Add is_dm filtering to Sliding Sync /sync

changelog.d/17277.feature

@@ -0,0 +1 @@
+Add `is_dm` filtering to experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint.

synapse/handlers/sliding_sync.py

@@ -31,7 +31,7 @@
 else:
     from pydantic import Extra
 
-from synapse.api.constants import Membership
+from synapse.api.constants import AccountDataTypes, Membership
 from synapse.events import EventBase
 from synapse.rest.client.models import SlidingSyncBody
 from synapse.types import JsonMapping, Requester, RoomStreamToken, StreamToken, UserID
@@ -332,11 +332,15 @@ async def current_sync_for_user(
         lists: Dict[str, SlidingSyncResult.SlidingWindowList] = {}
         if sync_config.lists:
             for list_key, list_config in sync_config.lists.items():
-                # TODO: Apply filters
-                #
-                # TODO: Exclude partially stated rooms unless the `required_state` has
-                # `["m.room.member", "$LAZY"]`
+                # Apply filters
                 filtered_room_ids = room_id_set
+                if list_config.filters is not None:
+                    # TODO: To be absolutely correct, this could also take into account
+                    # from/to tokens but some of the streams don't support looking back
+                    # in time (like global account_data).
+                    filtered_room_ids = await self.filter_rooms(
+                        sync_config.user, room_id_set, list_config.filters
+                    )
                 # TODO: Apply sorts
                 sorted_room_ids = sorted(filtered_room_ids)
 
@@ -608,3 +612,74 @@ async def get_sync_room_ids_for_user(
                 sync_room_id_set.add(room_id)
 
         return sync_room_id_set
+
+    async def filter_rooms(
+        self,
+        user: UserID,
+        room_id_set: AbstractSet[str],
+        filters: SlidingSyncConfig.SlidingSyncList.Filters,
+    ) -> AbstractSet[str]:
+        """
+        Filter rooms based on the sync request.
+        """
+        user_id = user.to_string()
+
+        # TODO: Apply filters
+        #
+        # TODO: Exclude partially stated rooms unless the `required_state` has
+        # `["m.room.member", "$LAZY"]`
+
+        filtered_room_id_set = set(room_id_set)
+
+        # Filter for Direct-Message (DM) rooms
+        if filters.is_dm is not None:
+            # We're using global account data (`m.direct`) instead of checking for
+            # `is_direct` on membership events because that property only appears for
+            # the invitee membership event (doesn't show up for the inviter). Account
+            # data is set by the client so it needs to be scrutinized.
+            dm_map = await self.store.get_global_account_data_by_type_for_user(
+                user_id, AccountDataTypes.DIRECT
+            )
+            logger.warn("dm_map: %s", dm_map)
+            # Flatten out the map
+            dm_room_id_set = set()
+            if dm_map:
+                for room_ids in dm_map.values():
+                    # Account data should be a list of room IDs. Ignore anything else
+                    if isinstance(room_ids, list):
+                        for room_id in room_ids:
+                            if isinstance(room_id, str):
+                                dm_room_id_set.add(room_id)
+
+            if filters.is_dm:
+                # Only DM rooms please
+                filtered_room_id_set = filtered_room_id_set.intersection(dm_room_id_set)
+            else:
+                # Only non-DM rooms please
+                filtered_room_id_set = filtered_room_id_set.difference(dm_room_id_set)
+
+        if filters.spaces:
+            raise NotImplementedError()
+
+        if filters.is_encrypted:
+            raise NotImplementedError()
+
+        if filters.is_invite:
+            raise NotImplementedError()
+
+        if filters.room_types:
+            raise NotImplementedError()
+
+        if filters.not_room_types:
+            raise NotImplementedError()
+
+        if filters.room_name_like:
+            raise NotImplementedError()
+
+        if filters.tags:
+            raise NotImplementedError()
+
+        if filters.not_tags:
+            raise NotImplementedError()
+
+        return filtered_room_id_set

synapse/rest/client/models.py

@@ -238,6 +238,53 @@ class SlidingSyncList(CommonRoomParameters):
         """
 
         class Filters(RequestBodyModel):
+            """
+            All fields are applied with AND operators, hence if `is_dm: True` and
+            `is_encrypted: True` then only Encrypted DM rooms will be returned. The
+            absence of fields implies no filter on that criteria: it does NOT imply
+            `False`. These fields may be expanded through use of extensions.
+
+            Attributes:
+                is_dm: Flag which only returns rooms present (or not) in the DM section
+                    of account data. If unset, both DM rooms and non-DM rooms are returned.
+                    If False, only non-DM rooms are returned. If True, only DM rooms are
+                    returned.
+                spaces: Filter the room based on the space they belong to according to
+                    `m.space.child` state events. If multiple spaces are present, a room can
+                    be part of any one of the listed spaces (OR'd). The server will inspect
+                    the `m.space.child` state events for the JOINED space room IDs given.
+                    Servers MUST NOT navigate subspaces. It is up to the client to give a
+                    complete list of spaces to navigate. Only rooms directly mentioned as
+                    `m.space.child` events in these spaces will be returned. Unknown spaces
+                    or spaces the user is not joined to will be ignored.
+                is_encrypted: Flag which only returns rooms which have an
+                    `m.room.encryption` state event. If unset, both encrypted and
+                    unencrypted rooms are returned. If `False`, only unencrypted rooms are
+                    returned. If `True`, only encrypted rooms are returned.
+                is_invite: Flag which only returns rooms the user is currently invited
+                    to. If unset, both invited and joined rooms are returned. If `False`, no
+                    invited rooms are returned. If `True`, only invited rooms are returned.
+                room_types: If specified, only rooms where the `m.room.create` event has
+                    a `type` matching one of the strings in this array will be returned. If
+                    this field is unset, all rooms are returned regardless of type. This can
+                    be used to get the initial set of spaces for an account. For rooms which
+                    do not have a room type, use `null`/`None` to include them.
+                not_room_types: Same as `room_types` but inverted. This can be used to
+                    filter out spaces from the room list. If a type is in both `room_types`
+                    and `not_room_types`, then `not_room_types` wins and they are not included
+                    in the result.
+                room_name_like: Filter the room name. Case-insensitive partial matching
+                    e.g 'foo' matches 'abFooab'. The term 'like' is inspired by SQL 'LIKE',
+                    and the text here is similar to '%foo%'.
+                tags: Filter the room based on its room tags. If multiple tags are
+                    present, a room can have any one of the listed tags (OR'd).
+                not_tags: Filter the room based on its room tags. Takes priority over
+                    `tags`. For example, a room with tags A and B with filters `tags: [A]`
+                    `not_tags: [B]` would NOT be included because `not_tags` takes priority over
+                    `tags`. This filter is useful if your rooms list does NOT include the
+                    list of favourite rooms again.
+            """
+
             is_dm: Optional[StrictBool] = None
             spaces: Optional[List[StrictStr]] = None
             is_encrypted: Optional[StrictBool] = None

tests/handlers/test_sliding_sync.py

@@ -22,7 +22,7 @@
 
 from twisted.test.proto_helpers import MemoryReactor
 
-from synapse.api.constants import EventTypes, JoinRules, Membership
+from synapse.api.constants import AccountDataTypes, EventTypes, JoinRules, Membership
 from synapse.api.room_versions import RoomVersions
 from synapse.rest import admin
 from synapse.rest.client import knock, login, room
@@ -1116,3 +1116,157 @@ def test_sharded_event_persisters(self) -> None:
                 room_id3,
             },
         )
+
+
+class FilterRoomsTestCase(HomeserverTestCase):
+    """
+    Tests Sliding Sync handler `filter_rooms()` to make sure it includes/excludes rooms
+    correctly.
+    """
+
+    servlets = [
+        admin.register_servlets,
+        knock.register_servlets,
+        login.register_servlets,
+        room.register_servlets,
+    ]
+
+    def default_config(self) -> JsonDict:
+        config = super().default_config()
+        # Enable sliding sync
+        config["experimental_features"] = {"msc3575_enabled": True}
+        return config
+
+    def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
+        self.sliding_sync_handler = self.hs.get_sliding_sync_handler()
+        self.store = self.hs.get_datastores().main
+
+    def _create_dm_room(
+        self,
+        inviter_user_id: str,
+        inviter_tok: str,
+        invitee_user_id: str,
+        invitee_tok: str,
+    ) -> str:
+        """
+        Helper to create a DM room as the "inviter" and invite the "invitee" user to the room. The
+        "invitee" user also will join the room. The `m.direct` account data will be set
+        for both users.
+        """
+
+        # Create a room and send an invite the other user
+        room_id = self.helper.create_room_as(
+            inviter_user_id,
+            is_public=False,
+            tok=inviter_tok,
+        )
+        self.helper.invite(
+            room_id,
+            src=inviter_user_id,
+            targ=invitee_user_id,
+            tok=inviter_tok,
+            extra_data={"is_direct": True},
+        )
+        # Person that was invited joins the room
+        self.helper.join(room_id, invitee_user_id, tok=invitee_tok)
+
+        # Mimic the client setting the room as a direct message in the global account
+        # data
+        self.get_success(
+            self.store.add_account_data_for_user(
+                invitee_user_id,
+                AccountDataTypes.DIRECT,
+                {inviter_user_id: [room_id]},
+            )
+        )
+        self.get_success(
+            self.store.add_account_data_for_user(
+                inviter_user_id,
+                AccountDataTypes.DIRECT,
+                {invitee_user_id: [room_id]},
+            )
+        )
+
+        return room_id
+
+    def test_filter_dm_rooms(self) -> None:
+        """
+        Test filter for DM rooms
+        """
+        user1_id = self.register_user("user1", "pass")
+        user1_tok = self.login(user1_id, "pass")
+        user2_id = self.register_user("user2", "pass")
+        user2_tok = self.login(user2_id, "pass")
+
+        # Create a normal room
+        room_id = self.helper.create_room_as(
+            user1_id,
+            is_public=False,
+            tok=user1_tok,
+        )
+
+        # Create a DM room
+        dm_room_id = self._create_dm_room(
+            inviter_user_id=user1_id,
+            inviter_tok=user1_tok,
+            invitee_user_id=user2_id,
+            invitee_tok=user2_tok,
+        )
+
+        # TODO: Better way to avoid the circular import? (see
+        # https://github.com/element-hq/synapse/pull/17187#discussion_r1619492779)
+        from synapse.handlers.sliding_sync import SlidingSyncConfig
+
+        filters = SlidingSyncConfig.SlidingSyncList.Filters(
+            is_dm=True,
+        )
+
+        # Try filtering the rooms
+        filtered_room_ids = self.get_success(
+            self.sliding_sync_handler.filter_rooms(
+                UserID.from_string(user1_id), {room_id, dm_room_id}, filters
+            )
+        )
+
+        self.assertEqual(filtered_room_ids, {dm_room_id})
+
+    def test_filter_non_dm_rooms(self) -> None:
+        """
+        Test filter for non-DM rooms
+        """
+        user1_id = self.register_user("user1", "pass")
+        user1_tok = self.login(user1_id, "pass")
+        user2_id = self.register_user("user2", "pass")
+        user2_tok = self.login(user2_id, "pass")
+
+        # Create a normal room
+        room_id = self.helper.create_room_as(
+            user1_id,
+            is_public=False,
+            tok=user1_tok,
+        )
+
+        # Create a DM room
+        dm_room_id = self._create_dm_room(
+            inviter_user_id=user1_id,
+            inviter_tok=user1_tok,
+            invitee_user_id=user2_id,
+            invitee_tok=user2_tok,
+        )
+
+        # TODO: Better way to avoid the circular import? (see
+        # https://github.com/element-hq/synapse/pull/17187#discussion_r1619492779)
+        from synapse.handlers.sliding_sync import SlidingSyncConfig
+
+        filters = SlidingSyncConfig.SlidingSyncList.Filters(
+            is_dm=False,
+        )
+
+        # Try filtering the rooms
+        filtered_room_ids = self.get_success(
+            self.sliding_sync_handler.filter_rooms(
+                UserID.from_string(user1_id), {room_id, dm_room_id}, filters
+            )
+        )
+
+        self.assertEqual(filtered_room_ids, {room_id})