Move server event filtering logic to rust (#17928)

### Pull Request Checklist

<!-- Please read
https://element-hq.github.io/synapse/latest/development/contributing_guide.html
before submitting your pull request -->

* [X] Pull request is based on the develop branch
* [X] Pull request includes a [changelog
file](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#changelog).
The entry should:
- Be a short description of your change which makes sense to users.
"Fixed a bug that prevented receiving messages from other servers."
instead of "Moved X method from `EventStore` to `EventWorkerStore`.".
  - Use markdown where necessary, mostly for `code blocks`.
  - End with either a period (.) or an exclamation mark (!).
  - Start with a capital letter.
- Feel free to credit yourself, by adding a sentence "Contributed by
@github_username." or "Contributed by [Your Name]." to the end of the
entry.
* [X] [Code
style](https://element-hq.github.io/synapse/latest/code_style.html) is
correct
(run the
[linters](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#run-the-linters))

changelog.d/17928.misc

@@ -0,0 +1 @@
+Move server event filtering logic to rust.

rust/src/events/filter.rs

@@ -0,0 +1,107 @@
+/*
+ * This file is licensed under the Affero General Public License (AGPL) version 3.
+ *
+ * Copyright (C) 2024 New Vector, 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>.
+ */
+
+use std::collections::HashMap;
+
+use pyo3::{exceptions::PyValueError, pyfunction, PyResult};
+
+use crate::{
+    identifier::UserID,
+    matrix_const::{
+        HISTORY_VISIBILITY_INVITED, HISTORY_VISIBILITY_JOINED, MEMBERSHIP_INVITE, MEMBERSHIP_JOIN,
+    },
+};
+
+#[pyfunction(name = "event_visible_to_server")]
+pub fn event_visible_to_server_py(
+    sender: String,
+    target_server_name: String,
+    history_visibility: String,
+    erased_senders: HashMap<String, bool>,
+    partial_state_invisible: bool,
+    memberships: Vec<(String, String)>, // (state_key, membership)
+) -> PyResult<bool> {
+    event_visible_to_server(
+        sender,
+        target_server_name,
+        history_visibility,
+        erased_senders,
+        partial_state_invisible,
+        memberships,
+    )
+    .map_err(|e| PyValueError::new_err(format!("{e}")))
+}
+
+/// Return whether the target server is allowed to see the event.
+///
+/// For a fully stated room, the target server is allowed to see an event E if:
+///   - the state at E has world readable or shared history vis, OR
+///   - the state at E says that the target server is in the room.
+///
+/// For a partially stated room, the target server is allowed to see E if:
+///   - E was created by this homeserver, AND:
+///       - the partial state at E has world readable or shared history vis, OR
+///       - the partial state at E says that the target server is in the room.
+pub fn event_visible_to_server(
+    sender: String,
+    target_server_name: String,
+    history_visibility: String,
+    erased_senders: HashMap<String, bool>,
+    partial_state_invisible: bool,
+    memberships: Vec<(String, String)>, // (state_key, membership)
+) -> anyhow::Result<bool> {
+    if let Some(&erased) = erased_senders.get(&sender) {
+        if erased {
+            return Ok(false);
+        }
+    }
+
+    if partial_state_invisible {
+        return Ok(false);
+    }
+
+    if history_visibility != HISTORY_VISIBILITY_INVITED
+        && history_visibility != HISTORY_VISIBILITY_JOINED
+    {
+        return Ok(true);
+    }
+
+    let mut visible = false;
+    for (state_key, membership) in memberships {
+        let state_key = UserID::try_from(state_key.as_ref())
+            .map_err(|e| anyhow::anyhow!(format!("invalid user_id ({state_key}): {e}")))?;
+        if state_key.server_name() != target_server_name {
+            return Err(anyhow::anyhow!(
+                "state_key.server_name ({}) does not match target_server_name ({target_server_name})",
+                state_key.server_name()
+            ));
+        }
+
+        match membership.as_str() {
+            MEMBERSHIP_INVITE => {
+                if history_visibility == HISTORY_VISIBILITY_INVITED {
+                    visible = true;
+                    break;
+                }
+            }
+            MEMBERSHIP_JOIN => {
+                visible = true;
+                break;
+            }
+            _ => continue,
+        }
+    }
+
+    Ok(visible)
+}

rust/src/events/mod.rs

@@ -22,15 +22,17 @@
 
 use pyo3::{
     types::{PyAnyMethods, PyModule, PyModuleMethods},
-    Bound, PyResult, Python,
+    wrap_pyfunction, Bound, PyResult, Python,
 };
 
+pub mod filter;
 mod internal_metadata;
 
 /// Called when registering modules with python.
 pub fn register_module(py: Python<'_>, m: &Bound<'_, PyModule>) -> PyResult<()> {
     let child_module = PyModule::new_bound(py, "events")?;
     child_module.add_class::<internal_metadata::EventInternalMetadata>()?;
+    child_module.add_function(wrap_pyfunction!(filter::event_visible_to_server_py, m)?)?;
 
     m.add_submodule(&child_module)?;
 

rust/src/identifier.rs

@@ -0,0 +1,86 @@
+/*
+ * This file is licensed under the Affero General Public License (AGPL) version 3.
+ *
+ * Copyright (C) 2024 New Vector, 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>.
+ */
+
+//! # Matrix Identifiers
+//!
+//! This module contains definitions and utilities for working with matrix identifiers.
+
+use std::{fmt, ops::Deref};
+
+/// Errors that can occur when parsing a matrix identifier.
+#[derive(Clone, Debug, PartialEq)]
+pub enum IdentifierError {
+    IncorrectSigil,
+    MissingColon,
+}
+
+impl fmt::Display for IdentifierError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "{:?}", self)
+    }
+}
+
+/// A Matrix user_id.
+#[derive(Clone, Debug, PartialEq)]
+pub struct UserID(String);
+
+impl UserID {
+    /// Returns the `localpart` of the user_id.
+    pub fn localpart(&self) -> &str {
+        &self[1..self.colon_pos()]
+    }
+
+    /// Returns the `server_name` / `domain` of the user_id.
+    pub fn server_name(&self) -> &str {
+        &self[self.colon_pos() + 1..]
+    }
+
+    /// Returns the position of the ':' inside of the user_id.
+    /// Used when splitting the user_id into it's respective parts.
+    fn colon_pos(&self) -> usize {
+        self.find(':').unwrap()
+    }
+}
+
+impl TryFrom<&str> for UserID {
+    type Error = IdentifierError;
+
+    /// Will try creating a `UserID` from the provided `&str`.
+    /// Can fail if the user_id is incorrectly formatted.
+    fn try_from(s: &str) -> Result<Self, Self::Error> {
+        if !s.starts_with('@') {
+            return Err(IdentifierError::IncorrectSigil);
+        }
+
+        if s.find(':').is_none() {
+            return Err(IdentifierError::MissingColon);
+        }
+
+        Ok(UserID(s.to_string()))
+    }
+}
+
+impl Deref for UserID {
+    type Target = str;
+
+    fn deref(&self) -> &Self::Target {
+        &self.0
+    }
+}
+
+impl fmt::Display for UserID {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        write!(f, "{}", self.0)
+    }
+}

rust/src/lib.rs

@@ -6,6 +6,8 @@ pub mod acl;
 pub mod errors;
 pub mod events;
 pub mod http;
+pub mod identifier;
+pub mod matrix_const;
 pub mod push;
 pub mod rendezvous;
 

rust/src/matrix_const.rs

@@ -0,0 +1,28 @@
+/*
+ * This file is licensed under the Affero General Public License (AGPL) version 3.
+ *
+ * Copyright (C) 2024 New Vector, 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>.
+ */
+
+//! # Matrix Constants
+//!
+//! This module contains definitions for constant values described by the matrix specification.
+
+pub const HISTORY_VISIBILITY_WORLD_READABLE: &str = "world_readable";
+pub const HISTORY_VISIBILITY_SHARED: &str = "shared";
+pub const HISTORY_VISIBILITY_INVITED: &str = "invited";
+pub const HISTORY_VISIBILITY_JOINED: &str = "joined";
+
+pub const MEMBERSHIP_BAN: &str = "ban";
+pub const MEMBERSHIP_LEAVE: &str = "leave";
+pub const MEMBERSHIP_KNOCK: &str = "knock";
+pub const MEMBERSHIP_INVITE: &str = "invite";
+pub const MEMBERSHIP_JOIN: &str = "join";

rust/src/push/utils.rs

@@ -23,7 +23,6 @@ use anyhow::bail;
 use anyhow::Context;
 use anyhow::Error;
 use lazy_static::lazy_static;
-use regex;
 use regex::Regex;
 use regex::RegexBuilder;
 

synapse/synapse_rust/events.pyi

@@ -10,7 +10,7 @@
 # See the GNU Affero General Public License for more details:
 # <https://www.gnu.org/licenses/agpl-3.0.html>.
 
-from typing import Optional
+from typing import List, Mapping, Optional, Tuple
 
 from synapse.types import JsonDict
 
@@ -105,3 +105,29 @@ class EventInternalMetadata:
 
     def is_notifiable(self) -> bool:
         """Whether this event can trigger a push notification"""
+
+def event_visible_to_server(
+    sender: str,
+    target_server_name: str,
+    history_visibility: str,
+    erased_senders: Mapping[str, bool],
+    partial_state_invisible: bool,
+    memberships: List[Tuple[str, str]],
+) -> bool:
+    """Determine whether the server is allowed to see the unredacted event.
+
+    Args:
+        sender: The sender of the event.
+        target_server_name: The server we want to send the event to.
+        history_visibility: The history_visibility value at the event.
+        erased_senders: A mapping of users and whether they have requested erasure. If a
+            user is not in the map, it is treated as though they haven't requested erasure.
+        partial_state_invisible: Whether the event should be treated as invisible due to
+            the partial state status of the room.
+        memberships: A list of membership state information at the event for users
+            matching the `target_server_name`. Each list item must contain a tuple of
+            (state_key, membership).
+
+    Returns:
+        Whether the server is allowed to see the unredacted event.
+    """