From 2d2828dcbc2c6360d28a64d3849cf849eb5348c4 Mon Sep 17 00:00:00 2001 From: Amber Brown Date: Thu, 6 Sep 2018 00:10:47 +1000 Subject: [PATCH] Port http/ to Python 3 (#3771) --- changelog.d/3771.misc | 1 + setup.cfg | 5 +- synapse/appservice/api.py | 13 +- synapse/federation/federation_server.py | 10 +- synapse/http/client.py | 82 ++++------ synapse/http/matrixfederationclient.py | 204 ++++++++++-------------- synapse/http/site.py | 4 +- synapse/python_dependencies.py | 1 + 8 files changed, 134 insertions(+), 186 deletions(-) create mode 100644 changelog.d/3771.misc diff --git a/changelog.d/3771.misc b/changelog.d/3771.misc new file mode 100644 index 0000000000..47aa34bc04 --- /dev/null +++ b/changelog.d/3771.misc @@ -0,0 +1 @@ +http/ is now ported to Python 3. diff --git a/setup.cfg b/setup.cfg index c2620be6c5..52feaa9cc7 100644 --- a/setup.cfg +++ b/setup.cfg @@ -17,13 +17,14 @@ ignore = [pep8] max-line-length = 90 # W503 requires that binary operators be at the end, not start, of lines. Erik -# doesn't like it. E203 is contrary to PEP8. -ignore = W503,E203 +# doesn't like it. E203 is contrary to PEP8. E731 is silly. +ignore = W503,E203,E731 [flake8] # note that flake8 inherits the "ignore" settings from "pep8" (because it uses # pep8 to do those checks), but not the "max-line-length" setting max-line-length = 90 +ignore=W503,E203,E731 [isort] line_length = 89 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_server.py b/synapse/federation/federation_server.py index 3e0cd294a1..6e52c4b6b5 100644 --- a/synapse/federation/federation_server.py +++ b/synapse/federation/federation_server.py @@ -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/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..6dd5179320 100644 --- a/synapse/python_dependencies.py +++ b/synapse/python_dependencies.py @@ -40,6 +40,7 @@ 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"],