Store room_versions in EventBase objects (#6875)

This is a bit fiddly because it all has to be done on one fell swoop:

* Wherever we create a new event, pass in the room version (and check it matches the format version)
* When we prune an event, use the room version of the unpruned event to create the pruned version.
* When we pass an event over the replication protocol, pass the room version over alongside it, and use it when deserialising the event again.

2 files changed, 43 insertions, 24 deletions

diff --git a/synapse/events/__init__.py b/synapse/events/__init__.py
index 7307116556..533ba327f5 100644
--- a/synapse/events/__init__.py
+++ b/synapse/events/__init__.py
@@ -15,9 +15,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import abc
 import os
 from distutils.util import strtobool
-from typing import Optional, Type
+from typing import Dict, Optional, Type
 
 import six
 
@@ -199,15 +200,25 @@ class _EventInternalMetadata(object):
         return self._dict.get("redacted", False)
 
 
-class EventBase(object):
+class EventBase(metaclass=abc.ABCMeta):
+    @property
+    @abc.abstractmethod
+    def format_version(self) -> int:
+        """The EventFormatVersion implemented by this event"""
+        ...
+
     def __init__(
         self,
-        event_dict,
-        signatures={},
-        unsigned={},
-        internal_metadata_dict={},
-        rejected_reason=None,
+        event_dict: JsonDict,
+        room_version: RoomVersion,
+        signatures: Dict[str, Dict[str, str]],
+        unsigned: JsonDict,
+        internal_metadata_dict: JsonDict,
+        rejected_reason: Optional[str],
     ):
+        assert room_version.event_format == self.format_version
+
+        self.room_version = room_version
         self.signatures = signatures
         self.unsigned = unsigned
         self.rejected_reason = rejected_reason
@@ -303,7 +314,13 @@ class EventBase(object):
 class FrozenEvent(EventBase):
     format_version = EventFormatVersions.V1  # All events of this type are V1
 
-    def __init__(self, event_dict, internal_metadata_dict={}, rejected_reason=None):
+    def __init__(
+        self,
+        event_dict: JsonDict,
+        room_version: RoomVersion,
+        internal_metadata_dict: JsonDict = {},
+        rejected_reason: Optional[str] = None,
+    ):
         event_dict = dict(event_dict)
 
         # Signatures is a dict of dicts, and this is faster than doing a
@@ -326,8 +343,9 @@ class FrozenEvent(EventBase):
 
         self._event_id = event_dict["event_id"]
 
-        super(FrozenEvent, self).__init__(
+        super().__init__(
             frozen_dict,
+            room_version=room_version,
             signatures=signatures,
             unsigned=unsigned,
             internal_metadata_dict=internal_metadata_dict,
@@ -352,7 +370,13 @@ class FrozenEvent(EventBase):
 class FrozenEventV2(EventBase):
     format_version = EventFormatVersions.V2  # All events of this type are V2
 
-    def __init__(self, event_dict, internal_metadata_dict={}, rejected_reason=None):
+    def __init__(
+        self,
+        event_dict: JsonDict,
+        room_version: RoomVersion,
+        internal_metadata_dict: JsonDict = {},
+        rejected_reason: Optional[str] = None,
+    ):
         event_dict = dict(event_dict)
 
         # Signatures is a dict of dicts, and this is faster than doing a
@@ -377,8 +401,9 @@ class FrozenEventV2(EventBase):
 
         self._event_id = None
 
-        super(FrozenEventV2, self).__init__(
+        super().__init__(
             frozen_dict,
+            room_version=room_version,
             signatures=signatures,
             unsigned=unsigned,
             internal_metadata_dict=internal_metadata_dict,
@@ -445,7 +470,7 @@ class FrozenEventV3(FrozenEventV2):
         return self._event_id
 
 
-def event_type_from_format_version(format_version: int) -> Type[EventBase]:
+def _event_type_from_format_version(format_version: int) -> Type[EventBase]:
     """Returns the python type to use to construct an Event object for the
     given event format version.
 
@@ -474,5 +499,5 @@ def make_event_from_dict(
     rejected_reason: Optional[str] = None,
 ) -> EventBase:
     """Construct an EventBase from the given event dict"""
-    event_type = event_type_from_format_version(room_version.event_format)
-    return event_type(event_dict, internal_metadata_dict, rejected_reason)
+    event_type = _event_type_from_format_version(room_version.event_format)
+    return event_type(event_dict, room_version, internal_metadata_dict, rejected_reason)
diff --git a/synapse/events/utils.py b/synapse/events/utils.py
index f70f5032fb..bc6f98ae3b 100644
--- a/synapse/events/utils.py
+++ b/synapse/events/utils.py
@@ -35,26 +35,20 @@ from . import EventBase
 SPLIT_FIELD_REGEX = re.compile(r"(?<!\\)\.")
 
 
-def prune_event(event):
+def prune_event(event: EventBase) -> EventBase:
     """ Returns a pruned version of the given event, which removes all keys we
     don't know about or think could potentially be dodgy.
 
     This is used when we "redact" an event. We want to remove all fields that
     the user has specified, but we do want to keep necessary information like
     type, state_key etc.
-
-    Args:
-        event (FrozenEvent)
-
-    Returns:
-        FrozenEvent
     """
     pruned_event_dict = prune_event_dict(event.get_dict())
 
-    from . import event_type_from_format_version
+    from . import make_event_from_dict
 
-    pruned_event = event_type_from_format_version(event.format_version)(
-        pruned_event_dict, event.internal_metadata.get_dict()
+    pruned_event = make_event_from_dict(
+        pruned_event_dict, event.room_version, event.internal_metadata.get_dict()
     )
 
     # Mark the event as redacted