Consistently exclude from user_directory (#10960)

* Introduce `should_include_local_users_in_dir`

We exclude three kinds of local users from the user_directory tables. At
present we don't consistently exclude all three in the same places. This
commit introduces a new function to gather those exclusion conditions
together. Because we have to handle local and remote users in different
ways, I've made that function only consider the case of remote users.
It's the caller's responsibility to make the local versus remote
distinction clear and correct.

A test fixup is required. The test now hits a path which makes db
queries against the users table. The expected rows were missing, because
we were using a dummy user that hadn't actually been registered.

We also add new test cases to covert the exclusion logic.

----

By my reading this makes these changes:

* When an app service user registers or changes their profile, they will
  _not_ be added to the user directory. (Previously only support and
  deactivated users were excluded). This is consistent with the logic that
  rebuilds the user directory. See also [the discussion
  here](https://github.com/matrix-org/synapse/pull/10914#discussion_r716859548).
* When rebuilding the directory, exclude support and disabled users from
  room sharing tables. Previously only appservice users were excluded.
* Exclude all three categories of local users when rebuilding the
  directory. Previously `_populate_user_directory_process_users` didn't do
  any exclusion.

Co-authored-by: Richard van der Hoff <1389908+richvdh@users.noreply.github.com>

synapse/storage/databases/main/user_directory.py

@@ -40,12 +40,10 @@ from synapse.util.caches.descriptors import cached
 
 logger = logging.getLogger(__name__)
 
-
 TEMP_TABLE = "_temp_populate_user_directory"
 
 
 class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
-
     # How many records do we calculate before sending it to
     # add_users_who_share_private_rooms?
     SHARE_PRIVATE_WORKING_SET = 500
@@ -235,6 +233,13 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
                 )
 
                 users_with_profile = await self.get_users_in_room_with_profiles(room_id)
+                # Throw away users excluded from the directory.
+                users_with_profile = {
+                    user_id: profile
+                    for user_id, profile in users_with_profile.items()
+                    if not self.hs.is_mine_id(user_id)
+                    or await self.should_include_local_user_in_dir(user_id)
+                }
 
                 # Update each user in the user directory.
                 for user_id, profile in users_with_profile.items():
@@ -246,9 +251,6 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
 
                 if is_public:
                     for user_id in users_with_profile:
-                        if self.get_if_app_services_interested_in_user(user_id):
-                            continue
-
                         to_insert.add(user_id)
 
                     if to_insert:
@@ -256,12 +258,12 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
                         to_insert.clear()
                 else:
                     for user_id in users_with_profile:
+                        # We want the set of pairs (L, M) where L and M are
+                        # in `users_with_profile` and L is local.
+                        # Do so by looking for the local user L first.
                         if not self.hs.is_mine_id(user_id):
                             continue
 
-                        if self.get_if_app_services_interested_in_user(user_id):
-                            continue
-
                         for other_user_id in users_with_profile:
                             if user_id == other_user_id:
                                 continue
@@ -349,10 +351,11 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
         )
 
         for user_id in users_to_work_on:
-            profile = await self.get_profileinfo(get_localpart_from_id(user_id))
-            await self.update_profile_in_user_dir(
-                user_id, profile.display_name, profile.avatar_url
-            )
+            if await self.should_include_local_user_in_dir(user_id):
+                profile = await self.get_profileinfo(get_localpart_from_id(user_id))
+                await self.update_profile_in_user_dir(
+                    user_id, profile.display_name, profile.avatar_url
+                )
 
             # We've finished processing a user. Delete it from the table.
             await self.db_pool.simple_delete_one(
@@ -369,6 +372,24 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
 
         return len(users_to_work_on)
 
+    async def should_include_local_user_in_dir(self, user: str) -> bool:
+        """Certain classes of local user are omitted from the user directory.
+        Is this user one of them?
+        """
+        # App service users aren't usually contactable, so exclude them.
+        if self.get_if_app_services_interested_in_user(user):
+            # TODO we might want to make this configurable for each app service
+            return False
+
+        # Support users are for diagnostics and should not appear in the user directory.
+        if await self.is_support_user(user):
+            return False
+
+        # Deactivated users aren't contactable, so should not appear in the user directory.
+        if await self.get_user_deactivated_status(user):
+            return False
+        return True
+
     async def is_room_world_readable_or_publicly_joinable(self, room_id: str) -> bool:
         """Check if the room is either world_readable or publically joinable"""
 
@@ -537,7 +558,6 @@ class UserDirectoryBackgroundUpdateStore(StateDeltasStore):
 
 
 class UserDirectoryStore(UserDirectoryBackgroundUpdateStore):
-
     # How many records do we calculate before sending it to
     # add_users_who_share_private_rooms?
     SHARE_PRIVATE_WORKING_SET = 500