def test_http_filesystem_no_versioning(self):
pattern = r"HTTP\(s\) DataSet doesn't support versioning\."
with pytest.raises(DataSetError, match=pattern):
ImageDataSet(
filepath="https://example.com/file.png", version=Version(None, None)
)
def test_protocol_usage(self, filepath, instance_type):
data_set = ImageDataSet(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 = "/tmp/test.png"
ds = ImageDataSet(filepath=filepath)
ds_versioned = ImageDataSet(filepath=filepath,
version=Version(load_version,
save_version))
assert filepath in str(ds)
assert filepath in str(ds_versioned)
assert "version" not in str(ds)
ver_str = f"version=Version(load={load_version}, save='{save_version}')"
assert ver_str in str(ds_versioned)
assert "ImageDataSet" in str(ds_versioned)
assert "ImageDataSet" in str(ds)
assert "protocol" in str(ds_versioned)
assert "protocol" in str(ds)
def test_multiple_loads(self, versioned_image_dataset, image_object,
filepath_png):
"""Test that if a new version is created mid-run, by an
external system, it won't be loaded in the current run."""
versioned_image_dataset.save(image_object)
v1 = versioned_image_dataset.resolve_load_version()
# force-drop a newer version into the same location
v_new = generate_timestamp()
ImageDataSet(filepath=filepath_png,
version=Version(v_new, v_new)).save(image_object)
v2 = versioned_image_dataset.resolve_load_version()
assert v2 == v1 # v2 should not be v_new!
ds_new = ImageDataSet(filepath=filepath_png,
version=Version(None, None))
assert (ds_new.resolve_load_version() == v_new
) # new version is discoverable by a new instance
def test_protocol_usage(self, filepath, instance_type):
data_set = ImageDataSet(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_image_dataset(filepath_png, load_version, save_version):
return ImageDataSet(filepath=filepath_png,
version=Version(load_version, save_version))
def image_dataset(filepath_png, save_args, fs_args):
return ImageDataSet(filepath=filepath_png,
save_args=save_args,
fs_args=fs_args)
def test_catalog_release(self, mocker):
fs_mock = mocker.patch("fsspec.filesystem").return_value
filepath = "test.png"
data_set = ImageDataSet(filepath=filepath)
data_set.release()
fs_mock.invalidate_cache.assert_called_once_with(filepath)
def affiche_image(rawda):
data_set = ImageDataSet(filepath="data/01_raw/elephant.jpg")
image = data_set.load()
image.show()
