mirror of
https://github.com/lancedb/lancedb.git
synced 2026-11-13 14:16:54 +00:00
importcppandimportcpp
8172298044
Expand the Linux Python test run without pandas and pylance from two files to the suite while retaining the regular dependency run for optional-package modules. Move optional imports into tests that need them and use Arrow assertions where pandas is not required, preserving the existing behavioral assertions. Validation: - Physical no-pandas/no-pylance broad run: 2884 passed, 316 skipped, 8 existing marker cases deselected. - Regular affected suite: 1687 passed, 39 skipped. - Current-head hosted integration: all 15 checks and 4 workflows passed. Co-authored-by: importcpp <57519936+importcpp@users.noreply.github.com>
97 lines
3.8 KiB
Python
97 lines
3.8 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
|
|
|
import subprocess
|
|
import sys
|
|
import textwrap
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize("api", ["sync", "async"])
|
|
@pytest.mark.parametrize("result", ["pandas", "batches", "lazy_error"])
|
|
def test_blob_query_without_pylance(tmp_path, api, result):
|
|
if result == "pandas":
|
|
pytest.importorskip("pandas")
|
|
script = """\
|
|
import importlib.abc
|
|
import sys
|
|
|
|
class MissingLance(importlib.abc.MetaPathFinder):
|
|
def find_spec(self, fullname, path, target=None):
|
|
if fullname == "lance" or fullname.startswith("lance."):
|
|
raise ModuleNotFoundError(fullname, name="lance")
|
|
|
|
sys.meta_path.insert(0, MissingLance())
|
|
""" + textwrap.dedent(
|
|
"""\
|
|
import asyncio
|
|
import lancedb
|
|
import pyarrow as pa
|
|
|
|
schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("video")])
|
|
rows = [{"id": 1, "video": b"one"}, {"id": 2, "video": None},
|
|
{"id": 3, "video": b"three"}]
|
|
|
|
def check(data):
|
|
assert data == [{"filename": 2, "payload": None},
|
|
{"filename": 3, "payload": b"three"}], data
|
|
|
|
async def main():
|
|
if sys.argv[2] == "async":
|
|
db = await lancedb.connect_async(sys.argv[1])
|
|
table = await db.create_table("videos", schema=schema)
|
|
await table.add(rows)
|
|
query = table.query()
|
|
else:
|
|
db = lancedb.connect(sys.argv[1])
|
|
table = db.create_table("videos", schema=schema)
|
|
table.add(rows)
|
|
query = table.search()
|
|
query = query.select({"filename": "id", "payload": "video"}).offset(1)
|
|
if sys.argv[3] == "pandas":
|
|
frame = query.to_pandas(blob_mode="bytes", split_blocks=True)
|
|
if sys.argv[2] == "async":
|
|
frame = await frame
|
|
check(frame.to_dict("records"))
|
|
frame = table.to_pandas(blob_mode="bytes")
|
|
if sys.argv[2] == "async":
|
|
frame = await frame
|
|
assert frame.to_dict("records") == rows
|
|
elif sys.argv[3] == "batches":
|
|
if sys.argv[2] == "async":
|
|
reader = await query.to_batches(
|
|
max_batch_length=1, blob_mode="bytes")
|
|
batches = [batch async for batch in reader]
|
|
else:
|
|
reader = query.to_batches(batch_size=1, blob_mode="bytes")
|
|
batches = list(reader)
|
|
assert reader.schema.field("payload").type == pa.large_binary()
|
|
assert all(batch.num_rows <= 1 for batch in batches)
|
|
assert all(batch.schema == reader.schema for batch in batches)
|
|
check([row for batch in batches for row in batch.to_pylist()])
|
|
else:
|
|
try:
|
|
frame = query.to_pandas()
|
|
if sys.argv[2] == "async":
|
|
await frame
|
|
except RuntimeError as error:
|
|
message = str(error)
|
|
assert "pip install pylance" in message, message
|
|
assert ".." not in message, message
|
|
assert "Use a plain scan query" not in message, message
|
|
assert "but The" not in message, message
|
|
else:
|
|
raise AssertionError("lazy handles should require pylance")
|
|
assert "lance" not in sys.modules
|
|
|
|
asyncio.run(main())
|
|
"""
|
|
)
|
|
completed = subprocess.run(
|
|
[sys.executable, "-c", script, str(tmp_path), api, result],
|
|
capture_output=True,
|
|
text=True,
|
|
)
|
|
assert completed.returncode == 0, completed.stderr
|