Correctly handle unpersisted events when calculating auth chain difference. (#8827)

We do state res with unpersisted events when calculating the new current state of the room, so that should be the only thing impacted. I don't think this is tooooo big of a deal as:

1. the next time a state event happens in the room the current state should correct itself;
2. in the common case all the unpersisted events' auth events will be pulled in by other state, so will still return the correct result (or one which is sufficiently close to not affect the result); and
3. we mostly use the state at an event to do important operations, which isn't affected by this.

1 files changed, 127 insertions, 1 deletions

diff --git a/tests/state/test_v2.py b/tests/state/test_v2.py
index ad9bbef9d2..f5c6db900d 100644
--- a/tests/state/test_v2.py
+++ b/tests/state/test_v2.py
@@ -24,7 +24,11 @@ from synapse.api.constants import EventTypes, JoinRules, Membership
 from synapse.api.room_versions import RoomVersions
 from synapse.event_auth import auth_types_for_event
 from synapse.events import make_event_from_dict
-from synapse.state.v2 import lexicographical_topological_sort, resolve_events_with_store
+from synapse.state.v2 import (
+    _get_auth_chain_difference,
+    lexicographical_topological_sort,
+    resolve_events_with_store,
+)
 from synapse.types import EventID
 
 from tests import unittest
@@ -587,6 +591,128 @@ class SimpleParamStateTestCase(unittest.TestCase):
         self.assert_dict(self.expected_combined_state, state)
 
 
+class AuthChainDifferenceTestCase(unittest.TestCase):
+    """We test that `_get_auth_chain_difference` correctly handles unpersisted
+    events.
+    """
+
+    def test_simple(self):
+        # Test getting the auth difference for a simple chain with a single
+        # unpersisted event:
+        #
+        #  Unpersisted | Persisted
+        #              |
+        #           C -|-> B -> A
+
+        a = FakeEvent(
+            id="A", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([], [])
+
+        b = FakeEvent(
+            id="B", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([a.event_id], [])
+
+        c = FakeEvent(
+            id="C", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([b.event_id], [])
+
+        persisted_events = {a.event_id: a, b.event_id: b}
+        unpersited_events = {c.event_id: c}
+
+        state_sets = [{"a": a.event_id, "b": b.event_id}, {"c": c.event_id}]
+
+        store = TestStateResolutionStore(persisted_events)
+
+        diff_d = _get_auth_chain_difference(state_sets, unpersited_events, store)
+        difference = self.successResultOf(defer.ensureDeferred(diff_d))
+
+        self.assertEqual(difference, {c.event_id})
+
+    def test_multiple_unpersisted_chain(self):
+        # Test getting the auth difference for a simple chain with multiple
+        # unpersisted events:
+        #
+        #  Unpersisted | Persisted
+        #              |
+        #      D -> C -|-> B -> A
+
+        a = FakeEvent(
+            id="A", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([], [])
+
+        b = FakeEvent(
+            id="B", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([a.event_id], [])
+
+        c = FakeEvent(
+            id="C", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([b.event_id], [])
+
+        d = FakeEvent(
+            id="D", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([c.event_id], [])
+
+        persisted_events = {a.event_id: a, b.event_id: b}
+        unpersited_events = {c.event_id: c, d.event_id: d}
+
+        state_sets = [
+            {"a": a.event_id, "b": b.event_id},
+            {"c": c.event_id, "d": d.event_id},
+        ]
+
+        store = TestStateResolutionStore(persisted_events)
+
+        diff_d = _get_auth_chain_difference(state_sets, unpersited_events, store)
+        difference = self.successResultOf(defer.ensureDeferred(diff_d))
+
+        self.assertEqual(difference, {d.event_id, c.event_id})
+
+    def test_unpersisted_events_different_sets(self):
+        # Test getting the auth difference for with multiple unpersisted events
+        # in different branches:
+        #
+        #  Unpersisted | Persisted
+        #              |
+        #     D --> C -|-> B -> A
+        #     E ----^ -|---^
+        #              |
+
+        a = FakeEvent(
+            id="A", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([], [])
+
+        b = FakeEvent(
+            id="B", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([a.event_id], [])
+
+        c = FakeEvent(
+            id="C", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([b.event_id], [])
+
+        d = FakeEvent(
+            id="D", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([c.event_id], [])
+
+        e = FakeEvent(
+            id="E", sender=ALICE, type=EventTypes.Member, state_key="", content={},
+        ).to_event([c.event_id, b.event_id], [])
+
+        persisted_events = {a.event_id: a, b.event_id: b}
+        unpersited_events = {c.event_id: c, d.event_id: d, e.event_id: e}
+
+        state_sets = [
+            {"a": a.event_id, "b": b.event_id, "e": e.event_id},
+            {"c": c.event_id, "d": d.event_id},
+        ]
+
+        store = TestStateResolutionStore(persisted_events)
+
+        diff_d = _get_auth_chain_difference(state_sets, unpersited_events, store)
+        difference = self.successResultOf(defer.ensureDeferred(diff_d))
+
+        self.assertEqual(difference, {d.event_id, e.event_id})
+
+
 def pairwise(iterable):
     "s -> (s0,s1), (s1,s2), (s2, s3), ..."
     a, b = itertools.tee(iterable)