rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-09-09 14:52:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: update lance dependency to v12.0.0-beta.15 (#4143)

Browse Source 
Updates the Rust workspace Lance dependencies, Cargo lockfile, and Java
lance-core from v12.0.0-beta.14 to
[v12.0.0-beta.15](https://github.com/lance-format/lance/releases/tag/v12.0.0-beta.15).
No compatibility fixes were required; `cargo clippy --quiet --workspace
--tests --all-features -- -D warnings`, `cargo fmt --all --quiet`, and
`git diff --check` passed.

---------

Co-authored-by: Jack Ye <yezhaoqin@gmail.com>
This commit is contained in:
LanceDB Robot
2026-09-08 05:12:45 -07:00
committed by GitHub
co-authored by Jack Ye
parent 19fb665c76
commit 3e3878b223
12 changed files with 155 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/python/tests/test_blob.py
+4 -1
View File
@@ -297,7 +297,10 @@ def test_blob_v2_projection_sources_use_typed_column_name():
def _legacy_v1_table(name):
db = lancedb.connect("memory:///")
# Legacy v1 blob columns are only writable at file version <= 2.1.
db = lancedb.connect(
"memory:///", storage_options={"new_table_data_storage_version": "2.1"}
)
schema = pa.schema(
[
pa.field("id", pa.int64()),
python/python/tests/test_namespace.py
+7 -1
View File
@@ -193,7 +193,13 @@ class TestNamespaceConnection:
),
)
table = db.create_table("blob_table", data, namespace_path=["test_ns"])
# Legacy v1 blob columns are only writable at file version <= 2.1.
table = db.create_table(
"blob_table",
data,
namespace_path=["test_ns"],
storage_options={"new_table_data_storage_version": "2.1"},
)
df = table.to_pandas(blob_mode="lazy").sort_values("id")
blob = df["blob"].iloc[0]
python/python/tests/test_query.py
+38 -10
View File
@@ -40,6 +40,10 @@ from utils import exception_output
from importlib.util import find_spec
# Legacy v1 blob columns are only writable at file version <= 2.1.
LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
def _blob_query_data():
return pa.table(
{
@@ -119,13 +123,17 @@ def _assert_blob_bytes_projection(df):
def _blob_query_table(db, name, blob_schema):
if blob_schema == "v1":
return db.create_table(name, _blob_query_data())
return db.create_table(
name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
)
return _create_blob_v2_query_table(db, name)
async def _blob_query_table_async(db, name, blob_schema):
if blob_schema == "v1":
return await db.create_table(name, _blob_query_data())
return await db.create_table(
name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
)
return await _create_blob_v2_query_table_async(db, name)
@@ -275,7 +283,9 @@ async def test_query_to_pandas_kwargs(table, table_async):
def test_plain_scan_query_to_pandas_blob_modes(tmp_db, blob_mode):
pytest.importorskip("lance")
table = tmp_db.create_table(
f"test_query_to_pandas_blob_{blob_mode}", _blob_query_data()
f"test_query_to_pandas_blob_{blob_mode}",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
df = (
@@ -322,7 +332,9 @@ def test_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow(
):
pytest.importorskip("lance")
table = tmp_db.create_table(
"test_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
"test_query_to_pandas_blob_no_arrow_collect",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
query = table.search().where("id = 1").select(["id", "blob"])
@@ -347,7 +359,9 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
):
pytest.importorskip("lance")
table = tmp_db.create_table(
"test_query_to_pandas_blob_desc_flatten", _blob_query_data()
"test_query_to_pandas_blob_desc_flatten",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
query = table.search().where("id = 1").select(["id", "blob"])
@@ -365,7 +379,11 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
pytest.importorskip("lance")
data = _blob_query_data()
table = tmp_db.create_table("test_query_to_pandas_scanner_state", data.slice(0, 2))
table = tmp_db.create_table(
"test_query_to_pandas_scanner_state",
data.slice(0, 2),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
table.add(data.slice(2, 2))
fragments = table.to_lance().get_fragments()
@@ -400,7 +418,9 @@ def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
async def test_async_plain_scan_query_to_pandas_blob_projection(tmp_db_async):
pytest.importorskip("lance")
table = await tmp_db_async.create_table(
"test_async_query_to_pandas_blob_projection", _blob_query_data()
"test_async_query_to_pandas_blob_projection",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
lazy_df = await (
@@ -452,7 +472,9 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
):
pytest.importorskip("lance")
table = await tmp_db_async.create_table(
"test_async_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
"test_async_query_to_pandas_blob_no_arrow_collect",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
query = table.query().where("id = 1").select(["id", "blob"])
@@ -474,7 +496,11 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
pytest.importorskip("lance")
table = tmp_db.create_table("test_vector_query_blob_mode", _blob_query_data())
table = tmp_db.create_table(
"test_vector_query_blob_mode",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
with pytest.raises(RuntimeError, match="Lance native pandas conversion"):
table.search([1.0, 0.0]).select(["blob", "vector"]).limit(1).to_pandas(
@@ -485,7 +511,9 @@ def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
def test_vector_query_to_pandas_blob_descriptions_requires_plain_scan(tmp_db):
pytest.importorskip("lance")
table = tmp_db.create_table(
"test_vector_query_blob_descriptions", _blob_query_data()
"test_vector_query_blob_descriptions",
_blob_query_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
with pytest.raises(RuntimeError, match="plain scan query"):
python/python/tests/test_table.py
+16 -4
View File
@@ -64,15 +64,23 @@ async def _blob_v2_table_async(db: AsyncConnection, name: str):
return table
# Legacy v1 blob columns are only writable at file version <= 2.1.
LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
def _blob_table(db: DBConnection, name: str, blob_schema: str):
if blob_schema == "v1":
return db.create_table(name, data=_blob_test_data())
return db.create_table(
name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
)
return _blob_v2_table(db, name)
async def _blob_table_async(db: AsyncConnection, name: str, blob_schema: str):
if blob_schema == "v1":
return await db.create_table(name, data=_blob_test_data())
return await db.create_table(
name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
)
return await _blob_v2_table_async(db, name)
@@ -147,7 +155,11 @@ def test_table_to_pandas_invalid_blob_mode_non_blob_table(tmp_db: DBConnection):
@pytest.mark.parametrize("blob_mode", ["lazy", "bytes", "descriptions"])
def test_table_to_pandas_blob_modes(tmp_db: DBConnection, blob_mode):
pytest.importorskip("lance")
table = tmp_db.create_table(f"test_to_pandas_blob_{blob_mode}", _blob_test_data())
table = tmp_db.create_table(
f"test_to_pandas_blob_{blob_mode}",
_blob_test_data(),
storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
)
df = table.to_pandas(blob_mode=blob_mode)
@@ -3959,7 +3971,7 @@ def test_stats(mem_db: DBConnection):
print(f"{stats=}")
assert stats == {
# Full on-disk size of the data file, footer and metadata included.
"total_bytes": 633,
"total_bytes": 637,
"num_rows": 2,
"num_indices": 0,
"fragment_stats": {