def test_http_filesystem_no_versioning(self):
pattern = r"HTTP\(s\) DataSet doesn't support versioning\."
with pytest.raises(DataSetError, match=pattern):
FeatherDataSet(
filepath="https://example.com/file.feather", version=Version(None, None)
)
def test_protocol_usage(self, filepath, instance_type):
data_set = FeatherDataSet(filepath=filepath)
assert isinstance(data_set._fs, instance_type)
path = filepath.split(PROTOCOL_DELIMITER, 1)[-1]
assert str(data_set._filepath) == path
assert isinstance(data_set._filepath, PurePosixPath)
def test_version_str_repr(self, load_version, save_version):
"""Test that version is in string representation of the class instance
when applicable."""
filepath = "test.feather"
ds = FeatherDataSet(filepath=filepath)
ds_versioned = FeatherDataSet(
filepath=filepath, version=Version(load_version, save_version)
)
assert filepath in str(ds)
assert "version" not in str(ds)
assert filepath in str(ds_versioned)
ver_str = f"version=Version(load={load_version}, save='{save_version}')"
assert ver_str in str(ds_versioned)
assert "FeatherDataSet" in str(ds_versioned)
assert "FeatherDataSet" in str(ds)
assert "protocol" in str(ds_versioned)
assert "protocol" in str(ds)
def test_protocol_usage(self, filepath, instance_type):
data_set = FeatherDataSet(filepath=filepath)
assert isinstance(data_set._fs, instance_type)
# _strip_protocol() doesn't strip http(s) protocol
if data_set._protocol == "https":
path = filepath.split("://")[-1]
else:
path = data_set._fs._strip_protocol(filepath)
assert str(data_set._filepath) == path
assert isinstance(data_set._filepath, PurePosixPath)
def versioned_feather_data_set(filepath_feather, load_version, save_version):
return FeatherDataSet(
filepath=filepath_feather, version=Version(load_version, save_version)
)
def feather_data_set(filepath_feather, load_args, fs_args):
return FeatherDataSet(
filepath=filepath_feather, load_args=load_args, fs_args=fs_args
)
def test_catalog_release(self, mocker):
fs_mock = mocker.patch("fsspec.filesystem").return_value
filepath = "test.feather"
data_set = FeatherDataSet(filepath=filepath)
data_set.release()
fs_mock.invalidate_cache.assert_called_once_with(filepath)
