diff options
Diffstat (limited to 'synapse')
| -rw-r--r-- | synapse/__init__.py | 2 | ||||
| -rw-r--r-- | synapse/api/filtering.py | 1 | ||||
| -rw-r--r-- | synapse/appservice/api.py | 13 | ||||
| -rw-r--r-- | synapse/federation/federation_base.py | 126 | ||||
| -rw-r--r-- | synapse/federation/federation_server.py | 30 | ||||
| -rw-r--r-- | synapse/federation/persistence.py | 8 | ||||
| -rw-r--r-- | synapse/federation/transport/server.py | 2 | ||||
| -rw-r--r-- | synapse/handlers/auth.py | 8 | ||||
| -rw-r--r-- | synapse/handlers/e2e_keys.py | 5 | ||||
| -rw-r--r-- | synapse/handlers/federation.py | 6 | ||||
| -rw-r--r-- | synapse/handlers/room_list.py | 2 | ||||
| -rw-r--r-- | synapse/handlers/search.py | 14 | ||||
| -rw-r--r-- | synapse/handlers/sync.py | 22 | ||||
| -rw-r--r-- | synapse/http/client.py | 82 | ||||
| -rw-r--r-- | synapse/http/matrixfederationclient.py | 204 | ||||
| -rw-r--r-- | synapse/http/site.py | 4 | ||||
| -rw-r--r-- | synapse/python_dependencies.py | 5 | ||||
| -rw-r--r-- | synapse/rest/client/v2_alpha/account.py | 16 | ||||
| -rw-r--r-- | synapse/rest/client/v2_alpha/register.py | 12 | ||||
| -rw-r--r-- | synapse/rest/client/v2_alpha/sync.py | 51 |
20 files changed, 348 insertions, 265 deletions
diff --git a/synapse/__init__.py b/synapse/__init__.py index e62901b761..e395a0a9ee 100644 --- a/synapse/__init__.py +++ b/synapse/__init__.py @@ -17,4 +17,4 @@ """ This is a reference implementation of a Matrix home server. """ -__version__ = "0.33.3" +__version__ = "0.33.3.1" diff --git a/synapse/api/filtering.py b/synapse/api/filtering.py index 186831e118..a31a9a17e0 100644 --- a/synapse/api/filtering.py +++ b/synapse/api/filtering.py @@ -251,6 +251,7 @@ class FilterCollection(object): "include_leave", False ) self.event_fields = filter_json.get("event_fields", []) + self.event_format = filter_json.get("event_format", "client") def __repr__(self): return "<FilterCollection %s>" % (json.dumps(self._filter_json),) diff --git a/synapse/appservice/api.py b/synapse/appservice/api.py index 6980e5890e..9ccc5a80fc 100644 --- a/synapse/appservice/api.py +++ b/synapse/appservice/api.py @@ -13,7 +13,8 @@ # See the License for the specific language governing permissions and # limitations under the License. import logging -import urllib + +from six.moves import urllib from prometheus_client import Counter @@ -98,7 +99,7 @@ class ApplicationServiceApi(SimpleHttpClient): def query_user(self, service, user_id): if service.url is None: defer.returnValue(False) - uri = service.url + ("/users/%s" % urllib.quote(user_id)) + uri = service.url + ("/users/%s" % urllib.parse.quote(user_id)) response = None try: response = yield self.get_json(uri, { @@ -119,7 +120,7 @@ class ApplicationServiceApi(SimpleHttpClient): def query_alias(self, service, alias): if service.url is None: defer.returnValue(False) - uri = service.url + ("/rooms/%s" % urllib.quote(alias)) + uri = service.url + ("/rooms/%s" % urllib.parse.quote(alias)) response = None try: response = yield self.get_json(uri, { @@ -153,7 +154,7 @@ class ApplicationServiceApi(SimpleHttpClient): service.url, APP_SERVICE_PREFIX, kind, - urllib.quote(protocol) + urllib.parse.quote(protocol) ) try: response = yield self.get_json(uri, fields) @@ -188,7 +189,7 @@ class ApplicationServiceApi(SimpleHttpClient): uri = "%s%s/thirdparty/protocol/%s" % ( service.url, APP_SERVICE_PREFIX, - urllib.quote(protocol) + urllib.parse.quote(protocol) ) try: info = yield self.get_json(uri, {}) @@ -228,7 +229,7 @@ class ApplicationServiceApi(SimpleHttpClient): txn_id = str(txn_id) uri = service.url + ("/transactions/%s" % - urllib.quote(txn_id)) + urllib.parse.quote(txn_id)) try: yield self.put_json( uri=uri, diff --git a/synapse/federation/federation_base.py b/synapse/federation/federation_base.py index c11798093d..5be8e66fb8 100644 --- a/synapse/federation/federation_base.py +++ b/synapse/federation/federation_base.py @@ -13,17 +13,20 @@ # See the License for the specific language governing permissions and # limitations under the License. import logging +from collections import namedtuple import six from twisted.internet import defer +from twisted.internet.defer import DeferredList -from synapse.api.constants import MAX_DEPTH +from synapse.api.constants import MAX_DEPTH, EventTypes, Membership from synapse.api.errors import Codes, SynapseError from synapse.crypto.event_signing import check_event_content_hash from synapse.events import FrozenEvent from synapse.events.utils import prune_event from synapse.http.servlet import assert_params_in_dict +from synapse.types import get_domain_from_id from synapse.util import logcontext, unwrapFirstError logger = logging.getLogger(__name__) @@ -133,34 +136,25 @@ class FederationBase(object): * throws a SynapseError if the signature check failed. The deferreds run their callbacks in the sentinel logcontext. """ - - redacted_pdus = [ - prune_event(pdu) - for pdu in pdus - ] - - deferreds = self.keyring.verify_json_objects_for_server([ - (p.origin, p.get_pdu_json()) - for p in redacted_pdus - ]) + deferreds = _check_sigs_on_pdus(self.keyring, pdus) ctx = logcontext.LoggingContext.current_context() - def callback(_, pdu, redacted): + def callback(_, pdu): with logcontext.PreserveLoggingContext(ctx): if not check_event_content_hash(pdu): logger.warn( "Event content has been tampered, redacting %s: %s", pdu.event_id, pdu.get_pdu_json() ) - return redacted + return prune_event(pdu) if self.spam_checker.check_event_for_spam(pdu): logger.warn( "Event contains spam, redacting %s: %s", pdu.event_id, pdu.get_pdu_json() ) - return redacted + return prune_event(pdu) return pdu @@ -173,16 +167,116 @@ class FederationBase(object): ) return failure - for deferred, pdu, redacted in zip(deferreds, pdus, redacted_pdus): + for deferred, pdu in zip(deferreds, pdus): deferred.addCallbacks( callback, errback, - callbackArgs=[pdu, redacted], + callbackArgs=[pdu], errbackArgs=[pdu], ) return deferreds +class PduToCheckSig(namedtuple("PduToCheckSig", [ + "pdu", "redacted_pdu_json", "event_id_domain", "sender_domain", "deferreds", +])): + pass + + +def _check_sigs_on_pdus(keyring, pdus): + """Check that the given events are correctly signed + + Args: + keyring (synapse.crypto.Keyring): keyring object to do the checks + pdus (Collection[EventBase]): the events to be checked + + Returns: + List[Deferred]: a Deferred for each event in pdus, which will either succeed if + the signatures are valid, or fail (with a SynapseError) if not. + """ + + # (currently this is written assuming the v1 room structure; we'll probably want a + # separate function for checking v2 rooms) + + # we want to check that the event is signed by: + # + # (a) the server which created the event_id + # + # (b) the sender's server. + # + # - except in the case of invites created from a 3pid invite, which are exempt + # from this check, because the sender has to match that of the original 3pid + # invite, but the event may come from a different HS, for reasons that I don't + # entirely grok (why do the senders have to match? and if they do, why doesn't the + # joining server ask the inviting server to do the switcheroo with + # exchange_third_party_invite?). + # + # That's pretty awful, since redacting such an invite will render it invalid + # (because it will then look like a regular invite without a valid signature), + # and signatures are *supposed* to be valid whether or not an event has been + # redacted. But this isn't the worst of the ways that 3pid invites are broken. + # + # let's start by getting the domain for each pdu, and flattening the event back + # to JSON. + pdus_to_check = [ + PduToCheckSig( + pdu=p, + redacted_pdu_json=prune_event(p).get_pdu_json(), + event_id_domain=get_domain_from_id(p.event_id), + sender_domain=get_domain_from_id(p.sender), + deferreds=[], + ) + for p in pdus + ] + + # first make sure that the event is signed by the event_id's domain + deferreds = keyring.verify_json_objects_for_server([ + (p.event_id_domain, p.redacted_pdu_json) + for p in pdus_to_check + ]) + + for p, d in zip(pdus_to_check, deferreds): + p.deferreds.append(d) + + # now let's look for events where the sender's domain is different to the + # event id's domain (normally only the case for joins/leaves), and add additional + # checks. + pdus_to_check_sender = [ + p for p in pdus_to_check + if p.sender_domain != p.event_id_domain and not _is_invite_via_3pid(p.pdu) + ] + + more_deferreds = keyring.verify_json_objects_for_server([ + (p.sender_domain, p.redacted_pdu_json) + for p in pdus_to_check_sender + ]) + + for p, d in zip(pdus_to_check_sender, more_deferreds): + p.deferreds.append(d) + + # replace lists of deferreds with single Deferreds + return [_flatten_deferred_list(p.deferreds) for p in pdus_to_check] + + +def _flatten_deferred_list(deferreds): + """Given a list of one or more deferreds, either return the single deferred, or + combine into a DeferredList. + """ + if len(deferreds) > 1: + return DeferredList(deferreds, fireOnOneErrback=True, consumeErrors=True) + else: + assert len(deferreds) == 1 + return deferreds[0] + + +def _is_invite_via_3pid(event): + return ( + event.type == EventTypes.Member + and event.membership == Membership.INVITE + and "third_party_invite" in event.content + ) + + def event_from_pdu_json(pdu_json, outlier=False): """Construct a FrozenEvent from an event json received over federation diff --git a/synapse/federation/federation_server.py b/synapse/federation/federation_server.py index 3e0cd294a1..dbee404ea7 100644 --- a/synapse/federation/federation_server.py +++ b/synapse/federation/federation_server.py @@ -99,7 +99,7 @@ class FederationServer(FederationBase): @defer.inlineCallbacks @log_function - def on_incoming_transaction(self, transaction_data): + def on_incoming_transaction(self, origin, transaction_data): # keep this as early as possible to make the calculated origin ts as # accurate as possible. request_time = self._clock.time_msec() @@ -108,34 +108,33 @@ class FederationServer(FederationBase): if not transaction.transaction_id: raise Exception("Transaction missing transaction_id") - if not transaction.origin: - raise Exception("Transaction missing origin") logger.debug("[%s] Got transaction", transaction.transaction_id) # use a linearizer to ensure that we don't process the same transaction # multiple times in parallel. with (yield self._transaction_linearizer.queue( - (transaction.origin, transaction.transaction_id), + (origin, transaction.transaction_id), )): result = yield self._handle_incoming_transaction( - transaction, request_time, + origin, transaction, request_time, ) defer.returnValue(result) @defer.inlineCallbacks - def _handle_incoming_transaction(self, transaction, request_time): + def _handle_incoming_transaction(self, origin, transaction, request_time): """ Process an incoming transaction and return the HTTP response Args: + origin (unicode): the server making the request transaction (Transaction): incoming transaction request_time (int): timestamp that the HTTP request arrived at Returns: Deferred[(int, object)]: http response code and body """ - response = yield self.transaction_actions.have_responded(transaction) + response = yield self.transaction_actions.have_responded(origin, transaction) if response: logger.debug( @@ -149,7 +148,7 @@ class FederationServer(FederationBase): received_pdus_counter.inc(len(transaction.pdus)) - origin_host, _ = parse_server_name(transaction.origin) + origin_host, _ = parse_server_name(origin) pdus_by_room = {} @@ -190,7 +189,7 @@ class FederationServer(FederationBase): event_id = pdu.event_id try: yield self._handle_received_pdu( - transaction.origin, pdu + origin, pdu ) pdu_results[event_id] = {} except FederationError as e: @@ -212,7 +211,7 @@ class FederationServer(FederationBase): if hasattr(transaction, "edus"): for edu in (Edu(**x) for x in transaction.edus): yield self.received_edu( - transaction.origin, + origin, edu.edu_type, edu.content ) @@ -224,6 +223,7 @@ class FederationServer(FederationBase): logger.debug("Returning: %s", str(response)) yield self.transaction_actions.set_response( + origin, transaction, 200, response ) @@ -838,9 +838,9 @@ class ReplicationFederationHandlerRegistry(FederationHandlerRegistry): ) return self._send_edu( - edu_type=edu_type, - origin=origin, - content=content, + edu_type=edu_type, + origin=origin, + content=content, ) def on_query(self, query_type, args): @@ -851,6 +851,6 @@ class ReplicationFederationHandlerRegistry(FederationHandlerRegistry): return handler(args) return self._get_query_client( - query_type=query_type, - args=args, + query_type=query_type, + args=args, ) diff --git a/synapse/federation/persistence.py b/synapse/federation/persistence.py index 9146215c21..74ffd13b4f 100644 --- a/synapse/federation/persistence.py +++ b/synapse/federation/persistence.py @@ -36,7 +36,7 @@ class TransactionActions(object): self.store = datastore @log_function - def have_responded(self, transaction): + def have_responded(self, origin, transaction): """ Have we already responded to a transaction with the same id and origin? @@ -50,11 +50,11 @@ class TransactionActions(object): "transaction_id") return self.store.get_received_txn_response( - transaction.transaction_id, transaction.origin + transaction.transaction_id, origin ) @log_function - def set_response(self, transaction, code, response): + def set_response(self, origin, transaction, code, response): """ Persist how we responded to a transaction. Returns: @@ -66,7 +66,7 @@ class TransactionActions(object): return self.store.set_received_txn_response( transaction.transaction_id, - transaction.origin, + origin, code, response, ) diff --git a/synapse/federation/transport/server.py b/synapse/federation/transport/server.py index 7a993fd1cf..3972922ff9 100644 --- a/synapse/federation/transport/server.py +++ b/synapse/federation/transport/server.py @@ -353,7 +353,7 @@ class FederationSendServlet(BaseFederationServlet): try: code, response = yield self.handler.on_incoming_transaction( - transaction_data + origin, transaction_data, ) except Exception: logger.exception("on_incoming_transaction failed") diff --git a/synapse/handlers/auth.py b/synapse/handlers/auth.py index 4a81bd2ba9..2a5eab124f 100644 --- a/synapse/handlers/auth.py +++ b/synapse/handlers/auth.py @@ -895,22 +895,24 @@ class AuthHandler(BaseHandler): Args: password (unicode): Password to hash. - stored_hash (unicode): Expected hash value. + stored_hash (bytes): Expected hash value. Returns: Deferred(bool): Whether self.hash(password) == stored_hash. """ - def _do_validate_hash(): # Normalise the Unicode in the password pw = unicodedata.normalize("NFKC", password) return bcrypt.checkpw( pw.encode('utf8') + self.hs.config.password_pepper.encode("utf8"), - stored_hash.encode('utf8') + stored_hash ) if stored_hash: + if not isinstance(stored_hash, bytes): + stored_hash = stored_hash.encode('ascii') + return make_deferred_yieldable( threads.deferToThreadPool( self.hs.get_reactor(), diff --git a/synapse/handlers/e2e_keys.py b/synapse/handlers/e2e_keys.py index 5816bf8b4f..578e9250fb 100644 --- a/synapse/handlers/e2e_keys.py +++ b/synapse/handlers/e2e_keys.py @@ -330,7 +330,8 @@ class E2eKeysHandler(object): (algorithm, key_id, ex_json, key) ) else: - new_keys.append((algorithm, key_id, encode_canonical_json(key))) + new_keys.append(( + algorithm, key_id, encode_canonical_json(key).decode('ascii'))) yield self.store.add_e2e_one_time_keys( user_id, device_id, time_now, new_keys @@ -358,7 +359,7 @@ def _exception_to_failure(e): # Note that some Exceptions (notably twisted's ResponseFailed etc) don't # give a string for e.message, which json then fails to serialize. return { - "status": 503, "message": str(e.message), + "status": 503, "message": str(e), } diff --git a/synapse/handlers/federation.py b/synapse/handlers/federation.py index 3fa7a98445..0c68e8a472 100644 --- a/synapse/handlers/federation.py +++ b/synapse/handlers/federation.py @@ -594,7 +594,7 @@ class FederationHandler(BaseHandler): required_auth = set( a_id - for event in events + state_events.values() + auth_events.values() + for event in events + list(state_events.values()) + list(auth_events.values()) for a_id, _ in event.auth_events ) auth_events.update({ @@ -802,7 +802,7 @@ class FederationHandler(BaseHandler): ) continue except NotRetryingDestination as e: - logger.info(e.message) + logger.info(str(e)) continue except FederationDeniedError as e: logger.info(e) @@ -1358,7 +1358,7 @@ class FederationHandler(BaseHandler): ) if state_groups: - _, state = state_groups.items().pop() + _, state = list(state_groups.items()).pop() results = state if event.is_state(): diff --git a/synapse/handlers/room_list.py b/synapse/handlers/room_list.py index 37e41afd61..38e1737ec9 100644 --- a/synapse/handlers/room_list.py +++ b/synapse/handlers/room_list.py @@ -162,7 +162,7 @@ class RoomListHandler(BaseHandler): # Filter out rooms that we don't want to return rooms_to_scan = [ r for r in sorted_rooms - if r not in newly_unpublished and rooms_to_num_joined[room_id] > 0 + if r not in newly_unpublished and rooms_to_num_joined[r] > 0 ] total_room_count = len(rooms_to_scan) diff --git a/synapse/handlers/search.py b/synapse/handlers/search.py index c464adbd0b..0c1d52fd11 100644 --- a/synapse/handlers/search.py +++ b/synapse/handlers/search.py @@ -54,7 +54,7 @@ class SearchHandler(BaseHandler): batch_token = None if batch: try: - b = decode_base64(batch) + b = decode_base64(batch).decode('ascii') batch_group, batch_group_key, batch_token = b.split("\n") assert batch_group is not None @@ -258,18 +258,18 @@ class SearchHandler(BaseHandler): # it returns more from the same group (if applicable) rather # than reverting to searching all results again. if batch_group and batch_group_key: - global_next_batch = encode_base64("%s\n%s\n%s" % ( + global_next_batch = encode_base64(("%s\n%s\n%s" % ( batch_group, batch_group_key, pagination_token - )) + )).encode('ascii')) else: - global_next_batch = encode_base64("%s\n%s\n%s" % ( + global_next_batch = encode_base64(("%s\n%s\n%s" % ( "all", "", pagination_token - )) + )).encode('ascii')) for room_id, group in room_groups.items(): - group["next_batch"] = encode_base64("%s\n%s\n%s" % ( + group["next_batch"] = encode_base64(("%s\n%s\n%s" % ( "room_id", room_id, pagination_token - )) + )).encode('ascii')) allowed_events.extend(room_events) diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py index ef20c2296c..9f133ded3f 100644 --- a/synapse/handlers/sync.py +++ b/synapse/handlers/sync.py @@ -545,7 +545,7 @@ class SyncHandler(object): member_ids = { state_key: event_id - for (t, state_key), event_id in state_ids.iteritems() + for (t, state_key), event_id in iteritems(state_ids) if t == EventTypes.Member } name_id = state_ids.get((EventTypes.Name, '')) @@ -774,7 +774,7 @@ class SyncHandler(object): logger.debug("filtering state from %r...", state_ids) state_ids = { t: event_id - for t, event_id in state_ids.iteritems() + for t, event_id in iteritems(state_ids) if cache.get(t[1]) != event_id } logger.debug("...to %r", state_ids) @@ -1729,17 +1729,17 @@ def _calculate_state( event_id_to_key = { e: key for key, e in itertools.chain( - timeline_contains.items(), - previous.items(), - timeline_start.items(), - current.items(), + iteritems(timeline_contains), + iteritems(previous), + iteritems(timeline_start), + iteritems(current), ) } - c_ids = set(e for e in current.values()) - ts_ids = set(e for e in timeline_start.values()) - p_ids = set(e for e in previous.values()) - tc_ids = set(e for e in timeline_contains.values()) + c_ids = set(e for e in itervalues(current)) + ts_ids = set(e for e in itervalues(timeline_start)) + p_ids = set(e for e in itervalues(previous)) + tc_ids = set(e for e in itervalues(timeline_contains)) # If we are lazyloading room members, we explicitly add the membership events # for the senders in the timeline into the state block returned by /sync, @@ -1753,7 +1753,7 @@ def _calculate_state( if lazy_load_members: p_ids.difference_update( - e for t, e in timeline_start.iteritems() + e for t, e in iteritems(timeline_start) if t[0] == EventTypes.Member ) diff --git a/synapse/http/client.py b/synapse/http/client.py index ab4fbf59b2..4ba54fed05 100644 --- a/synapse/http/client.py +++ b/synapse/http/client.py @@ -13,24 +13,25 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. + import logging -import urllib -from six import StringIO +from six import text_type +from six.moves import urllib +import treq from canonicaljson import encode_canonical_json, json from prometheus_client import Counter from OpenSSL import SSL from OpenSSL.SSL import VERIFY_NONE -from twisted.internet import defer, protocol, reactor, ssl, task +from twisted.internet import defer, protocol, reactor, ssl from twisted.internet.endpoints import HostnameEndpoint, wrapClientTLS from twisted.web._newclient import ResponseDone from twisted.web.client import ( Agent, BrowserLikeRedirectAgent, ContentDecoderAgent, - FileBodyProducer as TwistedFileBodyProducer, GzipDecoder, HTTPConnectionPool, PartialDownloadError, @@ -83,18 +84,20 @@ class SimpleHttpClient(object): if hs.config.user_agent_suffix: self.user_agent = "%s %s" % (self.user_agent, hs.config.user_agent_suffix,) + self.user_agent = self.user_agent.encode('ascii') + @defer.inlineCallbacks - def request(self, method, uri, *args, **kwargs): + def request(self, method, uri, data=b'', headers=None): # A small wrapper around self.agent.request() so we can easily attach # counters to it outgoing_requests_counter.labels(method).inc() # log request but strip `access_token` (AS requests for example include this) - logger.info("Sending request %s %s", method, redact_uri(uri)) + logger.info("Sending request %s %s", method, redact_uri(uri.encode('ascii'))) try: - request_deferred = self.agent.request( - method, uri, *args, **kwargs + request_deferred = treq.request( + method, uri, agent=self.agent, data=data, headers=headers ) add_timeout_to_deferred( request_deferred, 60, self.hs.get_reactor(), @@ -105,14 +108,14 @@ class SimpleHttpClient(object): incoming_responses_counter.labels(method, response.code).inc() logger.info( "Received response to %s %s: %s", - method, redact_uri(uri), response.code + method, redact_uri(uri.encode('ascii')), response.code ) defer.returnValue(response) except Exception as e: incoming_responses_counter.labels(method, "ERR").inc() logger.info( "Error sending request to %s %s: %s %s", - method, redact_uri(uri), type(e).__name__, e.message + method, redact_uri(uri.encode('ascii')), type(e).__name__, e.args[0] ) raise @@ -137,7 +140,8 @@ class SimpleHttpClient(object): # TODO: Do we ever want to log message contents? logger.debug("post_urlencoded_get_json args: %s", args) - query_bytes = urllib.urlencode(encode_urlencode_args(args), True) + query_bytes = urllib.parse.urlencode( + encode_urlencode_args(args), True).encode("utf8") actual_headers = { b"Content-Type": [b"application/x-www-form-urlencoded"], @@ -148,15 +152,14 @@ class SimpleHttpClient(object): response = yield self.request( "POST", - uri.encode("ascii"), + uri, headers=Headers(actual_headers), - bodyProducer=FileBodyProducer(StringIO(query_bytes)) + data=query_bytes ) - body = yield make_deferred_yieldable(readBody(response)) - if 200 <= response.code < 300: - defer.returnValue(json.loads(body)) + body = yield make_deferred_yieldable(treq.json_content(response)) + defer.returnValue(body) else: raise HttpResponseException(response.code, response.phrase, body) @@ -191,9 +194,9 @@ class SimpleHttpClient(object): response = yield self.request( "POST", - uri.encode("ascii"), + uri, headers=Headers(actual_headers), - bodyProducer=FileBodyProducer(StringIO(json_str)) + data=json_str ) body = yield make_deferred_yieldable(readBody(response)) @@ -248,7 +251,7 @@ class SimpleHttpClient(object): ValueError: if the response was not JSON """ if len(args): - query_bytes = urllib.urlencode(args, True) + query_bytes = urllib.parse.urlencode(args, True) uri = "%s?%s" % (uri, query_bytes) json_str = encode_canonical_json(json_body) @@ -262,9 +265,9 @@ class SimpleHttpClient(object): response = yield self.request( "PUT", - uri.encode("ascii"), + uri, headers=Headers(actual_headers), - bodyProducer=FileBodyProducer(StringIO(json_str)) + data=json_str ) body = yield make_deferred_yieldable(readBody(response)) @@ -293,7 +296,7 @@ class SimpleHttpClient(object): HttpResponseException on a non-2xx HTTP response. """ if len(args): - query_bytes = urllib.urlencode(args, True) + query_bytes = urllib.parse.urlencode(args, True) uri = "%s?%s" % (uri, query_bytes) actual_headers = { @@ -304,7 +307,7 @@ class SimpleHttpClient(object): response = yield self.request( "GET", - uri.encode("ascii"), + uri, headers=Headers(actual_headers), ) @@ -339,7 +342,7 @@ class SimpleHttpClient(object): response = yield self.request( "GET", - url.encode("ascii"), + url, headers=Headers(actual_headers), ) @@ -434,12 +437,12 @@ class CaptchaServerHttpClient(SimpleHttpClient): @defer.inlineCallbacks def post_urlencoded_get_raw(self, url, args={}): - query_bytes = urllib.urlencode(encode_urlencode_args(args), True) + query_bytes = urllib.parse.urlencode(encode_urlencode_args(args), True) response = yield self.request( "POST", - url.encode("ascii"), - bodyProducer=FileBodyProducer(StringIO(query_bytes)), + url, + data=query_bytes, headers=Headers({ b"Content-Type": [b"application/x-www-form-urlencoded"], b"User-Agent": [self.user_agent], @@ -510,7 +513,7 @@ def encode_urlencode_args(args): def encode_urlencode_arg(arg): - if isinstance(arg, unicode): + if isinstance(arg, text_type): return arg.encode('utf-8') elif isinstance(arg, list): return [encode_urlencode_arg(i) for i in arg] @@ -542,26 +545,3 @@ class InsecureInterceptableContextFactory(ssl.ContextFactory): def creatorForNetloc(self, hostname, port): return self - - -class FileBodyProducer(TwistedFileBodyProducer): - """Workaround for https://twistedmatrix.com/trac/ticket/8473 - - We override the pauseProducing and resumeProducing methods in twisted's - FileBodyProducer so that they do not raise exceptions if the task has - already completed. - """ - - def pauseProducing(self): - try: - super(FileBodyProducer, self).pauseProducing() - except task.TaskDone: - # task has already completed - pass - - def resumeProducing(self): - try: - super(FileBodyProducer, self).resumeProducing() - except task.NotPaused: - # task was not paused (probably because it had already completed) - pass diff --git a/synapse/http/matrixfederationclient.py b/synapse/http/matrixfederationclient.py index b34bb8e31a..6a1fc8ca55 100644 --- a/synapse/http/matrixfederationclient.py +++ b/synapse/http/matrixfederationclient.py @@ -17,19 +17,19 @@ import cgi import logging import random import sys -import urllib -from six import string_types -from six.moves.urllib import parse as urlparse +from six import PY3, string_types +from six.moves import urllib -from canonicaljson import encode_canonical_json, json +import treq +from canonicaljson import encode_canonical_json from prometheus_client import Counter from signedjson.sign import sign_json from twisted.internet import defer, protocol, reactor from twisted.internet.error import DNSLookupError from twisted.web._newclient import ResponseDone -from twisted.web.client import Agent, HTTPConnectionPool, readBody +from twisted.web.client import Agent, HTTPConnectionPool from twisted.web.http_headers import Headers import synapse.metrics @@ -58,13 +58,18 @@ incoming_responses_counter = Counter("synapse_http_matrixfederationclient_respon MAX_LONG_RETRIES = 10 MAX_SHORT_RETRIES = 3 +if PY3: + MAXINT = sys.maxsize +else: + MAXINT = sys.maxint + class MatrixFederationEndpointFactory(object): def __init__(self, hs): self.tls_client_options_factory = hs.tls_client_options_factory def endpointForURI(self, uri): - destination = uri.netloc + destination = uri.netloc.decode('ascii') return matrix_federation_endpoint( reactor, destination, timeout=10, @@ -93,26 +98,32 @@ class MatrixFederationHttpClient(object): ) self.clock = hs.get_clock() self._store = hs.get_datastore() - self.version_string = hs.version_string + self.version_string = hs.version_string.encode('ascii') self._next_id = 1 def _create_url(self, destination, path_bytes, param_bytes, query_bytes): - return urlparse.urlunparse( - ("matrix", destination, path_bytes, param_bytes, query_bytes, "") + return urllib.parse.urlunparse( + (b"matrix", destination, path_bytes, param_bytes, query_bytes, b"") ) @defer.inlineCallbacks def _request(self, destination, method, path, - body_callback, headers_dict={}, param_bytes=b"", - query_bytes=b"", retry_on_dns_fail=True, + json=None, json_callback=None, + param_bytes=b"", + query=None, retry_on_dns_fail=True, timeout=None, long_retries=False, ignore_backoff=False, backoff_on_404=False): - """ Creates and sends a request to the given server + """ + Creates and sends a request to the given server. + Args: destination (str): The remote server to send the HTTP request to. method (str): HTTP method path (str): The HTTP path + json (dict or None): JSON to send in the body. + json_callback (func or None): A callback to generate the JSON. + query (dict or None): Query arguments. ignore_backoff (bool): true to ignore the historical backoff data and try the request anyway. backoff_on_404 (bool): Back off if we get a 404 @@ -146,22 +157,29 @@ class MatrixFederationHttpClient(object): ignore_backoff=ignore_backoff, ) - destination = destination.encode("ascii") + headers_dict = {} path_bytes = path.encode("ascii") - with limiter: - headers_dict[b"User-Agent"] = [self.version_string] - headers_dict[b"Host"] = [destination] + if query: + query_bytes = encode_query_args(query) + else: + query_bytes = b"" - url_bytes = self._create_url( - destination, path_bytes, param_bytes, query_bytes - ) + headers_dict = { + "User-Agent": [self.version_string], + "Host": [destination], + } + + with limiter: + url = self._create_url( + destination.encode("ascii"), path_bytes, param_bytes, query_bytes + ).decode('ascii') txn_id = "%s-O-%s" % (method, self._next_id) - self._next_id = (self._next_id + 1) % (sys.maxint - 1) + self._next_id = (self._next_id + 1) % (MAXINT - 1) outbound_logger.info( "{%s} [%s] Sending request: %s %s", - txn_id, destination, method, url_bytes + txn_id, destination, method, url ) # XXX: Would be much nicer to retry only at the transaction-layer @@ -171,23 +189,33 @@ class MatrixFederationHttpClient(object): else: retries_left = MAX_SHORT_RETRIES - http_url_bytes = urlparse.urlunparse( - ("", "", path_bytes, param_bytes, query_bytes, "") - ) + http_url = urllib.parse.urlunparse( + (b"", b"", path_bytes, param_bytes, query_bytes, b"") + ).decode('ascii') log_result = None try: while True: - producer = None - if body_callback: - producer = body_callback(method, http_url_bytes, headers_dict) - try: - request_deferred = self.agent.request( + if json_callback: + json = json_callback() + + if json: + data = encode_canonical_json(json) + headers_dict["Content-Type"] = ["application/json"] + self.sign_request( + destination, method, http_url, headers_dict, json + ) + else: + data = None + self.sign_request(destination, method, http_url, headers_dict) + + request_deferred = treq.request( method, - url_bytes, - Headers(headers_dict), - producer + url, + headers=Headers(headers_dict), + data=data, + agent=self.agent, ) add_timeout_to_deferred( request_deferred, @@ -218,7 +246,7 @@ class MatrixFederationHttpClient(object): txn_id, destination, method, - url_bytes, + url, _flatten_response_never_received(e), ) @@ -252,7 +280,7 @@ class MatrixFederationHttpClient(object): # :'( # Update transactions table? with logcontext.PreserveLoggingContext(): - body = yield readBody(response) + body = yield treq.content(response) raise HttpResponseException( response.code, response.phrase, body ) @@ -297,11 +325,11 @@ class MatrixFederationHttpClient(object): auth_headers = [] for key, sig in request["signatures"][self.server_name].items(): - auth_headers.append(bytes( + auth_headers.append(( "X-Matrix origin=%s,key=\"%s\",sig=\"%s\"" % ( self.server_name, key, sig, - ) - )) + )).encode('ascii') + ) headers_dict[b"Authorization"] = auth_headers @@ -347,24 +375,14 @@ class MatrixFederationHttpClient(object): """ if not json_data_callback: - def json_data_callback(): - return data - - def body_callback(method, url_bytes, headers_dict): - json_data = json_data_callback() - self.sign_request( - destination, method, url_bytes, headers_dict, json_data - ) - producer = _JsonProducer(json_data) - return producer + json_data_callback = lambda: data response = yield self._request( destination, "PUT", path, - body_callback=body_callback, - headers_dict={"Content-Type": ["application/json"]}, - query_bytes=encode_query_args(args), + json_callback=json_data_callback, + query=args, long_retries=long_retries, timeout=timeout, ignore_backoff=ignore_backoff, @@ -376,8 +394,8 @@ class MatrixFederationHttpClient(object): check_content_type_is_json(response.headers) with logcontext.PreserveLoggingContext(): - body = yield readBody(response) - defer.returnValue(json.loads(body)) + body = yield treq.json_content(response) + defer.returnValue(body) @defer.inlineCallbacks def post_json(self, destination, path, data={}, long_retries=False, @@ -410,20 +428,12 @@ class MatrixFederationHttpClient(object): Fails with ``FederationDeniedError`` if this destination is not on our federation whitelist """ - - def body_callback(method, url_bytes, headers_dict): - self.sign_request( - destination, method, url_bytes, headers_dict, data - ) - return _JsonProducer(data) - response = yield self._request( destination, "POST", path, - query_bytes=encode_query_args(args), - body_callback=body_callback, - headers_dict={"Content-Type": ["application/json"]}, + query=args, + json=data, long_retries=long_retries, timeout=timeout, ignore_backoff=ignore_backoff, @@ -434,9 +444,9 @@ class MatrixFederationHttpClient(object): check_content_type_is_json(response.headers) with logcontext.PreserveLoggingContext(): - body = yield readBody(response) + body = yield treq.json_content(response) - defer.returnValue(json.loads(body)) + defer.returnValue(body) @defer.inlineCallbacks def get_json(self, destination, path, args=None, retry_on_dns_fail=True, @@ -471,16 +481,11 @@ class MatrixFederationHttpClient(object): logger.debug("Query bytes: %s Retry DNS: %s", args, retry_on_dns_fail) - def body_callback(method, url_bytes, headers_dict): - self.sign_request(destination, method, url_bytes, headers_dict) - return None - response = yield self._request( destination, "GET", path, - query_bytes=encode_query_args(args), - body_callback=body_callback, + query=args, retry_on_dns_fail=retry_on_dns_fail, timeout=timeout, ignore_backoff=ignore_backoff, @@ -491,9 +496,9 @@ class MatrixFederationHttpClient(object): check_content_type_is_json(response.headers) with logcontext.PreserveLoggingContext(): - body = yield readBody(response) + body = yield treq.json_content(response) - defer.returnValue(json.loads(body)) + defer.returnValue(body) @defer.inlineCallbacks def delete_json(self, destination, path, long_retries=False, @@ -523,13 +528,11 @@ class MatrixFederationHttpClient(object): Fails with ``FederationDeniedError`` if this destination is not on our federation whitelist """ - response = yield self._request( destination, "DELETE", path, - query_bytes=encode_query_args(args), - headers_dict={"Content-Type": ["application/json"]}, + query=args, long_retries=long_retries, timeout=timeout, ignore_backoff=ignore_backoff, @@ -540,9 +543,9 @@ class MatrixFederationHttpClient(object): check_content_type_is_json(response.headers) with logcontext.PreserveLoggingContext(): - body = yield readBody(response) + body = yield treq.json_content(response) - defer.returnValue(json.loads(body)) + defer.returnValue(body) @defer.inlineCallbacks def get_file(self, destination, path, output_stream, args={}, @@ -569,26 +572,11 @@ class MatrixFederationHttpClient(object): Fails with ``FederationDeniedError`` if this destination is not on our federation whitelist """ - - encoded_args = {} - for k, vs in args.items(): - if isinstance(vs, string_types): - vs = [vs] - encoded_args[k] = [v.encode("UTF-8") for v in vs] - - query_bytes = urllib.urlencode(encoded_args, True) - logger.debug("Query bytes: %s Retry DNS: %s", query_bytes, retry_on_dns_fail) - - def body_callback(method, url_bytes, headers_dict): - self.sign_request(destination, method, url_bytes, headers_dict) - return None - response = yield self._request( destination, "GET", path, - query_bytes=query_bytes, - body_callback=body_callback, + query=args, retry_on_dns_fail=retry_on_dns_fail, ignore_backoff=ignore_backoff, ) @@ -639,30 +627,6 @@ def _readBodyToFile(response, stream, max_size): return d -class _JsonProducer(object): - """ Used by the twisted http client to create the HTTP body from json - """ - def __init__(self, jsn): - self.reset(jsn) - - def reset(self, jsn): - self.body = encode_canonical_json(jsn) - self.length = len(self.body) - - def startProducing(self, consumer): - consumer.write(self.body) - return defer.succeed(None) - - def pauseProducing(self): - pass - - def stopProducing(self): - pass - - def resumeProducing(self): - pass - - def _flatten_response_never_received(e): if hasattr(e, "reasons"): reasons = ", ".join( @@ -693,7 +657,7 @@ def check_content_type_is_json(headers): "No Content-Type header" ) - c_type = c_type[0] # only the first header + c_type = c_type[0].decode('ascii') # only the first header val, options = cgi.parse_header(c_type) if val != "application/json": raise RuntimeError( @@ -711,6 +675,6 @@ def encode_query_args(args): vs = [vs] encoded_args[k] = [v.encode("UTF-8") for v in vs] - query_bytes = urllib.urlencode(encoded_args, True) + query_bytes = urllib.parse.urlencode(encoded_args, True) - return query_bytes + return query_bytes.encode('utf8') diff --git a/synapse/http/site.py b/synapse/http/site.py index 88ed3714f9..f0828c6542 100644 --- a/synapse/http/site.py +++ b/synapse/http/site.py @@ -204,14 +204,14 @@ class SynapseRequest(Request): self.start_time = time.time() self.request_metrics = RequestMetrics() self.request_metrics.start( - self.start_time, name=servlet_name, method=self.method, + self.start_time, name=servlet_name, method=self.method.decode('ascii'), ) self.site.access_logger.info( "%s - %s - Received request: %s %s", self.getClientIP(), self.site.site_tag, - self.method, + self.method.decode('ascii'), self.get_redacted_uri() ) diff --git a/synapse/python_dependencies.py b/synapse/python_dependencies.py index 942d7c721f..0d8de600cf 100644 --- a/synapse/python_dependencies.py +++ b/synapse/python_dependencies.py @@ -40,9 +40,10 @@ REQUIREMENTS = { "pynacl>=1.2.1": ["nacl>=1.2.1", "nacl.bindings"], "service_identity>=1.0.0": ["service_identity>=1.0.0"], "Twisted>=17.1.0": ["twisted>=17.1.0"], + "treq>=15.1": ["treq>=15.1"], - # We use crypto.get_elliptic_curve which is only supported in >=0.15 - "pyopenssl>=0.15": ["OpenSSL>=0.15"], + # Twisted has required pyopenssl 16.0 since about Twisted 16.6. + "pyopenssl>=16.0.0": ["OpenSSL>=16.0.0"], "pyyaml": ["yaml"], "pyasn1": ["pyasn1"], diff --git a/synapse/rest/client/v2_alpha/account.py b/synapse/rest/client/v2_alpha/account.py index 372648cafd..37b32dd37b 100644 --- a/synapse/rest/client/v2_alpha/account.py +++ b/synapse/rest/client/v2_alpha/account.py @@ -53,7 +53,9 @@ class EmailPasswordRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "email", body['email']): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Your email domain is not authorized on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.hs.get_datastore().get_user_id_by_threepid( @@ -89,7 +91,9 @@ class MsisdnPasswordRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "msisdn", msisdn): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Account phone numbers are not authorized on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.datastore.get_user_id_by_threepid( @@ -241,7 +245,9 @@ class EmailThreepidRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "email", body['email']): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Your email domain is not authorized on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.datastore.get_user_id_by_threepid( @@ -276,7 +282,9 @@ class MsisdnThreepidRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "msisdn", msisdn): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Account phone numbers are not authorized on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.datastore.get_user_id_by_threepid( diff --git a/synapse/rest/client/v2_alpha/register.py b/synapse/rest/client/v2_alpha/register.py index 2fb4d43ccb..192f52e462 100644 --- a/synapse/rest/client/v2_alpha/register.py +++ b/synapse/rest/client/v2_alpha/register.py @@ -75,7 +75,9 @@ class EmailRegisterRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "email", body['email']): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Your email domain is not authorized to register on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.hs.get_datastore().get_user_id_by_threepid( @@ -115,7 +117,9 @@ class MsisdnRegisterRequestTokenRestServlet(RestServlet): if not check_3pid_allowed(self.hs, "msisdn", msisdn): raise SynapseError( - 403, "Third party identifier is not allowed", Codes.THREEPID_DENIED, + 403, + "Phone numbers are not authorized to register on this server", + Codes.THREEPID_DENIED, ) existingUid = yield self.hs.get_datastore().get_user_id_by_threepid( @@ -373,7 +377,9 @@ class RegisterRestServlet(RestServlet): if not check_3pid_allowed(self.hs, medium, address): raise SynapseError( - 403, "Third party identifier is not allowed", + 403, + "Third party identifiers (email/phone numbers)" + + " are not authorized on this server", Codes.THREEPID_DENIED, ) diff --git a/synapse/rest/client/v2_alpha/sync.py b/synapse/rest/client/v2_alpha/sync.py index 1275baa1ba..263d8eb73e 100644 --- a/synapse/rest/client/v2_alpha/sync.py +++ b/synapse/rest/client/v2_alpha/sync.py @@ -25,6 +25,7 @@ from synapse.api.errors import SynapseError from synapse.api.filtering import DEFAULT_FILTER_COLLECTION, FilterCollection from synapse.events.utils import ( format_event_for_client_v2_without_room_id, + format_event_raw, serialize_event, ) from synapse.handlers.presence import format_user_presence_state @@ -175,17 +176,28 @@ class SyncRestServlet(RestServlet): @staticmethod def encode_response(time_now, sync_result, access_token_id, filter): + if filter.event_format == 'client': + event_formatter = format_event_for_client_v2_without_room_id + elif filter.event_format == 'federation': + event_formatter = format_event_raw + else: + raise Exception("Unknown event format %s" % (filter.event_format, )) + joined = SyncRestServlet.encode_joined( - sync_result.joined, time_now, access_token_id, filter.event_fields + sync_result.joined, time_now, access_token_id, + filter.event_fields, + event_formatter, ) invited = SyncRestServlet.encode_invited( sync_result.invited, time_now, access_token_id, + event_formatter, ) archived = SyncRestServlet.encode_archived( sync_result.archived, time_now, access_token_id, filter.event_fields, + event_formatter, ) return { @@ -228,7 +240,7 @@ class SyncRestServlet(RestServlet): } @staticmethod - def encode_joined(rooms, time_now, token_id, event_fields): + def encode_joined(rooms, time_now, token_id, event_fields, event_formatter): """ Encode the joined rooms in a sync result @@ -240,7 +252,9 @@ class SyncRestServlet(RestServlet): token_id(int): ID of the user's auth token - used for namespacing of transaction IDs event_fields(list<str>): List of event fields to include. If empty, - all fields will be returned. + all fields will be returned. + event_formatter (func[dict]): function to convert from federation format + to client format Returns: dict[str, dict[str, object]]: the joined rooms list, in our response format @@ -248,13 +262,14 @@ class SyncRestServlet(RestServlet): joined = {} for room in rooms: joined[room.room_id] = SyncRestServlet.encode_room( - room, time_now, token_id, only_fields=event_fields + room, time_now, token_id, joined=True, only_fields=event_fields, + event_formatter=event_formatter, ) return joined @staticmethod - def encode_invited(rooms, time_now, token_id): + def encode_invited(rooms, time_now, token_id, event_formatter): """ Encode the invited rooms in a sync result @@ -264,7 +279,9 @@ class SyncRestServlet(RestServlet): time_now(int): current time - used as a baseline for age calculations token_id(int): ID of the user's auth token - used for namespacing - of transaction IDs + of transaction IDs + event_formatter (func[dict]): function to convert from federation format + to client format Returns: dict[str, dict[str, object]]: the invited rooms list, in our @@ -274,7 +291,7 @@ class SyncRestServlet(RestServlet): for room in rooms: invite = serialize_event( room.invite, time_now, token_id=token_id, - event_format=format_event_for_client_v2_without_room_id, + event_format=event_formatter, is_invite=True, ) unsigned = dict(invite.get("unsigned", {})) @@ -288,7 +305,7 @@ class SyncRestServlet(RestServlet): return invited @staticmethod - def encode_archived(rooms, time_now, token_id, event_fields): + def encode_archived(rooms, time_now, token_id, event_fields, event_formatter): """ Encode the archived rooms in a sync result @@ -300,7 +317,9 @@ class SyncRestServlet(RestServlet): token_id(int): ID of the user's auth token - used for namespacing of transaction IDs event_fields(list<str>): List of event fields to include. If empty, - all fields will be returned. + all fields will be returned. + event_formatter (func[dict]): function to convert from federation format + to client format Returns: dict[str, dict[str, object]]: The invited rooms list, in our response format @@ -308,13 +327,18 @@ class SyncRestServlet(RestServlet): joined = {} for room in rooms: joined[room.room_id] = SyncRestServlet.encode_room( - room, time_now, token_id, joined=False, only_fields=event_fields + room, time_now, token_id, joined=False, + only_fields=event_fields, + event_formatter=event_formatter, ) return joined @staticmethod - def encode_room(room, time_now, token_id, joined=True, only_fields=None): + def encode_room( + room, time_now, token_id, joined, + only_fields, event_formatter, + ): """ Args: room (JoinedSyncResult|ArchivedSyncResult): sync result for a @@ -326,14 +350,15 @@ class SyncRestServlet(RestServlet): joined (bool): True if the user is joined to this room - will mean we handle ephemeral events only_fields(list<str>): Optional. The list of event fields to include. + event_formatter (func[dict]): function to convert from federation format + to client format Returns: dict[str, object]: the room, encoded in our response format """ def serialize(event): - # TODO(mjark): Respect formatting requirements in the filter. return serialize_event( event, time_now, token_id=token_id, - event_format=format_event_for_client_v2_without_room_id, + event_format=event_formatter, only_event_fields=only_fields, ) |