Filter the results of user directory searching via the spam checker (#6888)

Add a method to the spam checker to filter the user directory results.

synapse/events/spamcheck.py

@@ -15,6 +15,7 @@
 # limitations under the License.
 
 import inspect
+from typing import Dict
 
 from synapse.spam_checker_api import SpamCheckerApi
 
@@ -125,3 +126,29 @@ class SpamChecker(object):
             return True
 
         return self.spam_checker.user_may_publish_room(userid, room_id)
+
+    def check_username_for_spam(self, user_profile: Dict[str, str]) -> bool:
+        """Checks if a user ID or display name are considered "spammy" by this server.
+
+        If the server considers a username spammy, then it will not be included in
+        user directory results.
+
+        Args:
+            user_profile: The user information to check, it contains the keys:
+                * user_id
+                * display_name
+                * avatar_url
+
+        Returns:
+            True if the user is spammy.
+        """
+        if self.spam_checker is None:
+            return False
+
+        # For backwards compatibility, if the method does not exist on the spam checker, fallback to not interfering.
+        checker = getattr(self.spam_checker, "check_username_for_spam", None)
+        if not checker:
+            return False
+        # Make a copy of the user profile object to ensure the spam checker
+        # cannot modify it.
+        return checker(user_profile.copy())

synapse/handlers/user_directory.py

@@ -52,6 +52,7 @@ class UserDirectoryHandler(StateDeltasHandler):
         self.is_mine_id = hs.is_mine_id
         self.update_user_directory = hs.config.update_user_directory
         self.search_all_users = hs.config.user_directory_search_all_users
+        self.spam_checker = hs.get_spam_checker()
         # The current position in the current_state_delta stream
         self.pos = None
 
@@ -65,7 +66,7 @@ class UserDirectoryHandler(StateDeltasHandler):
             # we start populating the user directory
             self.clock.call_later(0, self.notify_new_event)
 
-    def search_users(self, user_id, search_term, limit):
+    async def search_users(self, user_id, search_term, limit):
         """Searches for users in directory
 
         Returns:
@@ -82,7 +83,16 @@ class UserDirectoryHandler(StateDeltasHandler):
                     ]
                 }
         """
-        return self.store.search_user_dir(user_id, search_term, limit)
+        results = await self.store.search_user_dir(user_id, search_term, limit)
+
+        # Remove any spammy users from the results.
+        results["results"] = [
+            user
+            for user in results["results"]
+            if not self.spam_checker.check_username_for_spam(user)
+        ]
+
+        return results
 
     def notify_new_event(self):
         """Called when there may be more deltas to process