Fix import in module_api module and docs on the new check_event_for_spam signature (#12918)

Co-authored-by: Richard van der Hoff <1389908+richvdh@users.noreply.github.com>

5 files changed, 46 insertions, 58 deletions

diff --git a/synapse/events/spamcheck.py b/synapse/events/spamcheck.py
index 7984874e21..1048b4c825 100644
--- a/synapse/events/spamcheck.py
+++ b/synapse/events/spamcheck.py
@@ -30,7 +30,7 @@ from typing import (
 from synapse.api.errors import Codes
 from synapse.rest.media.v1._base import FileInfo
 from synapse.rest.media.v1.media_storage import ReadableFileWrapper
-from synapse.spam_checker_api import Allow, Decision, RegistrationBehaviour
+from synapse.spam_checker_api import RegistrationBehaviour
 from synapse.types import RoomAlias, UserProfile
 from synapse.util.async_helpers import delay_cancellation, maybe_awaitable
 from synapse.util.metrics import Measure
@@ -46,12 +46,9 @@ CHECK_EVENT_FOR_SPAM_CALLBACK = Callable[
     ["synapse.events.EventBase"],
     Awaitable[
         Union[
-            Allow,
-            Codes,
+            str,
             # Deprecated
             bool,
-            # Deprecated
-            str,
         ]
     ],
 ]
@@ -178,6 +175,8 @@ def load_legacy_spam_checkers(hs: "synapse.server.HomeServer") -> None:
 
 
 class SpamChecker:
+    NOT_SPAM = "NOT_SPAM"
+
     def __init__(self, hs: "synapse.server.HomeServer") -> None:
         self.hs = hs
         self.clock = hs.get_clock()
@@ -268,9 +267,7 @@ class SpamChecker:
         if check_media_file_for_spam is not None:
             self._check_media_file_for_spam_callbacks.append(check_media_file_for_spam)
 
-    async def check_event_for_spam(
-        self, event: "synapse.events.EventBase"
-    ) -> Union[Decision, str]:
+    async def check_event_for_spam(self, event: "synapse.events.EventBase") -> str:
         """Checks if a given event is considered "spammy" by this server.
 
         If the server considers an event spammy, then it will be rejected if
@@ -281,22 +278,20 @@ class SpamChecker:
             event: the event to be checked
 
         Returns:
-            - on `ALLOW`, the event is considered good (non-spammy) and should
-                be let through. Other spamcheck filters may still reject it.
-            - on `Code`, the event is considered spammy and is rejected with a specific
+            - `NOT_SPAM` if the event is considered good (non-spammy) and should be let
+                through. Other spamcheck filters may still reject it.
+            - A `Code` if the event is considered spammy and is rejected with a specific
                 error message/code.
-            - on `str`, the event is considered spammy and the string is used as error
-                message. This usage is generally discouraged as it doesn't support
-                internationalization.
+            - A string that isn't `NOT_SPAM` if the event is considered spammy and the
+                string should be used as the client-facing error message. This usage is
+                generally discouraged as it doesn't support internationalization.
         """
         for callback in self._check_event_for_spam_callbacks:
             with Measure(
                 self.clock, "{}.{}".format(callback.__module__, callback.__qualname__)
             ):
-                res: Union[Decision, str, bool] = await delay_cancellation(
-                    callback(event)
-                )
-                if res is False or res is Allow.ALLOW:
+                res = await delay_cancellation(callback(event))
+                if res is False or res == self.NOT_SPAM:
                     # This spam-checker accepts the event.
                     # Other spam-checkers may reject it, though.
                     continue
@@ -304,13 +299,23 @@ class SpamChecker:
                     # This spam-checker rejects the event with deprecated
                     # return value `True`
                     return Codes.FORBIDDEN
+                elif not isinstance(res, str):
+                    # mypy complains that we can't reach this code because of the
+                    # return type in CHECK_EVENT_FOR_SPAM_CALLBACK, but we don't know
+                    # for sure that the module actually returns it.
+                    logger.warning(  # type: ignore[unreachable]
+                        "Module returned invalid value, rejecting message as spam"
+                    )
+                    res = "This message has been rejected as probable spam"
                 else:
-                    # This spam-checker rejects the event either with a `str`
-                    # or with a `Codes`. In either case, we stop here.
-                    return res
+                    # The module rejected the event either with a `Codes`
+                    # or some other `str`. In either case, we stop here.
+                    pass
+
+                return res
 
         # No spam-checker has rejected the event, let it pass.
-        return Allow.ALLOW
+        return self.NOT_SPAM
 
     async def should_drop_federated_event(
         self, event: "synapse.events.EventBase"
diff --git a/synapse/federation/federation_base.py b/synapse/federation/federation_base.py
index 1e866b19d8..7bc54b9988 100644
--- a/synapse/federation/federation_base.py
+++ b/synapse/federation/federation_base.py
@@ -15,7 +15,6 @@
 import logging
 from typing import TYPE_CHECKING
 
-import synapse
 from synapse.api.constants import MAX_DEPTH, EventContentFields, EventTypes, Membership
 from synapse.api.errors import Codes, SynapseError
 from synapse.api.room_versions import EventFormatVersions, RoomVersion
@@ -101,7 +100,7 @@ class FederationBase:
 
         spam_check = await self.spam_checker.check_event_for_spam(pdu)
 
-        if spam_check is not synapse.spam_checker_api.Allow.ALLOW:
+        if spam_check != self.spam_checker.NOT_SPAM:
             logger.warning("Event contains spam, soft-failing %s", pdu.event_id)
             # we redact (to save disk space) as well as soft-failing (to stop
             # using the event in prev_events).
diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py
index cb1bc4c06f..22cdad3f33 100644
--- a/synapse/handlers/message.py
+++ b/synapse/handlers/message.py
@@ -23,7 +23,6 @@ from canonicaljson import encode_canonical_json
 
 from twisted.internet.interfaces import IDelayedCall
 
-import synapse
 from synapse import event_auth
 from synapse.api.constants import (
     EventContentFields,
@@ -886,10 +885,22 @@ class EventCreationHandler:
                 event.sender,
             )
 
-            spam_check = await self.spam_checker.check_event_for_spam(event)
-            if spam_check is not synapse.spam_checker_api.Allow.ALLOW:
+            spam_check_result = await self.spam_checker.check_event_for_spam(event)
+            if spam_check_result != self.spam_checker.NOT_SPAM:
+                if isinstance(spam_check_result, Codes):
+                    raise SynapseError(
+                        403,
+                        "This message has been rejected as probable spam",
+                        spam_check_result,
+                    )
+
+                # Backwards compatibility: if the return value is not an error code, it
+                # means the module returned an error message to be included in the
+                # SynapseError (which is now deprecated).
                 raise SynapseError(
-                    403, "This message had been rejected as probable spam", spam_check
+                    403,
+                    spam_check_result,
+                    Codes.FORBIDDEN,
                 )
 
             ev = await self.handle_new_client_event(
diff --git a/synapse/module_api/__init__.py b/synapse/module_api/__init__.py
index 95f3b27927..c44e9da121 100644
--- a/synapse/module_api/__init__.py
+++ b/synapse/module_api/__init__.py
@@ -35,7 +35,6 @@ from typing_extensions import ParamSpec
 from twisted.internet import defer
 from twisted.web.resource import Resource
 
-from synapse import spam_checker_api
 from synapse.api.errors import SynapseError
 from synapse.events import EventBase
 from synapse.events.presence_router import (
@@ -55,6 +54,7 @@ from synapse.events.spamcheck import (
     USER_MAY_JOIN_ROOM_CALLBACK,
     USER_MAY_PUBLISH_ROOM_CALLBACK,
     USER_MAY_SEND_3PID_INVITE_CALLBACK,
+    SpamChecker,
 )
 from synapse.events.third_party_rules import (
     CHECK_CAN_DEACTIVATE_USER_CALLBACK,
@@ -140,9 +140,7 @@ are loaded into Synapse.
 """
 
 PRESENCE_ALL_USERS = PresenceRouter.ALL_USERS
-
-ALLOW = spam_checker_api.Allow.ALLOW
-# Singleton value used to mark a message as permitted.
+NOT_SPAM = SpamChecker.NOT_SPAM
 
 __all__ = [
     "errors",
@@ -151,7 +149,7 @@ __all__ = [
     "respond_with_html",
     "run_in_background",
     "cached",
-    "Allow",
+    "NOT_SPAM",
     "UserID",
     "DatabasePool",
     "LoggingTransaction",
diff --git a/synapse/spam_checker_api/__init__.py b/synapse/spam_checker_api/__init__.py
index 95132c80b7..75578270ac 100644
--- a/synapse/spam_checker_api/__init__.py
+++ b/synapse/spam_checker_api/__init__.py
@@ -12,9 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from enum import Enum
-from typing import Union
-
-from synapse.api.errors import Codes
 
 
 class RegistrationBehaviour(Enum):
@@ -25,25 +22,3 @@ class RegistrationBehaviour(Enum):
     ALLOW = "allow"
     SHADOW_BAN = "shadow_ban"
     DENY = "deny"
-
-
-# We define the following singleton enum rather than a string to be able to
-# write `Union[Allow, ..., str]` in some of the callbacks for the spam-checker
-# API, where the `str` is required to maintain backwards compatibility with
-# previous versions of the API.
-class Allow(Enum):
-    """
-    Singleton to allow events to pass through in SpamChecker APIs.
-    """
-
-    ALLOW = "allow"
-
-
-Decision = Union[Allow, Codes]
-"""
-Union to define whether a request should be allowed or rejected.
-
-To accept a request, return `ALLOW`.
-
-To reject a request without any specific information, use `Codes.FORBIDDEN`.
-"""