Handle missing Content-Type header when accessing remote media

changelog.d/11200.bugfix

@@ -0,0 +1 @@
+Fixes a long-standing bug wherein a missing Content-Type header when downloading remote media causes Synapse to throw an error.

synapse/rest/media/v1/media_repository.py

@@ -214,7 +214,7 @@ async def get_local_media(
 
         self.mark_recently_accessed(None, media_id)
 
-        media_type = media_info["media_type"]
+        media_type = media_info.get("media_type", "application/octet-stream")
         media_length = media_info["media_length"]
         upload_name = name if name else media_info["upload_name"]
         url_cache = media_info["url_cache"]
@@ -445,7 +445,10 @@ async def _download_remote_file(
 
             await finish()
 
-            media_type = headers[b"Content-Type"][0].decode("ascii")
+            if b"Content-Type" in headers:
+                media_type = headers[b"Content-Type"][0].decode("ascii")
+            else:
+                media_type = "application/octet-stream"
             upload_name = get_filename_from_headers(headers)
             time_now_ms = self.clock.time_msec()
 

synapse/rest/media/v1/upload_resource.py

@@ -80,7 +80,7 @@ async def _async_render_POST(self, request: SynapseRequest) -> None:
             assert content_type_headers  # for mypy
             media_type = content_type_headers[0].decode("ascii")
         else:
-            raise SynapseError(msg="Upload request missing 'Content-Type'", code=400)
+            media_type = "application/octet-stream"
 
         # if headers.hasHeader(b"Content-Disposition"):
         #     disposition = headers.getRawHeaders(b"Content-Disposition")[0]

tests/rest/media/v1/test_media_storage.py

@@ -285,6 +285,51 @@ def _req(self, content_disposition):
 
         return channel
 
+    def test_handle_missing_content_type(self):
+        def _req_missing_headers(content_disposition):
+            channel = make_request(
+                self.reactor,
+                FakeSite(self.download_resource, self.reactor),
+                "GET",
+                self.media_id,
+                shorthand=False,
+                await_result=False,
+            )
+            self.pump()
+
+            # We've made one fetch, to example.com, using the media URL, and asking
+            # the other server not to do a remote fetch
+            self.assertEqual(len(self.fetches), 1)
+            self.assertEqual(self.fetches[0][1], "example.com")
+            self.assertEqual(
+                self.fetches[0][2], "/_matrix/media/r0/download/" + self.media_id
+            )
+            self.assertEqual(self.fetches[0][3], {"allow_remote": "false"})
+
+            headers = {
+                b"Content-Length": [b"%d" % (len(self.test_image.data))],
+            }
+            if content_disposition:
+                headers[b"Content-Disposition"] = [content_disposition]
+
+            self.fetches[0][0].callback(
+                (self.test_image.data, (len(self.test_image.data), headers))
+            )
+
+            self.pump()
+            self.assertEqual(channel.code, 200)
+
+            return channel
+
+        channel = _req_missing_headers(
+            b"inline; filename=out" + self.test_image.extension
+        )
+        headers = channel.headers
+        self.assertEqual(channel.code, 200)
+        self.assertEqual(
+            headers.getRawHeaders(b"Content-Type"), [b"application/octet-stream"]
+        )
+
     def test_disposition_filename_ascii(self):
         """
         If the filename is filename=<ascii> then Synapse will decode it as an