Add a config option to prioritise local users in user directory search results (#9383)

This PR adds a homeserver config option, `user_directory.prefer_local_users`, that when enabled will show local users higher in user directory search results than remote users. This option is off by default.

Note that turning this on doesn't necessarily mean that remote users will always be put below local users, but they should be assuming all other ranking factors (search query match, profile information present etc) are identical.

This is useful for, say, University networks that are openly federating, but want to prioritise local students and staff in the user directory over other random users.

2 files changed, 59 insertions, 9 deletions

diff --git a/synapse/config/user_directory.py b/synapse/config/user_directory.py
index c8d19c5d6b..89dbebd148 100644
--- a/synapse/config/user_directory.py
+++ b/synapse/config/user_directory.py
@@ -26,6 +26,7 @@ class UserDirectoryConfig(Config):
     def read_config(self, config, **kwargs):
         self.user_directory_search_enabled = True
         self.user_directory_search_all_users = False
+        self.user_directory_search_prefer_local_users = False
         user_directory_config = config.get("user_directory", None)
         if user_directory_config:
             self.user_directory_search_enabled = user_directory_config.get(
@@ -34,6 +35,9 @@ class UserDirectoryConfig(Config):
             self.user_directory_search_all_users = user_directory_config.get(
                 "search_all_users", False
             )
+            self.user_directory_search_prefer_local_users = user_directory_config.get(
+                "prefer_local_users", False
+            )
 
     def generate_config_section(self, config_dir_path, server_name, **kwargs):
         return """
@@ -49,7 +53,12 @@ class UserDirectoryConfig(Config):
         # rebuild the user_directory search indexes, see
         # https://github.com/matrix-org/synapse/blob/master/docs/user_directory.md
         #
+        # 'prefer_local_users' defines whether to prioritise local users in
+        # search query results. If True, local users are more likely to appear above
+        # remote users when searching the user directory. Defaults to false.
+        #
         #user_directory:
         #  enabled: true
         #  search_all_users: false
+        #  prefer_local_users: false
         """
diff --git a/synapse/storage/databases/main/user_directory.py b/synapse/storage/databases/main/user_directory.py
index 63f88eac51..02ee15676c 100644
--- a/synapse/storage/databases/main/user_directory.py
+++ b/synapse/storage/databases/main/user_directory.py
@@ -556,6 +556,11 @@ class UserDirectoryStore(UserDirectoryBackgroundUpdateStore):
     def __init__(self, database: DatabasePool, db_conn, hs):
         super().__init__(database, db_conn, hs)
 
+        self._prefer_local_users_in_search = (
+            hs.config.user_directory_search_prefer_local_users
+        )
+        self._server_name = hs.config.server_name
+
     async def remove_from_user_dir(self, user_id: str) -> None:
         def _remove_from_user_dir_txn(txn):
             self.db_pool.simple_delete_txn(
@@ -754,9 +759,24 @@ class UserDirectoryStore(UserDirectoryBackgroundUpdateStore):
                 )
             """
 
+        # We allow manipulating the ranking algorithm by injecting statements
+        # based on config options.
+        additional_ordering_statements = []
+        ordering_arguments = ()
+
         if isinstance(self.database_engine, PostgresEngine):
             full_query, exact_query, prefix_query = _parse_query_postgres(search_term)
 
+            # If enabled, this config option will rank local users higher than those on
+            # remote instances.
+            if self._prefer_local_users_in_search:
+                # This statement checks whether a given user's user ID contains a server name
+                # that matches the local server
+                statement = "* (CASE WHEN user_id LIKE ? THEN 2.0 ELSE 1.0 END)"
+                additional_ordering_statements.append(statement)
+
+                ordering_arguments += ("%:" + self._server_name,)
+
             # We order by rank and then if they have profile info
             # The ranking algorithm is hand tweaked for "best" results. Broadly
             # the idea is we give a higher weight to exact matches.
@@ -767,7 +787,7 @@ class UserDirectoryStore(UserDirectoryBackgroundUpdateStore):
                 FROM user_directory_search as t
                 INNER JOIN user_directory AS d USING (user_id)
                 WHERE
-                    %s
+                    %(where_clause)s
                     AND vector @@ to_tsquery('simple', ?)
                 ORDER BY
                     (CASE WHEN d.user_id IS NOT NULL THEN 4.0 ELSE 1.0 END)
@@ -787,33 +807,54 @@ class UserDirectoryStore(UserDirectoryBackgroundUpdateStore):
                             8
                         )
                     )
+                    %(order_case_statements)s
                     DESC,
                     display_name IS NULL,
                     avatar_url IS NULL
                 LIMIT ?
-            """ % (
-                where_clause,
+            """ % {
+                "where_clause": where_clause,
+                "order_case_statements": " ".join(additional_ordering_statements),
+            }
+            args = (
+                join_args
+                + (full_query, exact_query, prefix_query)
+                + ordering_arguments
+                + (limit + 1,)
             )
-            args = join_args + (full_query, exact_query, prefix_query, limit + 1)
         elif isinstance(self.database_engine, Sqlite3Engine):
             search_query = _parse_query_sqlite(search_term)
 
+            # If enabled, this config option will rank local users higher than those on
+            # remote instances.
+            if self._prefer_local_users_in_search:
+                # This statement checks whether a given user's user ID contains a server name
+                # that matches the local server
+                #
+                # Note that we need to include a comma at the end for valid SQL
+                statement = "user_id LIKE ? DESC,"
+                additional_ordering_statements.append(statement)
+
+                ordering_arguments += ("%:" + self._server_name,)
+
             sql = """
                 SELECT d.user_id AS user_id, display_name, avatar_url
                 FROM user_directory_search as t
                 INNER JOIN user_directory AS d USING (user_id)
                 WHERE
-                    %s
+                    %(where_clause)s
                     AND value MATCH ?
                 ORDER BY
                     rank(matchinfo(user_directory_search)) DESC,
+                    %(order_statements)s
                     display_name IS NULL,
                     avatar_url IS NULL
                 LIMIT ?
-            """ % (
-                where_clause,
-            )
-            args = join_args + (search_query, limit + 1)
+            """ % {
+                "where_clause": where_clause,
+                "order_statements": " ".join(additional_ordering_statements),
+            }
+            args = join_args + (search_query,) + ordering_arguments + (limit + 1,)
         else:
             # This should be unreachable.
             raise Exception("Unrecognized database engine")