in collection_manager/collection_manager/services/history_manager/IngestionHistory.py [0:0]
def _get_standardized_path(file_path: str):
file_path = file_path.strip()
# TODO: Why do we need to record the basename of the path, instead of just the full path?
# The only reason this is here right now is for backwards compatibility to avoid triggering a full reingestion.
if urlparse(file_path).scheme == 's3':
return urlparse(file_path).path.strip("/")
else:
return os.path.basename(file_path)