Remove SynapseRequest.get_user_agent (#9069)

SynapseRequest is in danger of becoming a bit of a dumping-ground for "useful stuff relating to Requests",
which isn't really its intention (its purpose is to override render, finished and connectionLost to set up the 
LoggingContext and write the right entries to the request log).

Putting utility functions inside SynapseRequest means that lots of our code ends up requiring a
SynapseRequest when there is nothing synapse-specific about the Request at all, and any old
twisted.web.iweb.IRequest will do. This increases code coupling and makes testing more difficult.

In short: move get_user_agent out to a utility function.

2 files changed, 17 insertions, 16 deletions

diff --git a/synapse/http/__init__.py b/synapse/http/__init__.py
index 59b01b812c..4bc3cb53f0 100644
--- a/synapse/http/__init__.py
+++ b/synapse/http/__init__.py
@@ -17,6 +17,7 @@ import re
 
 from twisted.internet import task
 from twisted.web.client import FileBodyProducer
+from twisted.web.iweb import IRequest
 
 from synapse.api.errors import SynapseError
 
@@ -50,3 +51,17 @@ class QuieterFileBodyProducer(FileBodyProducer):
             FileBodyProducer.stopProducing(self)
         except task.TaskStopped:
             pass
+
+
+def get_request_user_agent(request: IRequest, default: str = "") -> str:
+    """Return the last User-Agent header, or the given default.
+    """
+    # There could be raw utf-8 bytes in the User-Agent header.
+
+    # N.B. if you don't do this, the logger explodes cryptically
+    # with maximum recursion trying to log errors about
+    # the charset problem.
+    # c.f. https://github.com/matrix-org/synapse/issues/3471
+
+    h = request.getHeader(b"User-Agent")
+    return h.decode("ascii", "replace") if h else default
diff --git a/synapse/http/site.py b/synapse/http/site.py
index 5a5790831b..12ec3f851f 100644
--- a/synapse/http/site.py
+++ b/synapse/http/site.py
@@ -20,7 +20,7 @@ from twisted.python.failure import Failure
 from twisted.web.server import Request, Site
 
 from synapse.config.server import ListenerConfig
-from synapse.http import redact_uri
+from synapse.http import get_request_user_agent, redact_uri
 from synapse.http.request_metrics import RequestMetrics, requests_counter
 from synapse.logging.context import LoggingContext, PreserveLoggingContext
 from synapse.types import Requester
@@ -113,15 +113,6 @@ class SynapseRequest(Request):
             method = self.method.decode("ascii")
         return method
 
-    def get_user_agent(self, default: str) -> str:
-        """Return the last User-Agent header, or the given default.
-        """
-        user_agent = self.requestHeaders.getRawHeaders(b"User-Agent", [None])[-1]
-        if user_agent is None:
-            return default
-
-        return user_agent.decode("ascii", "replace")
-
     def render(self, resrc):
         # this is called once a Resource has been found to serve the request; in our
         # case the Resource in question will normally be a JsonResource.
@@ -292,12 +283,7 @@ class SynapseRequest(Request):
             # and can see that we're doing something wrong.
             authenticated_entity = repr(self.requester)  # type: ignore[unreachable]
 
-        # ...or could be raw utf-8 bytes in the User-Agent header.
-        # N.B. if you don't do this, the logger explodes cryptically
-        # with maximum recursion trying to log errors about
-        # the charset problem.
-        # c.f. https://github.com/matrix-org/synapse/issues/3471
-        user_agent = self.get_user_agent("-")
+        user_agent = get_request_user_agent(self, "-")
 
         code = str(self.code)
         if not self.finished: