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.xlsx"
ds = ExcelDataSet(filepath=filepath)
ds_versioned = ExcelDataSet(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 = "version=Version(load={}, save='{}')".format(
load_version, save_version)
assert ver_str in str(ds_versioned)
assert "ExcelDataSet" in str(ds_versioned)
assert "ExcelDataSet" in str(ds)
assert "protocol" in str(ds_versioned)
assert "protocol" in str(ds)
assert "writer_args" in str(ds_versioned)
assert "writer_args" in str(ds)
# Default save_args and load_args
assert "save_args={'index': False}" in str(ds)
assert "save_args={'index': False}" in str(ds_versioned)
assert "load_args={'engine': xlrd}" in str(ds_versioned)
assert "load_args={'engine': xlrd}" in str(ds)
def excel_data_set(filepath_excel, load_args, save_args, fs_args):
return ExcelDataSet(
filepath=filepath_excel,
load_args=load_args,
save_args=save_args,
fs_args=fs_args,
)
def test_http_filesystem_no_versioning(self):
pattern = r"HTTP\(s\) DataSet doesn't support versioning\."
with pytest.raises(DataSetError, match=pattern):
ExcelDataSet(
filepath="https://example.com/file.xlsx", version=Version(None, None)
)
def test_protocol_usage(self, filepath, instance_type):
data_set = ExcelDataSet(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 excel_multisheet_data_set(filepath_excel, save_args, fs_args):
load_args = {"sheet_name": None}
return ExcelDataSet(
filepath=filepath_excel,
load_args=load_args,
save_args=save_args,
fs_args=fs_args,
)
def test_protocol_usage(self, filepath, instance_type):
data_set = ExcelDataSet(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 setup_excel_dataset(path):
excel_dataset = ExcelDataSet(path)
df = pd.DataFrame({"col1": [1, 2]})
excel_dataset.save(df)
return excel_dataset, df
def versioned_excel_data_set(filepath_excel, load_version, save_version):
return ExcelDataSet(filepath=filepath_excel,
version=Version(load_version, save_version))
def test_catalog_release(self, mocker):
fs_mock = mocker.patch("fsspec.filesystem").return_value
filepath = "test.xlsx"
data_set = ExcelDataSet(filepath=filepath)
data_set.release()
fs_mock.invalidate_cache.assert_called_once_with(filepath)