Rename MSC2716 things from chunk to batch to match /batch_send endpoint

changelog.d/10838.misc

@@ -0,0 +1 @@
+Rename [MSC2716](https://github.com/matrix-org/matrix-doc/pull/2716) fields and event types from `chunk` to `batch` to match the `/batch_send` endpoint.

synapse/api/constants.py

@@ -121,7 +121,7 @@ class EventTypes:
     SpaceParent = "m.space.parent"
 
     MSC2716_INSERTION = "org.matrix.msc2716.insertion"
-    MSC2716_CHUNK = "org.matrix.msc2716.chunk"
+    MSC2716_BATCH = "org.matrix.msc2716.batch"
     MSC2716_MARKER = "org.matrix.msc2716.marker"
 
 
@@ -209,11 +209,11 @@ class EventContentFields:
 
     # Used on normal messages to indicate they were historically imported after the fact
     MSC2716_HISTORICAL = "org.matrix.msc2716.historical"
-    # For "insertion" events to indicate what the next chunk ID should be in
+    # For "insertion" events to indicate what the next batch ID should be in
     # order to connect to it
-    MSC2716_NEXT_CHUNK_ID = "org.matrix.msc2716.next_chunk_id"
-    # Used on "chunk" events to indicate which insertion event it connects to
-    MSC2716_CHUNK_ID = "org.matrix.msc2716.chunk_id"
+    MSC2716_NEXT_BATCH_ID = "org.matrix.msc2716.next_batch_id"
+    # Used on "batch" events to indicate which insertion event it connects to
+    MSC2716_BATCH_ID = "org.matrix.msc2716.batch_id"
     # For "marker" events
     MSC2716_MARKER_INSERTION = "org.matrix.msc2716.marker.insertion"
 

synapse/api/room_versions.py

@@ -244,24 +244,8 @@ class RoomVersions:
         msc2716_historical=False,
         msc2716_redactions=False,
     )
-    MSC2716 = RoomVersion(
-        "org.matrix.msc2716",
-        RoomDisposition.UNSTABLE,
-        EventFormatVersions.V3,
-        StateResolutionVersions.V2,
-        enforce_key_validity=True,
-        special_case_aliases_auth=False,
-        strict_canonicaljson=True,
-        limit_notifications_power_levels=True,
-        msc2176_redaction_rules=False,
-        msc3083_join_rules=False,
-        msc3375_redaction_rules=False,
-        msc2403_knocking=True,
-        msc2716_historical=True,
-        msc2716_redactions=False,
-    )
-    MSC2716v2 = RoomVersion(
-        "org.matrix.msc2716v2",
+    MSC2716v3 = RoomVersion(
+        "org.matrix.msc2716v3",
         RoomDisposition.UNSTABLE,
         EventFormatVersions.V3,
         StateResolutionVersions.V2,
@@ -289,9 +273,9 @@ class RoomVersions:
         RoomVersions.V6,
         RoomVersions.MSC2176,
         RoomVersions.V7,
-        RoomVersions.MSC2716,
         RoomVersions.V8,
         RoomVersions.V9,
+        RoomVersions.MSC2716v3,
     )
 }
 

synapse/event_auth.py

@@ -213,7 +213,7 @@ def check(
 
     if (
         event.type == EventTypes.MSC2716_INSERTION
-        or event.type == EventTypes.MSC2716_CHUNK
+        or event.type == EventTypes.MSC2716_BATCH
         or event.type == EventTypes.MSC2716_MARKER
     ):
         check_historical(room_version_obj, event, auth_events)
@@ -552,14 +552,14 @@ def check_historical(
     auth_events: StateMap[EventBase],
 ) -> None:
     """Check whether the event sender is allowed to send historical related
-    events like "insertion", "chunk", and "marker".
+    events like "insertion", "batch", and "marker".
 
     Returns:
         None
 
     Raises:
         AuthError if the event sender is not allowed to send historical related events
-        ("insertion", "chunk", and "marker").
+        ("insertion", "batch", and "marker").
     """
     # Ignore the auth checks in room versions that do not support historical
     # events
@@ -573,7 +573,7 @@ def check_historical(
     if user_level < historical_level:
         raise AuthError(
             403,
-            'You don\'t have permission to send send historical related events ("insertion", "chunk", and "marker")',
+            'You don\'t have permission to send send historical related events ("insertion", "batch", and "marker")',
         )
 
 

synapse/events/utils.py

@@ -141,9 +141,9 @@ def add_fields(*fields):
     elif event_type == EventTypes.Redaction and room_version.msc2176_redaction_rules:
         add_fields("redacts")
     elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_INSERTION:
-        add_fields(EventContentFields.MSC2716_NEXT_CHUNK_ID)
-    elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_CHUNK:
-        add_fields(EventContentFields.MSC2716_CHUNK_ID)
+        add_fields(EventContentFields.MSC2716_NEXT_BATCH_ID)
+    elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_BATCH:
+        add_fields(EventContentFields.MSC2716_BATCH_ID)
     elif room_version.msc2716_redactions and event_type == EventTypes.MSC2716_MARKER:
         add_fields(EventContentFields.MSC2716_MARKER_INSERTION)
 

synapse/handlers/message.py

@@ -1425,7 +1425,7 @@ async def persist_and_notify_client_event(
                 # structural protocol level).
                 is_msc2716_event = (
                     original_event.type == EventTypes.MSC2716_INSERTION
-                    or original_event.type == EventTypes.MSC2716_CHUNK
+                    or original_event.type == EventTypes.MSC2716_BATCH
                     or original_event.type == EventTypes.MSC2716_MARKER
                 )
                 if not room_version_obj.msc2716_historical and is_msc2716_event:

synapse/rest/client/room_batch.py

@@ -43,25 +43,25 @@
 
 class RoomBatchSendEventRestServlet(RestServlet):
     """
-    API endpoint which can insert a chunk of events historically back in time
+    API endpoint which can insert a batch of events historically back in time
     next to the given `prev_event`.
 
-    `chunk_id` comes from `next_chunk_id `in the response of the batch send
-    endpoint and is derived from the "insertion" events added to each chunk.
+    `batch_id` comes from `next_batch_id `in the response of the batch send
+    endpoint and is derived from the "insertion" events added to each batch.
     It's not required for the first batch send.
 
     `state_events_at_start` is used to define the historical state events
     needed to auth the events like join events. These events will float
     outside of the normal DAG as outlier's and won't be visible in the chat
-    history which also allows us to insert multiple chunks without having a bunch
-    of `@mxid joined the room` noise between each chunk.
+    history which also allows us to insert multiple batches without having a bunch
+    of `@mxid joined the room` noise between each batch.
 
-    `events` is chronological chunk/list of events you want to insert.
-    There is a reverse-chronological constraint on chunks so once you insert
+    `events` is chronological list of events you want to insert.
+    There is a reverse-chronological constraint on batches so once you insert
     some messages, you can only insert older ones after that.
-    tldr; Insert chunks from your most recent history -> oldest history.
+    tldr; Insert batches from your most recent history -> oldest history.
 
-    POST /_matrix/client/unstable/org.matrix.msc2716/rooms/<roomID>/batch_send?prev_event_id=<eventID>&chunk_id=<chunkID>
+    POST /_matrix/client/unstable/org.matrix.msc2716/rooms/<roomID>/batch_send?prev_event_id=<eventID>&batch_id=<batchID>
     {
         "events": [ ... ],
         "state_events_at_start": [ ... ]
@@ -129,7 +129,7 @@ def _create_insertion_event_dict(
         self, sender: str, room_id: str, origin_server_ts: int
     ) -> JsonDict:
         """Creates an event dict for an "insertion" event with the proper fields
-        and a random chunk ID.
+        and a random batch ID.
 
         Args:
             sender: The event author MXID
@@ -140,13 +140,13 @@ def _create_insertion_event_dict(
             The new event dictionary to insert.
         """
 
-        next_chunk_id = random_string(8)
+        next_batch_id = random_string(8)
         insertion_event = {
             "type": EventTypes.MSC2716_INSERTION,
             "sender": sender,
             "room_id": room_id,
             "content": {
-                EventContentFields.MSC2716_NEXT_CHUNK_ID: next_chunk_id,
+                EventContentFields.MSC2716_NEXT_BATCH_ID: next_batch_id,
                 EventContentFields.MSC2716_HISTORICAL: True,
             },
             "origin_server_ts": origin_server_ts,
@@ -191,7 +191,7 @@ async def on_POST(
         prev_event_ids_from_query = parse_strings_from_args(
             request.args, "prev_event_id"
         )
-        chunk_id_from_query = parse_string(request, "chunk_id")
+        batch_id_from_query = parse_string(request, "batch_id")
 
         if prev_event_ids_from_query is None:
             raise SynapseError(
@@ -291,27 +291,27 @@ async def on_POST(
             prev_event_ids_from_query
         )
 
-        # Figure out which chunk to connect to. If they passed in
-        # chunk_id_from_query let's use it. The chunk ID passed in comes
-        # from the chunk_id in the "insertion" event from the previous chunk.
-        last_event_in_chunk = events_to_create[-1]
-        chunk_id_to_connect_to = chunk_id_from_query
+        # Figure out which batch to connect to. If they passed in
+        # batch_id_from_query let's use it. The batch ID passed in comes
+        # from the batch_id in the "insertion" event from the previous batch.
+        last_event_in_batch = events_to_create[-1]
+        batch_id_to_connect_to = batch_id_from_query
         base_insertion_event = None
-        if chunk_id_from_query:
+        if batch_id_from_query:
             #  All but the first base insertion event should point at a fake
             #  event, which causes the HS to ask for the state at the start of
-            #  the chunk later.
+            #  the batch later.
             prev_event_ids = [fake_prev_event_id]
 
-            # Verify the chunk_id_from_query corresponds to an actual insertion event
-            # and have the chunk connected.
+            # Verify the batch_id_from_query corresponds to an actual insertion event
+            # and have the batch connected.
             corresponding_insertion_event_id = (
-                await self.store.get_insertion_event_by_chunk_id(chunk_id_from_query)
+                await self.store.get_insertion_event_by_batch_id(batch_id_from_query)
             )
             if corresponding_insertion_event_id is None:
                 raise SynapseError(
                     400,
-                    "No insertion event corresponds to the given ?chunk_id",
+                    "No insertion event corresponds to the given ?batch_id",
                     errcode=Codes.INVALID_PARAM,
                 )
             pass
@@ -328,7 +328,7 @@ async def on_POST(
             base_insertion_event_dict = self._create_insertion_event_dict(
                 sender=requester.user.to_string(),
                 room_id=room_id,
-                origin_server_ts=last_event_in_chunk["origin_server_ts"],
+                origin_server_ts=last_event_in_batch["origin_server_ts"],
             )
             base_insertion_event_dict["prev_events"] = prev_event_ids.copy()
 
@@ -347,38 +347,38 @@ async def on_POST(
                 depth=inherited_depth,
             )
 
-            chunk_id_to_connect_to = base_insertion_event["content"][
-                EventContentFields.MSC2716_NEXT_CHUNK_ID
+            batch_id_to_connect_to = base_insertion_event["content"][
+                EventContentFields.MSC2716_NEXT_BATCH_ID
             ]
 
-        # Connect this current chunk to the insertion event from the previous chunk
-        chunk_event = {
-            "type": EventTypes.MSC2716_CHUNK,
+        # Connect this current batch to the insertion event from the previous batch
+        batch_event = {
+            "type": EventTypes.MSC2716_BATCH,
             "sender": requester.user.to_string(),
             "room_id": room_id,
             "content": {
-                EventContentFields.MSC2716_CHUNK_ID: chunk_id_to_connect_to,
+                EventContentFields.MSC2716_BATCH_ID: batch_id_to_connect_to,
                 EventContentFields.MSC2716_HISTORICAL: True,
             },
-            # Since the chunk event is put at the end of the chunk,
+            # Since the batch event is put at the end of the batch,
             # where the newest-in-time event is, copy the origin_server_ts from
             # the last event we're inserting
-            "origin_server_ts": last_event_in_chunk["origin_server_ts"],
+            "origin_server_ts": last_event_in_batch["origin_server_ts"],
         }
-        # Add the chunk event to the end of the chunk (newest-in-time)
-        events_to_create.append(chunk_event)
+        # Add the batch event to the end of the batch (newest-in-time)
+        events_to_create.append(batch_event)
 
-        # Add an "insertion" event to the start of each chunk (next to the oldest-in-time
-        # event in the chunk) so the next chunk can be connected to this one.
+        # Add an "insertion" event to the start of each batch (next to the oldest-in-time
+        # event in the batch) so the next batch can be connected to this one.
         insertion_event = self._create_insertion_event_dict(
             sender=requester.user.to_string(),
             room_id=room_id,
-            # Since the insertion event is put at the start of the chunk,
+            # Since the insertion event is put at the start of the batch,
             # where the oldest-in-time event is, copy the origin_server_ts from
             # the first event we're inserting
             origin_server_ts=events_to_create[0]["origin_server_ts"],
         )
-        # Prepend the insertion event to the start of the chunk (oldest-in-time)
+        # Prepend the insertion event to the start of the batch (oldest-in-time)
         events_to_create = [insertion_event] + events_to_create
 
         event_ids = []
@@ -439,17 +439,17 @@ async def on_POST(
             )
 
         insertion_event_id = event_ids[0]
-        chunk_event_id = event_ids[-1]
+        batch_event_id = event_ids[-1]
         historical_event_ids = event_ids[1:-1]
 
         response_dict = {
             "state_event_ids": state_event_ids_at_start,
             "event_ids": historical_event_ids,
-            "next_chunk_id": insertion_event["content"][
-                EventContentFields.MSC2716_NEXT_CHUNK_ID
+            "next_batch_id": insertion_event["content"][
+                EventContentFields.MSC2716_NEXT_BATCH_ID
             ],
             "insertion_event_id": insertion_event_id,
-            "chunk_event_id": chunk_event_id,
+            "batch_event_id": batch_event_id,
         }
         if base_insertion_event is not None:
             response_dict["base_insertion_event_id"] = base_insertion_event.event_id

synapse/storage/databases/main/event_federation.py

@@ -1034,13 +1034,13 @@ def _get_backfill_events(self, txn, room_id, event_list, limit):
             LIMIT ?
         """
 
-        # Find any chunk connections of a given insertion event
-        chunk_connection_query = """
+        # Find any batch connections of a given insertion event
+        batch_connection_query = """
             SELECT e.depth, c.event_id FROM insertion_events AS i
-            /* Find the chunk that connects to the given insertion event */
-            INNER JOIN chunk_events AS c
-            ON i.next_chunk_id = c.chunk_id
-            /* Get the depth of the chunk start event from the events table */
+            /* Find the batch that connects to the given insertion event */
+            INNER JOIN batch_events AS c
+            ON i.next_batch_id = c.batch_id
+            /* Get the depth of the batch start event from the events table */
             INNER JOIN events AS e USING (event_id)
             /* Find an insertion event which matches the given event_id */
             WHERE i.event_id = ?
@@ -1077,12 +1077,12 @@ def _get_backfill_events(self, txn, room_id, event_list, limit):
 
             event_results.add(event_id)
 
-            # Try and find any potential historical chunks of message history.
+            # Try and find any potential historical batches of message history.
             #
             # First we look for an insertion event connected to the current
             # event (by prev_event). If we find any, we need to go and try to
-            # find any chunk events connected to the insertion event (by
-            # chunk_id). If we find any, we'll add them to the queue and
+            # find any batch events connected to the insertion event (by
+            # batch_id). If we find any, we'll add them to the queue and
             # navigate up the DAG like normal in the next iteration of the loop.
             txn.execute(
                 connected_insertion_event_query, (event_id, limit - len(event_results))
@@ -1097,17 +1097,17 @@ def _get_backfill_events(self, txn, room_id, event_list, limit):
                 connected_insertion_event = row[1]
                 queue.put((-connected_insertion_event_depth, connected_insertion_event))
 
-                # Find any chunk connections for the given insertion event
+                # Find any batch connections for the given insertion event
                 txn.execute(
-                    chunk_connection_query,
+                    batch_connection_query,
                     (connected_insertion_event, limit - len(event_results)),
                 )
-                chunk_start_event_id_results = txn.fetchall()
+                batch_start_event_id_results = txn.fetchall()
                 logger.debug(
-                    "_get_backfill_events: chunk_start_event_id_results %s",
-                    chunk_start_event_id_results,
+                    "_get_backfill_events: batch_start_event_id_results %s",
+                    batch_start_event_id_results,
                 )
-                for row in chunk_start_event_id_results:
+                for row in batch_start_event_id_results:
                     if row[1] not in event_results:
                         queue.put((-row[0], row[1]))