v1 agent=bb500f0d1ddefeba3c7d7d8390a2fb74
generation=1 -->

Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
This commit is contained in:
lancedb-gatefixer[bot]
2026-10-03 05:57:56 -05:00
committed by GitHub
parent 7e979c1416
commit 8c2c39b3c4
2 changed files with 27 additions and 1 deletions
+1 -1
View File
@@ -4766,7 +4766,7 @@ class LanceTable(Table):
[LanceTable.uses_v2_manifest_paths][lancedb.table.LanceTable.uses_v2_manifest_paths]
to check if the table is already using the new path style.
"""
LOOP.run(self._table.migrate_v2_manifest_paths())
LOOP.run(self._table.migrate_manifest_paths_v2())
@deprecation.deprecated(
deprecated_in="0.33.1",
+26
View File
@@ -113,6 +113,32 @@ def test_basic(mem_db: DBConnection):
assert table.to_arrow() == expected_data
@pytest.mark.parametrize("enable_v2", [False, True])
def test_migrate_v2_manifest_paths(tmp_path, enable_v2):
db = lancedb.connect(
tmp_path,
storage_options={"new_table_enable_v2_manifest_paths": str(enable_v2).lower()},
)
table = db.create_table("calls", [{"id": 1, "vector": [1.0, 1.0]}])
table.add([{"id": 2, "vector": [2.0, 2.0]}])
expected_data = table.to_arrow()
expected_versions = table.list_versions()
assert table.uses_v2_manifest_paths() == enable_v2
# Migration is also safe to repeat on a table already using v2 paths.
for _ in range(2):
table.migrate_v2_manifest_paths()
assert table.uses_v2_manifest_paths()
reopened = db.open_table("calls")
assert reopened.uses_v2_manifest_paths()
assert reopened.to_arrow() == expected_data
assert reopened.list_versions() == expected_versions
manifests = list((tmp_path / "calls.lance" / "_versions").glob("*.manifest"))
assert len(manifests) == len(expected_versions)
assert all(len(path.stem) == 20 and path.stem.isdigit() for path in manifests)
def test_search_preserves_nulls_from_sliced_arrow_table(mem_db: DBConnection):
data = pa.table(
{