Skip to content

ARROW-901: [Python] Add Parquet unit test for fixed size binary #665

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

Closed
wesm wants to merge 1 commit into from
Closed

ARROW-901: [Python] Add Parquet unit test for fixed size binary #665

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
33 changes: 25 additions & 8 deletions python/pyarrow/tests/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -349,9 +349,7 @@ def test_column_of_lists(tmpdir):


@parquet
def test_date_time_types(tmpdir):
buf = io.BytesIO()

def test_date_time_types():
t1 = pa.date32()
data1 = np.array([17259, 17260, 17261], dtype='int32')
a1 = pa.Array.from_pandas(data1, type=t1)
Expand Down Expand Up @@ -388,11 +386,7 @@ def test_date_time_types(tmpdir):
['date32', 'date64', 'timestamp[us]',
'time32[s]', 'time64[us]', 'time32[s]'])

pq.write_table(table, buf, version="2.0")
buf.seek(0)

result = pq.read_table(buf)
assert result.equals(expected)
_check_roundtrip(table, expected=expected, version='2.0')

# Unsupported stuff
def _assert_unsupported(array):
Expand All @@ -408,6 +402,29 @@ def _assert_unsupported(array):
_assert_unsupported(a7)


@parquet
def test_fixed_size_binary():
t0 = pa.binary(10)
data = [b'fooooooooo', None, b'barooooooo', b'quxooooooo']
a0 = pa.array(data, type=t0)

table = pa.Table.from_arrays([a0],
['binary[10]'])
_check_roundtrip(table)


def _check_roundtrip(table, expected=None, **params):
buf = io.BytesIO()
pq.write_table(table, buf, **params)
buf.seek(0)

if expected is None:
expected = table

result = pq.read_table(buf)
assert result.equals(expected)


@parquet
def test_multithreaded_read():
df = alltypes_sample(size=10000)
Expand Down