Files
synapse/tests/storage/test_msc4242_state_dag.py
T
Erik JohnstonandEric Eastwood 9e2a076144 Port Event class to Rust (#19701)
Ports the event class to Rust.

The main difference here are:
1. There is now a single event class
2. We now validate a lot more at event construction time than we
previously did (we basically checked nothing before). This required some
changes to the tests, including
https://github.com/matrix-org/sytest/pull/1423

Reviewable commit-by-commit.

### Overview of Event Rust structure

The format of the event struct in Rust is quite different than that in
Python.

The top-level looks like:

```rust
pub struct Event {
    /// The parsed event JSON.
    fields: FormattedEvent,

    /// The event ID. For format v1 this is read directly from the JSON;
    /// for v2+ it is computed from the canonical-JSON hash at
    /// construction time and cached here.
    event_id: Arc<str>,

    /// Synapse-internal per-event state that lives outside the federated
    /// JSON (e.g. outlier flag, soft-failure, stream positions).
    #[pyo3(get)]
    internal_metadata: EventInternalMetadata,

    /// The room version this event was parsed for.
    #[pyo3(get)]
    room_version: &'static RoomVersion,

    /// `None` for accepted events; otherwise a short reason set by auth
    /// when the event was rejected.
    rejected_reason: Option<Box<str>>,
}
```

which includes the actual parsed event in `FormattedEvent`, plus the
rest of the event metadata.

```rust
pub struct FormattedEvent<E = Arc<EventFormatEnum>> {
    #[serde(default)]
    pub signatures: Signatures,

    #[serde(default)]
    pub unsigned: Unsigned,

    #[serde(flatten)]
    pub specific_fields: E,

    #[serde(flatten)]
    pub common_fields: Arc<EventCommonFields>,
}
```

The struct is further split into the common fields, format specific
fields, plus the signatures and unsigned. We split out the signature and
unsigned fields as they are mutable, so when we clone the event we can
still share the common and specific fields and only copy signature and
unsigned.

The `specific_fields` are the fields that depend on the format version.
They can either be a specific format (e.g. `E = EventFormatV1`) or a
type-erased enum `EventFormatEnum` that is across all room versions:

```rust
pub enum EventFormatEnum {
    V1(EventFormatV1),
    V2V3(EventFormatV2V3),
    V4(EventFormatV4),
    VMSC4242(EventFormatVMSC4242),
}
```

For example:

```rust
/// Shared flat-list encoding of `auth_events` and `prev_events`, reused
/// by every format from v2/v3 onwards.
#[derive(Serialize, Deserialize)]
pub struct SimpleAuthPrevEvents {
    pub auth_events: Vec<String>,
    pub prev_events: Vec<String>,
}

/// Version-specific fields for room versions 3-10.
#[derive(Serialize, Deserialize)]
pub struct EventFormatV2V3 {
    pub room_id: Box<str>,
    #[serde(flatten)]
    pub auth_prev_events: SimpleAuthPrevEvents,
}
```


### Dev notes

As discussed in
[`#element-backend-internal:matrix.org`](https://matrix.to/#/!SGNQGPGUwtcPBUotTL:matrix.org/$3gTjDO440GbAz57cXcCawwiyFLiD0crrarvS1uhzKOY?via=jki.re&via=element.io&via=matrix.org)

---------

Co-authored-by: Eric Eastwood <erice@element.io>
2026-06-02 11:05:38 +01:00

368 lines
14 KiB
Python

#
# This file is licensed under the Affero General Public License (AGPL) version 3.
#
# Copyright (C) 2026 Element Creations, Ltd
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# See the GNU Affero General Public License for more details:
# <https://www.gnu.org/licenses/agpl-3.0.html>.
from typing import Iterable
from unittest.mock import Mock
from twisted.test.proto_helpers import MemoryReactor
from synapse.api.constants import EventTypes
from synapse.api.errors import SynapseError
from synapse.api.room_versions import RoomVersions
from synapse.events import EventBase
from synapse.events.py_protocol import MSC4242Event
from synapse.events.snapshot import EventContext
from synapse.rest.client import room
from synapse.server import HomeServer
from synapse.util.clock import Clock
from tests.unittest import HomeserverTestCase, override_config
class MSC4242StateDagsTests(HomeserverTestCase):
user_id = "@user1:server"
servlets = [room.register_servlets]
def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer:
hs = self.setup_test_homeserver("server")
return hs
def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
self.room_id = self.helper.create_room_as(
self.user_id,
room_version=RoomVersions.MSC4242v12.identifier,
)
self.store = hs.get_datastores().main
self._storage_controllers = self.hs.get_storage_controllers()
def _get_prev_state_events(self, event_id: str) -> list[str]:
ev = self.helper.get_event(self.room_id, event_id)
prev_state_events: list[str] | None = ev.get("prev_state_events", None)
assert prev_state_events is not None
return prev_state_events
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_forward_extremities_are_calculated(self) -> None:
"""
Check that forward extremities are set as prev_state_events and that they don't change
for non-state events.
"""
# they don't change for messages
first_event_id = self.helper.send(self.room_id, body="test1")["event_id"]
first_prev_state_events = self._get_prev_state_events(first_event_id)
assert len(first_prev_state_events) == 1
second_id = self.helper.send(self.room_id, body="test2")["event_id"]
second_prev_state_events = self._get_prev_state_events(second_id)
assert len(second_prev_state_events) == 1
self.assertIncludes(
set(first_prev_state_events), set(second_prev_state_events), exact=True
)
# send an auth event, which should change the prev_state_events on *subsequent* events
join_rule_state_event_id = self.helper.send_state(
self.room_id,
EventTypes.JoinRules,
{
"join_rule": "knock",
},
tok="nope",
)["event_id"]
join_rule_prev_state_event_ids = self._get_prev_state_events(
join_rule_state_event_id
)
self.assertIncludes(
set(second_prev_state_events),
set(join_rule_prev_state_event_ids),
exact=True,
)
# prev_state_events should always point to the join rule now
third_event_id = self.helper.send(self.room_id, body="test3")["event_id"]
third_prev_state_events = self._get_prev_state_events(third_event_id)
self.assertIncludes(
set(third_prev_state_events), {join_rule_state_event_id}, exact=True
)
# and non-auth state should also update prev_state_events
name_state_event_id = self.helper.send_state(
self.room_id,
EventTypes.Name,
{
"name": "State DAGs!",
},
tok="nope",
)["event_id"]
name_prev_state_event_ids = self._get_prev_state_events(name_state_event_id)
self.assertIncludes(
set(name_prev_state_event_ids), {join_rule_state_event_id}, exact=True
)
fourth_event_id = self.helper.send(self.room_id, body="test4")["event_id"]
fourth_prev_state_events = self._get_prev_state_events(fourth_event_id)
self.assertIncludes(
set(fourth_prev_state_events), {name_state_event_id}, exact=True
)
class MSC4242EventPersistenceStateDagsStoreTestCase(HomeserverTestCase):
servlets = [
room.register_servlets,
]
def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None:
self.store = hs.get_datastores().main
persistence = hs.get_storage_controllers().persistence
assert persistence is not None
self.persistence = persistence
self.room_id = "!foo:bar"
self.seen_event_ids: set[str] = set()
self.persistence.main_store = Mock(spec=["have_seen_events"])
self.persistence.main_store.have_seen_events.side_effect = (
self._have_seen_events
)
self.rejected_event_ids_and_their_prevs: set[str] = set()
self.persistence.persist_events_store = Mock(
spec=["_get_prevs_before_rejected"]
)
self.persistence.persist_events_store._get_prevs_before_rejected.side_effect = (
self._get_prevs_before_rejected
)
async def _have_seen_events(
self, room_id: str, event_ids: Iterable[str]
) -> set[str]:
unknown_events = set(event_ids)
return self.seen_event_ids.intersection(unknown_events)
async def _get_prevs_before_rejected(
self, event_ids: Iterable[str], include_soft_failed: bool = True
) -> set[str]:
return self.rejected_event_ids_and_their_prevs
def _make_event(
self,
id: str,
prev_state_events: list[str],
rejected: bool = False,
) -> tuple[MSC4242Event, EventContext]:
# We use a mock here to allow us to set the `event_id`.
#
# FIXME: Having consistent human-readable event IDs in these tests is
# nice but the `Mock` is less than ideal. It would be better to use a
# real event but that is more complex to set up.
ev = Mock(spec=EventBase)
ev.event_id = id
ev.prev_state_events = prev_state_events
ev.state_key = "@unimportant:info"
ev.is_state.return_value = True
ctx = Mock()
ctx.rejected = rejected
return ev, ctx
def _test(
self,
current_fwds: list[str],
new_events: list[tuple[MSC4242Event, EventContext]],
want_new_extrems: set[str],
want_raises: bool = False,
) -> None:
"""
Tests the logic of _calculate_new_state_dag_extremities.
Tests that the new extremities calculated as a result of processing current_fwds and new_events
matches want_new_extrems or raises if want_raises is True.
"""
coroutine = self.persistence._calculate_new_state_dag_extremities(
self.room_id,
frozenset(current_fwds),
new_events,
)
if want_raises:
f = self.get_failure(coroutine, SynapseError)
assert f is not None
return
new_extrems = set(self.get_success(coroutine))
self.assertIncludes(
new_extrems,
set(want_new_extrems),
exact=True,
message=f"want_new_extrems={want_new_extrems} got={new_extrems}",
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_simple(self) -> None:
# Simple linear chain
self._test(
current_fwds=[],
new_events=[
self._make_event("$1", []),
self._make_event("$2", ["$1"]),
self._make_event("$3", ["$2"]),
self._make_event("$4", ["$3"]),
],
want_new_extrems={"$4"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_fork(self) -> None:
# Simple fork so we end up with two forward extrems
self._test(
current_fwds=[],
new_events=[
self._make_event("$1", []),
self._make_event("$2", ["$1"]),
self._make_event("$3", ["$2"]),
self._make_event("$4", ["$2"]),
],
want_new_extrems={"$3", "$4"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_merge(self) -> None:
# Simple fork so we end up with two forward extrems
self._test(
current_fwds=[],
new_events=[
self._make_event("$1", []),
self._make_event("$2", ["$1"]),
self._make_event("$3", ["$1"]),
self._make_event("$4", ["$2", "$3"]),
],
want_new_extrems={"$4"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_fork_on_existing(self) -> None:
# Fork where we are adding to older events
self.seen_event_ids = {"$1", "$2", "$3"}
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$3"]), # append to the forward extrem
self._make_event("$5", ["$1"]), # append to the root
],
want_new_extrems={"$4", "$5"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_merge_on_existing(self) -> None:
# Merge where we are merging to older events
self.seen_event_ids = {"$1", "$2", "$3"}
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$3", "$2"]),
],
want_new_extrems={"$4"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_merge_on_not_current(self) -> None:
# Merge where we are merging to older events
self.seen_event_ids = {"$1", "$2", "$3"}
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$1", "$2"]),
],
want_new_extrems={"$3", "$4"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_append_with_rejected(self) -> None:
# rejected events cannot be forward extremities
self.seen_event_ids = {"$1", "$2", "$3"}
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$3"], rejected=True),
],
want_new_extrems={"$3"},
)
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$3"], rejected=True),
self._make_event("$5", ["$4"], rejected=True),
],
want_new_extrems={"$3"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_append_with_rejected_in_chain(
self,
) -> None:
# rejected events cannot be forward extremities, but events that come after them can.
# this shouldn't cause multiple forward extremities.
self.seen_event_ids = {"$1", "$2", "$3"}
self.rejected_event_ids_and_their_prevs = {"$4", "$3"}
self._test(
current_fwds=["$3"],
new_events=[
self._make_event("$4", ["$3"], rejected=True),
self._make_event("$5", ["$4"]),
],
want_new_extrems={"$5"},
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_missing_prevs_raises(self) -> None:
self._test(
current_fwds=[],
new_events=[
self._make_event("$1", []),
self._make_event("$2", ["$1"]),
self._make_event("$3", ["$unknown"]),
self._make_event("$4", ["$3"]),
],
want_new_extrems={"$4"},
want_raises=True,
)
@override_config({"experimental_features": {"msc4242_enabled": True}})
def test_calculate_new_state_dag_extremities_complex(self) -> None:
"""
1
| \
2 4
|
3
Exists already, then becomes...
1______
| \\ |
2 4 5R
| | |
3--7 6R
| \\ / \
10R 8 9
"""
# Merge where we are merging to older events
self.seen_event_ids = {"$1", "$2", "$3", "$4"}
self.rejected_event_ids_and_their_prevs = {"$1", "$5", "$6", "$3", "$10"}
self._test(
current_fwds=["$3", "$4"],
new_events=[
self._make_event("$5", ["$1"], rejected=True),
self._make_event("$6", ["$5"], rejected=True),
self._make_event("$7", ["$4", "$3"]),
self._make_event("$8", ["$6", "$7"]),
self._make_event("$9", ["$6"]),
self._make_event("$10", ["$3"], rejected=True),
],
want_new_extrems={"$8", "$9"},
)