Implement a content type allow list for URL previews (#11936)

This implements an allow list for content types for which Synapse will attempt URL preview. If a URL resolves to a resource with a content type which isn't in the list, the download will terminate immediately.

This makes sense given that Synapse would never successfully generate a URL preview for such files in the first place, and helps prevent issues with streaming media servers, such as #8302.

Signed-off-by: Denis Kasak dkasak@termina.org.uk

1 files changed, 72 insertions, 0 deletions

diff --git a/tests/rest/media/v1/test_url_preview.py b/tests/rest/media/v1/test_url_preview.py
index 53f6186213..da2c533260 100644
--- a/tests/rest/media/v1/test_url_preview.py
+++ b/tests/rest/media/v1/test_url_preview.py
@@ -243,6 +243,78 @@ class URLPreviewTests(unittest.HomeserverTestCase):
         self.assertEqual(channel.code, 200)
         self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430")
 
+    def test_video_rejected(self):
+        self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")]
+
+        end_content = b"anything"
+
+        channel = self.make_request(
+            "GET",
+            "preview_url?url=http://matrix.org",
+            shorthand=False,
+            await_result=False,
+        )
+        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: video/mp4\r\n\r\n"
+            )
+            % (len(end_content))
+            + end_content
+        )
+
+        self.pump()
+        self.assertEqual(channel.code, 502)
+        self.assertEqual(
+            channel.json_body,
+            {
+                "errcode": "M_UNKNOWN",
+                "error": "Requested file's content type not allowed for this operation: video/mp4",
+            },
+        )
+
+    def test_audio_rejected(self):
+        self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")]
+
+        end_content = b"anything"
+
+        channel = self.make_request(
+            "GET",
+            "preview_url?url=http://matrix.org",
+            shorthand=False,
+            await_result=False,
+        )
+        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: audio/aac\r\n\r\n"
+            )
+            % (len(end_content))
+            + end_content
+        )
+
+        self.pump()
+        self.assertEqual(channel.code, 502)
+        self.assertEqual(
+            channel.json_body,
+            {
+                "errcode": "M_UNKNOWN",
+                "error": "Requested file's content type not allowed for this operation: audio/aac",
+            },
+        )
+
     def test_non_ascii_preview_content_type(self):
         self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")]