diff --git a/synapse/http/endpoint.py b/synapse/http/endpoint.py
index 80da870584..5a9cbb3324 100644
--- a/synapse/http/endpoint.py
+++ b/synapse/http/endpoint.py
@@ -38,6 +38,36 @@ _Server = collections.namedtuple(
)
+def parse_server_name(server_name):
+ """Split a server name into host/port parts.
+
+ Does some basic sanity checking of the
+
+ Args:
+ server_name (str): server name to parse
+
+ Returns:
+ Tuple[str, int|None]: host/port parts.
+
+ Raises:
+ ValueError if the server name could not be parsed.
+ """
+ try:
+ if server_name[-1] == ']':
+ # ipv6 literal, hopefully
+ if server_name[0] != '[':
+ raise Exception()
+
+ return server_name, None
+
+ domain_port = server_name.rsplit(":", 1)
+ domain = domain_port[0]
+ port = int(domain_port[1]) if domain_port[1:] else None
+ return domain, port
+ except Exception:
+ raise ValueError("Invalid server name '%s'" % server_name)
+
+
def matrix_federation_endpoint(reactor, destination, ssl_context_factory=None,
timeout=None):
"""Construct an endpoint for the given matrix destination.
@@ -50,9 +80,7 @@ def matrix_federation_endpoint(reactor, destination, ssl_context_factory=None,
timeout (int): connection timeout in seconds
"""
- domain_port = destination.split(":")
- domain = domain_port[0]
- port = int(domain_port[1]) if domain_port[1:] else None
+ domain, port = parse_server_name(destination)
endpoint_kw_args = {}
diff --git a/synapse/http/site.py b/synapse/http/site.py
index 74a752d6cf..fe93643b1e 100644
--- a/synapse/http/site.py
+++ b/synapse/http/site.py
@@ -107,13 +107,28 @@ class SynapseRequest(Request):
end_time = time.time()
+ # need to decode as it could be raw utf-8 bytes
+ # from a IDN servname in an auth header
+ authenticated_entity = self.authenticated_entity
+ if authenticated_entity is not None:
+ authenticated_entity = authenticated_entity.decode("utf-8", "replace")
+
+ # ...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()
+ if user_agent is not None:
+ user_agent = user_agent.decode("utf-8", "replace")
+
self.site.access_logger.info(
"%s - %s - {%s}"
" Processed request: %.3fsec (%.3fsec, %.3fsec) (%.3fsec/%.3fsec/%d)"
" %sB %s \"%s %s %s\" \"%s\" [%d dbevts]",
self.getClientIP(),
self.site.site_tag,
- self.authenticated_entity,
+ authenticated_entity,
end_time - self.start_time,
ru_utime,
ru_stime,
@@ -125,7 +140,7 @@ class SynapseRequest(Request):
self.method,
self.get_redacted_uri(),
self.clientproto,
- self.get_user_agent(),
+ user_agent,
evt_db_fetch_count,
)
|