def _is_accessible(path, config):
if path is None:
return True
try:
dl = DataLocator(path,
region_name=config.data_locator__s3__region_name)
return dl.exists()
except RuntimeError:
return False
@staticmethod
def get_csp_hashes(app, app_config):
script_hashes, style_hashes = WSGIServer.load_static_csp_hashes(app)
script_hashes += WSGIServer.compute_inline_scp_hashes(app, app_config)
return (script_hashes, style_hashes)
try:
app_config = AppConfig()
has_config = False
# config file: look first for "config.yaml" in the current working directory
config_file = "config.yaml"
config_location = DataLocator(config_file)
if config_location.exists():
with config_location.local_handle() as lh:
logging.info(f"Configuration from {config_file}")
app_config.update_from_config_file(lh)
has_config = True
else:
# config file: second, use the CXG_CONFIG_FILE
config_file = os.getenv("CXG_CONFIG_FILE")
if config_file:
region_name = discover_s3_region_name(config_file)
config_location = DataLocator(config_file, region_name)
if config_location.exists():
with config_location.local_handle() as lh:
logging.info(f"Configuration from {config_file}")
app_config.update_from_config_file(lh)
class MatrixDataLoader(object):
def __init__(self, location, matrix_data_type=None, app_config=None):
""" location can be a string or DataLocator """
region_name = None if app_config is None else app_config.server_config.data_locator__s3__region_name
self.location = DataLocator(location, region_name=region_name)
if not self.location.exists():
raise DatasetAccessError("Dataset does not exist.",
HTTPStatus.NOT_FOUND)
# matrix_data_type is an enum value of type MatrixDataType
self.matrix_data_type = matrix_data_type
# matrix_type is a DataAdaptor type, which corresonds to the matrix_data_type
self.matrix_type = None
if matrix_data_type is None:
self.matrix_data_type = self.__matrix_data_type()
if not self.__matrix_data_type_allowed(app_config):
raise DatasetAccessError("Dataset does not have an allowed type.")
if self.matrix_data_type == MatrixDataType.H5AD:
from server.data_anndata.anndata_adaptor import AnndataAdaptor
self.matrix_type = AnndataAdaptor
elif self.matrix_data_type == MatrixDataType.CXG:
from server.data_cxg.cxg_adaptor import CxgAdaptor
self.matrix_type = CxgAdaptor
def __matrix_data_type(self):
if self.location.path.endswith(".h5ad"):
return MatrixDataType.H5AD
elif ".cxg" in self.location.path:
return MatrixDataType.CXG
else:
return MatrixDataType.UNKNOWN
def __matrix_data_type_allowed(self, app_config):
if self.matrix_data_type == MatrixDataType.UNKNOWN:
return False
if not app_config:
return True
if not app_config.is_multi_dataset():
return True
if len(app_config.server_config.multi_dataset__allowed_matrix_types
) == 0:
return True
for val in app_config.server_config.multi_dataset__allowed_matrix_types:
try:
if self.matrix_data_type == MatrixDataType(val):
return True
except ValueError:
# Check case where multi_dataset_allowed_matrix_type does not have a
# valid MatrixDataType value. TODO: Add a feature to check
# the AppConfig for errors on startup
return False
return False
def pre_load_validation(self):
if self.matrix_data_type == MatrixDataType.UNKNOWN:
raise DatasetAccessError(
"Dataset does not have a recognized type: .h5ad or .cxg")
self.matrix_type.pre_load_validation(self.location)
def file_size(self):
return self.matrix_type.file_size(self.location)
def open(self, app_config, dataset_config=None):
# create and return a DataAdaptor object
return self.matrix_type.open(self.location, app_config, dataset_config)