A common pattern in the current schema is to use a List of generic objects to keep track of such objects. For instance, cameras can be expressed as follows:
https://github.com/AllenNeuralDynamics/aind-data-schema/blob/c8aca0341d86efc82aa32ba0255b1f66287a4a3c/src/aind_data_schema/rig.py#L64C1
While easy to use, Lists make grabbing a specific device somewhat difficult without parsing all objects since they must be indexed by the order (which can easily change across days) or the experimenter must generate somesort of keyed collection type with an unique key (e.g. device name).
I wonder if rather than using generic unsorted lists, it would be beneficial to simply use some sort of hashed dictionary structure in the form of Dict[str, CameraAssembly] instead of List[CameraAssembly]. This would make it much easier to access the objects after deserialization.
A common pattern in the current schema is to use a
Listof generic objects to keep track of such objects. For instance, cameras can be expressed as follows:https://github.com/AllenNeuralDynamics/aind-data-schema/blob/c8aca0341d86efc82aa32ba0255b1f66287a4a3c/src/aind_data_schema/rig.py#L64C1
While easy to use,
Lists make grabbing a specific device somewhat difficult without parsing all objects since they must be indexed by the order (which can easily change across days) or the experimenter must generate somesort of keyed collection type with an unique key (e.g. device name).I wonder if rather than using generic unsorted lists, it would be beneficial to simply use some sort of hashed dictionary structure in the form of
Dict[str, CameraAssembly]instead ofList[CameraAssembly]. This would make it much easier to access the objects after deserialization.