Merge branch 'develop' into babolivier/message_retention

3 files changed, 114 insertions, 1 deletions

diff --git a/tests/rest/admin/test_admin.py b/tests/rest/admin/test_admin.py
index 8e1ca8b738..9575058252 100644
--- a/tests/rest/admin/test_admin.py
+++ b/tests/rest/admin/test_admin.py
@@ -628,10 +628,12 @@ class PurgeRoomTestCase(unittest.HomeserverTestCase):
             "local_invites",
             "room_account_data",
             "room_tags",
+            "state_groups",
+            "state_groups_state",
         ):
             count = self.get_success(
                 self.store._simple_select_one_onecol(
-                    table="events",
+                    table=table,
                     keyvalues={"room_id": room_id},
                     retcol="COUNT(*)",
                     desc="test_purge_room",
@@ -639,3 +641,5 @@ class PurgeRoomTestCase(unittest.HomeserverTestCase):
             )
 
             self.assertEqual(count, 0, msg="Rows not purged in {}".format(table))
+
+    test_purge_room.skip = "Disabled because it's currently broken"
diff --git a/tests/rest/client/v1/test_rooms.py b/tests/rest/client/v1/test_rooms.py
index 5e38fd6ced..e84e578f99 100644
--- a/tests/rest/client/v1/test_rooms.py
+++ b/tests/rest/client/v1/test_rooms.py
@@ -25,7 +25,9 @@ from twisted.internet import defer
 
 import synapse.rest.admin
 from synapse.api.constants import EventContentFields, EventTypes, Membership
+from synapse.handlers.pagination import PurgeStatus
 from synapse.rest.client.v1 import login, profile, room
+from synapse.util.stringutils import random_string
 
 from tests import unittest
 
@@ -910,6 +912,78 @@ class RoomMessageListTestCase(RoomBase):
 
         return channel.json_body["chunk"]
 
+    def test_room_messages_purge(self):
+        store = self.hs.get_datastore()
+        pagination_handler = self.hs.get_pagination_handler()
+
+        # Send a first message in the room, which will be removed by the purge.
+        first_event_id = self.helper.send(self.room_id, "message 1")["event_id"]
+        first_token = self.get_success(
+            store.get_topological_token_for_event(first_event_id)
+        )
+
+        # Send a second message in the room, which won't be removed, and which we'll
+        # use as the marker to purge events before.
+        second_event_id = self.helper.send(self.room_id, "message 2")["event_id"]
+        second_token = self.get_success(
+            store.get_topological_token_for_event(second_event_id)
+        )
+
+        # Send a third event in the room to ensure we don't fall under any edge case
+        # due to our marker being the latest forward extremity in the room.
+        self.helper.send(self.room_id, "message 3")
+
+        # Check that we get the first and second message when querying /messages.
+        request, channel = self.make_request(
+            "GET",
+            "/rooms/%s/messages?access_token=x&from=%s&dir=b&filter=%s"
+            % (self.room_id, second_token, json.dumps({"types": [EventTypes.Message]})),
+        )
+        self.render(request)
+        self.assertEqual(channel.code, 200, channel.json_body)
+
+        chunk = channel.json_body["chunk"]
+        self.assertEqual(len(chunk), 2, [event["content"] for event in chunk])
+
+        # Purge every event before the second event.
+        purge_id = random_string(16)
+        pagination_handler._purges_by_id[purge_id] = PurgeStatus()
+        self.get_success(
+            pagination_handler._purge_history(
+                purge_id=purge_id,
+                room_id=self.room_id,
+                token=second_token,
+                delete_local_events=True,
+            )
+        )
+
+        # Check that we only get the second message through /message now that the first
+        # has been purged.
+        request, channel = self.make_request(
+            "GET",
+            "/rooms/%s/messages?access_token=x&from=%s&dir=b&filter=%s"
+            % (self.room_id, second_token, json.dumps({"types": [EventTypes.Message]})),
+        )
+        self.render(request)
+        self.assertEqual(channel.code, 200, channel.json_body)
+
+        chunk = channel.json_body["chunk"]
+        self.assertEqual(len(chunk), 1, [event["content"] for event in chunk])
+
+        # Check that we get no event, but also no error, when querying /messages with
+        # the token that was pointing at the first event, because we don't have it
+        # anymore.
+        request, channel = self.make_request(
+            "GET",
+            "/rooms/%s/messages?access_token=x&from=%s&dir=b&filter=%s"
+            % (self.room_id, first_token, json.dumps({"types": [EventTypes.Message]})),
+        )
+        self.render(request)
+        self.assertEqual(channel.code, 200, channel.json_body)
+
+        chunk = channel.json_body["chunk"]
+        self.assertEqual(len(chunk), 0, [event["content"] for event in chunk])
+
 
 class RoomSearchTestCase(unittest.HomeserverTestCase):
     servlets = [
diff --git a/tests/rest/media/v1/test_url_preview.py b/tests/rest/media/v1/test_url_preview.py
index 976652aee8..852b8ab11c 100644
--- a/tests/rest/media/v1/test_url_preview.py
+++ b/tests/rest/media/v1/test_url_preview.py
@@ -247,6 +247,41 @@ class URLPreviewTests(unittest.HomeserverTestCase):
         self.assertEqual(channel.code, 200)
         self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430")
 
+    def test_overlong_title(self):
+        self.lookups["matrix.org"] = [(IPv4Address, "8.8.8.8")]
+
+        end_content = (
+            b"<html><head>"
+            b"<title>" + b"x" * 2000 + b"</title>"
+            b'<meta property="og:description" content="hi" />'
+            b"</head></html>"
+        )
+
+        request, channel = self.make_request(
+            "GET", "url_preview?url=http://matrix.org", shorthand=False
+        )
+        request.render(self.preview_url)
+        self.pump()
+
+        client = self.reactor.tcpClients[0][2].buildProtocol(None)
+        server = AccumulatingProtocol()
+        server.makeConnection(FakeTransport(client, self.reactor))
+        client.makeConnection(FakeTransport(server, self.reactor))
+        client.dataReceived(
+            (
+                b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n"
+                b'Content-Type: text/html; charset="windows-1251"\r\n\r\n'
+            )
+            % (len(end_content),)
+            + end_content
+        )
+
+        self.pump()
+        self.assertEqual(channel.code, 200)
+        res = channel.json_body
+        # We should only see the `og:description` field, as `title` is too long and should be stripped out
+        self.assertCountEqual(["og:description"], res.keys())
+
     def test_ipaddr(self):
         """
         IP addresses can be previewed directly.