Skip to content

Remove and rewrite unnecessary pandas cursor tests #1256

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
laughingman7743 merged 7 commits into from
Oct 18, 2026
Merged

Remove and rewrite unnecessary pandas cursor tests #1256

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b22ef48
Remove and rewrite redundant PandasCursor tests
laughingman7743 Oct 17, 2026
e6b5f65
Remove async and aio pandas tests that repeat the sync result set
laughingman7743 Oct 17, 2026
3eb4184
Read the pandas result-set tests through the result set's constructor
laughingman7743 Oct 17, 2026
ecf6f4d
Check the pandas reads against explicit values and close whole binary…
laughingman7743 Oct 17, 2026
3c543d7
Share the local result files of the offline pandas tests
laughingman7743 Oct 17, 2026
efbdb7c
Check the pandas read options that the independent review found untested
laughingman7743 Oct 17, 2026
102e971
Check the pyarrow CSV dispatch with numeric-looking text
laughingman7743 Oct 17, 2026
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
65 changes: 5 additions & 60 deletions tests/pyathena/aio/pandas/test_cursor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,7 @@
from pyathena.aio.pandas.cursor import AioPandasCursor
from pyathena.error import ProgrammingError
from pyathena.model import AthenaQueryExecution
from pyathena.pandas.result_set import AthenaPandasResultSet
from pyathena.util import RetryConfig
from tests import ENV
from tests.pyathena.aio.conftest import _aio_connect


class TestAioPandasCursor:
Expand All @@ -35,17 +32,15 @@ async def test_binary_null_vs_empty(self, aio_pandas_cursor):
]

async def test_fetchone(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT * FROM one_row")
assert await aio_pandas_cursor.execute("SELECT * FROM one_row") is aio_pandas_cursor
assert aio_pandas_cursor.description == [
("number_of_rows", "integer", None, None, 10, 0, "UNKNOWN")
]
assert aio_pandas_cursor.rownumber == 0
assert await aio_pandas_cursor.fetchone() == (1,)
assert aio_pandas_cursor.rownumber == 1
assert await aio_pandas_cursor.fetchone() is None

async def test_fetchmany(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT * FROM many_rows LIMIT 15")
assert len(await aio_pandas_cursor.fetchmany(10)) == 10
assert len(await aio_pandas_cursor.fetchmany(10)) == 5

async def test_fetchall(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT * FROM one_row")
assert await aio_pandas_cursor.fetchall() == [(1,)]
Expand All @@ -59,10 +54,6 @@ async def test_as_pandas(self, aio_pandas_cursor):
assert df.columns.tolist() == ["number_of_rows"]
assert df["number_of_rows"].iloc[0] == 1

async def test_execute_returns_self(self, aio_pandas_cursor):
result = await aio_pandas_cursor.execute("SELECT * FROM one_row")
assert result is aio_pandas_cursor

async def test_no_result_set_raises(self, aio_pandas_cursor):
with pytest.raises(ProgrammingError):
await aio_pandas_cursor.fetchone()
Expand All @@ -73,73 +64,27 @@ async def test_no_result_set_raises(self, aio_pandas_cursor):
with pytest.raises(ProgrammingError):
aio_pandas_cursor.as_pandas()

async def test_context_manager(self):
from pyathena.aio.pandas.cursor import AioPandasCursor

conn = await _aio_connect(schema_name=ENV.schema, cursor_class=AioPandasCursor)
try:
async with conn.cursor() as cursor:
await cursor.execute("SELECT * FROM one_row")
assert await cursor.fetchone() == (1,)
finally:
conn.close()

async def test_arraysize_default(self, aio_pandas_cursor):
assert aio_pandas_cursor.arraysize == AthenaPandasResultSet.DEFAULT_FETCH_SIZE

async def test_invalid_arraysize(self, aio_pandas_cursor):
aio_pandas_cursor.arraysize = 10000
assert aio_pandas_cursor.arraysize == 10000
with pytest.raises(ProgrammingError):
aio_pandas_cursor.arraysize = -1

async def test_description(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT CAST(1 AS INT) AS foobar FROM one_row")
assert await aio_pandas_cursor.fetchall() == [(1,)]
assert aio_pandas_cursor.description == [
("foobar", "integer", None, None, 10, 0, "UNKNOWN")
]

async def test_description_initial(self, aio_pandas_cursor):
assert aio_pandas_cursor.description is None

async def test_cancel_initial(self, aio_pandas_cursor):
with pytest.raises(ProgrammingError):
await aio_pandas_cursor.cancel()

async def test_executemany_fetch(self, aio_pandas_cursor):
await aio_pandas_cursor.executemany(
"SELECT %(x)d FROM one_row", [{"x": i} for i in range(1, 2)]
)
with pytest.raises(ProgrammingError):
await aio_pandas_cursor.fetchall()
with pytest.raises(ProgrammingError):
await aio_pandas_cursor.fetchmany()
with pytest.raises(ProgrammingError):
await aio_pandas_cursor.fetchone()
with pytest.raises(ProgrammingError):
aio_pandas_cursor.as_pandas()

@pytest.mark.parametrize(
"aio_pandas_cursor",
[{"cursor_kwargs": {"unload": True}}],
indirect=["aio_pandas_cursor"],
)
async def test_fetchone_unload(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT * FROM one_row")
assert aio_pandas_cursor.as_pandas()["number_of_rows"].tolist() == [1]
assert await aio_pandas_cursor.fetchone() == (1,)
assert await aio_pandas_cursor.fetchone() is None

@pytest.mark.parametrize(
"aio_pandas_cursor",
[{"cursor_kwargs": {"unload": True}}],
indirect=["aio_pandas_cursor"],
)
async def test_as_pandas_unload(self, aio_pandas_cursor):
await aio_pandas_cursor.execute("SELECT * FROM one_row")
df = aio_pandas_cursor.as_pandas()
assert len(df) == 1

@pytest.mark.parametrize(
"execute_kwargs",
[
Expand Down
Loading
Loading