Merge pull request #5589 from matrix-org/erikj/admin_exfiltrate_data

Add basic function to get all data for a user out of synapse

2 files changed, 28 insertions, 6 deletions

diff --git a/synapse/storage/roommember.py b/synapse/storage/roommember.py
index 8004aeb909..32cfd010a5 100644
--- a/synapse/storage/roommember.py
+++ b/synapse/storage/roommember.py
@@ -575,6 +575,26 @@ class RoomMemberWorkerStore(EventsWorkerStore):
         count = yield self.runInteraction("did_forget_membership", f)
         defer.returnValue(count == 0)
 
+    @defer.inlineCallbacks
+    def get_rooms_user_has_been_in(self, user_id):
+        """Get all rooms that the user has ever been in.
+
+        Args:
+            user_id (str)
+
+        Returns:
+            Deferred[set[str]]: Set of room IDs.
+        """
+
+        room_ids = yield self._simple_select_onecol(
+            table="room_memberships",
+            keyvalues={"membership": Membership.JOIN, "user_id": user_id},
+            retcol="room_id",
+            desc="get_rooms_user_has_been_in",
+        )
+
+        return set(room_ids)
+
 
 class RoomMemberStore(RoomMemberWorkerStore):
     def __init__(self, db_conn, hs):
diff --git a/synapse/storage/stream.py b/synapse/storage/stream.py
index 386a9dbe14..a0465484df 100644
--- a/synapse/storage/stream.py
+++ b/synapse/storage/stream.py
@@ -833,7 +833,9 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore):
         Returns:
             Deferred[tuple[list[_EventDictReturn], str]]: Returns the results
             as a list of _EventDictReturn and a token that points to the end
-            of the result set.
+            of the result set. If no events are returned then the end of the
+            stream has been reached (i.e. there are no events between
+            `from_token` and `to_token`), or `limit` is zero.
         """
 
         assert int(limit) >= 0
@@ -905,15 +907,15 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore):
                 only those before
             direction(char): Either 'b' or 'f' to indicate whether we are
                 paginating forwards or backwards from `from_key`.
-            limit (int): The maximum number of events to return. Zero or less
-                means no limit.
+            limit (int): The maximum number of events to return.
             event_filter (Filter|None): If provided filters the events to
                 those that match the filter.
 
         Returns:
-            tuple[list[dict], str]: Returns the results as a list of dicts and
-            a token that points to the end of the result set. The dicts have
-            the keys "event_id", "topological_ordering" and "stream_orderign".
+            tuple[list[FrozenEvent], str]: Returns the results as a list of
+            events and a token that points to the end of the result set. If no
+            events are returned then the end of the stream has been reached
+            (i.e. there are no events between `from_key` and `to_key`).
         """
 
         from_key = RoomStreamToken.parse(from_key)