This proposal would give a public API for reading and writing stream state for a Cache interface.
Signature might be something like:
class CacheBase:
...
def get_state(
stream_name: str,
) -> StreamState | None:
"""Return a stream state object for the provided stream name.
This is a thin wrapper around the internal `StateProvider` interface.
"""
...
def set_state(
stream_name: str,
stream_state: StreamState | dict,
) -> None:
"""Set a stream state object for the provided stream name.
This is a thin wrapper around the internal `StateWriter` interface.
"""
...
def migrate_state(
streams: list[str] | Literal["*"],
to_cache: CacheBase,
) -> None:
"""Copies all matching stream states to the specified `Cache` object.
This is a thin wrapper around the respective `Cache` objects'
`get_state` and `set_state` methods.
"""
...
Other considerations:
- Since there are as of now many different strongly typed
State classes (StateMessage, StreamState, etc.), we'd want to think carefully on which (if any) we feel comfortable to make a part of the public interface.
- It might actually be cleaner to get/set values as
dict objects, since that would fully avoid needing to expose a public API for the state object itself. (Tradeoff: dict objects may be difficult to parse.)
- It should be noted that manually modifying a
state artifact for a stream basically always "voids the warranty", and sources and not guaranteed to have stable state artifact interfaces over time.
- This feature is actually more appropriate for migration of state - such as during renames or moving from one state backend to another, or from one table name/alias to a new one. For this reason, I've included a possible
migrate_state() method in the above which could streamline a "copy-all"-type operation.
- Internally, states are often cached in memory by the
StateProvider class. We'd need to take care to invalidate or refresh the caches after a "set" action.
This proposal would give a public API for reading and writing stream state for a
Cacheinterface.Signature might be something like:
Other considerations:
Stateclasses (StateMessage,StreamState, etc.), we'd want to think carefully on which (if any) we feel comfortable to make a part of the public interface.dictobjects, since that would fully avoid needing to expose a public API for the state object itself. (Tradeoff:dictobjects may be difficult to parse.)stateartifact for a stream basically always "voids the warranty", and sources and not guaranteed to have stablestateartifact interfaces over time.migrate_state()method in the above which could streamline a "copy-all"-type operation.StateProviderclass. We'd need to take care to invalidate or refresh the caches after a "set" action.