fix merge conflicts

CHANGES.rst

@@ -3,7 +3,8 @@ Changes in synapse v0.27.0-rc2 (2018-03-19)
 Bugs:
 
 * Fix bug introduced in v0.27.0-rc1 that causes much increased memory usage in state cache (PR #3005)
-
+* Fix bug where an invalid event caused server to stop functioning correctly,
+  due to parsing and serializing bugs in ujson library. (pulled in from 0.26.1)
 
 Changes in synapse v0.27.0-rc1 (2018-03-14)
 ===========================================
@@ -54,6 +55,15 @@ Bug fixes:
 * Fix slow event search, switch back from GIST to GIN indexes (PR #2769, #2848)
 
 
+Changes in synapse v0.26.1 (2018-03-15)
+=======================================
+
+Bug fixes:
+
+* Fix bug where an invalid event caused server to stop functioning correctly,
+  due to parsing and serializing bugs in ujson library.
+
+
 
 Changes in synapse v0.26.0 (2018-01-05)
 =======================================

CONTRIBUTING.rst

@@ -30,8 +30,12 @@ use github's pull request workflow to review the contribution, and either ask
 you to make any refinements needed or merge it and make them ourselves. The
 changes will then land on master when we next do a release.
 
-We use Jenkins for continuous integration (http://matrix.org/jenkins), and
-typically all pull requests get automatically tested Jenkins: if your change breaks the build, Jenkins will yell about it in #matrix-dev:matrix.org so please lurk there and keep an eye open.
+We use `Jenkins <http://matrix.org/jenkins>`_ and 
+`Travis <https://travis-ci.org/matrix-org/synapse>`_ for continuous
+integration. All pull requests to synapse get automatically tested by Travis; 
+the Jenkins builds require an adminstrator to start them. If your change 
+breaks the build, this will be shown in github, so please keep an eye on the 
+pull request for feedback.
 
 Code style
 ~~~~~~~~~~

README.rst

@@ -354,6 +354,10 @@ https://matrix.org/docs/projects/try-matrix-now.html (or build your own with one
 Fedora
 ------
 
+Synapse is in the Fedora repositories as ``matrix-synapse``::
+
+    sudo dnf install matrix-synapse
+
 Oleg Girko provides Fedora RPMs at
 https://obs.infoserver.lv/project/monitor/matrix-synapse
 
@@ -890,6 +894,17 @@ This should end with a 'PASSED' result::
 
     PASSED (successes=143)
 
+Running the Integration Tests
+=============================
+
+Synapse is accompanied by `SyTest <https://github.com/matrix-org/sytest>`_,
+a Matrix homeserver integration testing suite, which uses HTTP requests to
+access the API as a Matrix client would. It is able to run Synapse directly from
+the source tree, so installation of the server is not required.
+
+Testing with SyTest is recommended for verifying that changes related to the
+Client-Server API are functioning correctly. See the `installation instructions
+<https://github.com/matrix-org/sytest#installing>`_ for details.
 
 Building Internal API Documentation
 ===================================

synapse/api/filtering.py

@@ -17,7 +17,7 @@ from synapse.storage.presence import UserPresenceState
 from synapse.types import UserID, RoomID
 from twisted.internet import defer
 
-import ujson as json
+import simplejson as json
 import jsonschema
 from jsonschema import FormatChecker
 

synapse/config/registration.py

@@ -77,7 +77,9 @@ class RegistrationConfig(Config):
 
         # Set the number of bcrypt rounds used to generate password hash.
         # Larger numbers increase the work factor needed to generate the hash.
-        # The default number of rounds is 12.
+        # The default number is 12 (which equates to 2^12 rounds).
+        # N.B. that increasing this will exponentially increase the time required
+        # to register or login - e.g. 24 => 2^24 rounds which will take >20 mins.
         bcrypt_rounds: 12
 
         # Allows users to register as guests without a password/email/etc, and

synapse/handlers/e2e_keys.py

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import ujson as json
+import simplejson as json
 import logging
 
 from canonicaljson import encode_canonical_json

synapse/handlers/message.py

@@ -38,7 +38,7 @@ from canonicaljson import encode_canonical_json
 
 import logging
 import random
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -678,8 +678,8 @@ class EventCreationHandler(object):
 
         # Ensure that we can round trip before trying to persist in db
         try:
-            dump = ujson.dumps(unfreeze(event.content))
-            ujson.loads(dump)
+            dump = simplejson.dumps(unfreeze(event.content))
+            simplejson.loads(dump)
         except Exception:
             logger.exception("Failed to encode content: %r", event.content)
             raise

synapse/http/server.py

@@ -37,7 +37,7 @@ from twisted.web.util import redirectTo
 import collections
 import logging
 import urllib
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -461,8 +461,7 @@ def respond_with_json(request, code, json_object, send_cors=False,
         if canonical_json or synapse.events.USE_FROZEN_DICTS:
             json_bytes = encode_canonical_json(json_object)
         else:
-            # ujson doesn't like frozen_dicts.
-            json_bytes = ujson.dumps(json_object, ensure_ascii=False)
+            json_bytes = simplejson.dumps(json_object)
 
     return respond_with_json_bytes(
         request, code, json_bytes,

synapse/replication/tcp/commands.py

@@ -19,7 +19,7 @@ allowed to be sent by which side.
 """
 
 import logging
-import ujson as json
+import simplejson as json
 
 
 logger = logging.getLogger(__name__)

synapse/rest/client/v1/room.py

@@ -30,7 +30,7 @@ from synapse.http.servlet import (
 
 import logging
 import urllib
-import ujson as json
+import simplejson as json
 
 logger = logging.getLogger(__name__)
 

synapse/rest/client/v2_alpha/sync.py

@@ -33,7 +33,7 @@ from ._base import set_timeline_upper_limit
 import itertools
 import logging
 
-import ujson as json
+import simplejson as json
 
 logger = logging.getLogger(__name__)
 

synapse/rest/media/v1/preview_url_resource.py

@@ -23,7 +23,7 @@ import re
 import shutil
 import sys
 import traceback
-import ujson as json
+import simplejson as json
 import urlparse
 
 from twisted.web.server import NOT_DONE_YET

synapse/storage/account_data.py

@@ -23,7 +23,7 @@ from synapse.util.caches.stream_change_cache import StreamChangeCache
 from synapse.util.caches.descriptors import cached, cachedList, cachedInlineCallbacks
 
 import abc
-import ujson as json
+import simplejson as json
 import logging
 
 logger = logging.getLogger(__name__)

synapse/storage/background_updates.py

@@ -19,7 +19,7 @@ from . import engines
 
 from twisted.internet import defer
 
-import ujson as json
+import simplejson as json
 import logging
 
 logger = logging.getLogger(__name__)

synapse/storage/deviceinbox.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 
 import logging
-import ujson
+import simplejson
 
 from twisted.internet import defer
 
@@ -85,7 +85,7 @@ class DeviceInboxStore(BackgroundUpdateStore):
             )
             rows = []
             for destination, edu in remote_messages_by_destination.items():
-                edu_json = ujson.dumps(edu)
+                edu_json = simplejson.dumps(edu)
                 rows.append((destination, stream_id, now_ms, edu_json))
             txn.executemany(sql, rows)
 
@@ -177,7 +177,7 @@ class DeviceInboxStore(BackgroundUpdateStore):
                     " WHERE user_id = ?"
                 )
                 txn.execute(sql, (user_id,))
-                message_json = ujson.dumps(messages_by_device["*"])
+                message_json = simplejson.dumps(messages_by_device["*"])
                 for row in txn:
                     # Add the message for all devices for this user on this
                     # server.
@@ -199,7 +199,7 @@ class DeviceInboxStore(BackgroundUpdateStore):
                     # Only insert into the local inbox if the device exists on
                     # this server
                     device = row[0]
-                    message_json = ujson.dumps(messages_by_device[device])
+                    message_json = simplejson.dumps(messages_by_device[device])
                     messages_json_for_user[device] = message_json
 
             if messages_json_for_user:
@@ -253,7 +253,7 @@ class DeviceInboxStore(BackgroundUpdateStore):
             messages = []
             for row in txn:
                 stream_pos = row[0]
-                messages.append(ujson.loads(row[1]))
+                messages.append(simplejson.loads(row[1]))
             if len(messages) < limit:
                 stream_pos = current_stream_id
             return (messages, stream_pos)
@@ -389,7 +389,7 @@ class DeviceInboxStore(BackgroundUpdateStore):
             messages = []
             for row in txn:
                 stream_pos = row[0]
-                messages.append(ujson.loads(row[1]))
+                messages.append(simplejson.loads(row[1]))
             if len(messages) < limit:
                 stream_pos = current_stream_id
             return (messages, stream_pos)

synapse/storage/devices.py

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import logging
-import ujson as json
+import simplejson as json
 
 from twisted.internet import defer
 

synapse/storage/end_to_end_keys.py

@@ -17,7 +17,7 @@ from twisted.internet import defer
 from synapse.util.caches.descriptors import cached
 
 from canonicaljson import encode_canonical_json
-import ujson as json
+import simplejson as json
 
 from ._base import SQLBaseStore
 

synapse/storage/event_push_actions.py

@@ -22,7 +22,7 @@ from synapse.types import RoomStreamToken
 from .stream import lower_bound
 
 import logging
-import ujson as json
+import simplejson as json
 
 logger = logging.getLogger(__name__)
 

synapse/storage/events.py

@@ -38,7 +38,7 @@ from functools import wraps
 import synapse.metrics
 
 import logging
-import ujson as json
+import simplejson as json
 
 # these are only included to make the type annotations work
 from synapse.events import EventBase    # noqa: F401
@@ -56,7 +56,6 @@ event_counter = metrics.register_counter(
 
 def encode_json(json_object):
     if USE_FROZEN_DICTS:
-        # ujson doesn't like frozen_dicts
         return encode_canonical_json(json_object)
     else:
         return json.dumps(json_object, ensure_ascii=False)

synapse/storage/events_worker.py

@@ -28,7 +28,7 @@ from synapse.api.errors import SynapseError
 from collections import namedtuple
 
 import logging
-import ujson as json
+import simplejson as json
 
 # these are only included to make the type annotations work
 from synapse.events import EventBase    # noqa: F401

synapse/storage/receipts.py

@@ -23,7 +23,7 @@ from twisted.internet import defer
 
 import abc
 import logging
-import ujson as json
+import simplejson as json
 
 
 logger = logging.getLogger(__name__)

synapse/storage/room.py

@@ -22,7 +22,7 @@ from synapse.util.caches.descriptors import cached, cachedInlineCallbacks
 
 import collections
 import logging
-import ujson as json
+import simplejson as json
 import re
 
 logger = logging.getLogger(__name__)

synapse/storage/roommember.py

@@ -28,7 +28,7 @@ from synapse.api.constants import Membership, EventTypes
 from synapse.types import get_domain_from_id
 
 import logging
-import ujson as json
+import simplejson as json
 
 logger = logging.getLogger(__name__)
 

synapse/storage/schema/delta/25/fts.py

@@ -17,7 +17,7 @@ import logging
 from synapse.storage.prepare_database import get_statements
 from synapse.storage.engines import PostgresEngine, Sqlite3Engine
 
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -66,7 +66,7 @@ def run_create(cur, database_engine, *args, **kwargs):
             "max_stream_id_exclusive": max_stream_id + 1,
             "rows_inserted": 0,
         }
-        progress_json = ujson.dumps(progress)
+        progress_json = simplejson.dumps(progress)
 
         sql = (
             "INSERT into background_updates (update_name, progress_json)"

synapse/storage/schema/delta/27/ts.py

@@ -16,7 +16,7 @@ import logging
 
 from synapse.storage.prepare_database import get_statements
 
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -45,7 +45,7 @@ def run_create(cur, database_engine, *args, **kwargs):
             "max_stream_id_exclusive": max_stream_id + 1,
             "rows_inserted": 0,
         }
-        progress_json = ujson.dumps(progress)
+        progress_json = simplejson.dumps(progress)
 
         sql = (
             "INSERT into background_updates (update_name, progress_json)"

synapse/storage/schema/delta/31/search_update.py

@@ -16,7 +16,7 @@ from synapse.storage.engines import PostgresEngine
 from synapse.storage.prepare_database import get_statements
 
 import logging
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -49,7 +49,7 @@ def run_create(cur, database_engine, *args, **kwargs):
             "rows_inserted": 0,
             "have_added_indexes": False,
         }
-        progress_json = ujson.dumps(progress)
+        progress_json = simplejson.dumps(progress)
 
         sql = (
             "INSERT into background_updates (update_name, progress_json)"

synapse/storage/schema/delta/33/event_fields.py

@@ -15,7 +15,7 @@
 from synapse.storage.prepare_database import get_statements
 
 import logging
-import ujson
+import simplejson
 
 logger = logging.getLogger(__name__)
 
@@ -44,7 +44,7 @@ def run_create(cur, database_engine, *args, **kwargs):
             "max_stream_id_exclusive": max_stream_id + 1,
             "rows_inserted": 0,
         }
-        progress_json = ujson.dumps(progress)
+        progress_json = simplejson.dumps(progress)
 
         sql = (
             "INSERT into background_updates (update_name, progress_json)"

synapse/storage/search.py

@@ -16,7 +16,7 @@
 from collections import namedtuple
 import logging
 import re
-import ujson as json
+import simplejson as json
 
 from twisted.internet import defer
 

synapse/storage/tags.py

@@ -19,7 +19,7 @@ from synapse.storage.account_data import AccountDataWorkerStore
 from synapse.util.caches.descriptors import cached
 from twisted.internet import defer
 
-import ujson as json
+import simplejson as json
 import logging
 
 logger = logging.getLogger(__name__)

synapse/storage/transactions.py

@@ -23,7 +23,7 @@ from canonicaljson import encode_canonical_json
 from collections import namedtuple
 
 import logging
-import ujson as json
+import simplejson as json
 
 logger = logging.getLogger(__name__)
 

synapse/util/caches/dictionary_cache.py

@@ -132,9 +132,13 @@ class DictionaryCache(object):
                 self._update_or_insert(key, value, known_absent)
 
     def _update_or_insert(self, key, value, known_absent):
-        entry = self.cache.setdefault(key, DictionaryEntry(False, set(), {}))
+        # We pop and reinsert as we need to tell the cache the size may have
+        # changed
+
+        entry = self.cache.pop(key, DictionaryEntry(False, set(), {}))
         entry.value.update(value)
         entry.known_absent.update(known_absent)
+        self.cache[key] = entry
 
     def _insert(self, key, value, known_absent):
         self.cache[key] = DictionaryEntry(True, known_absent, value)

synapse/util/caches/lrucache.py

@@ -154,14 +154,21 @@ class LruCache(object):
         def cache_set(key, value, callbacks=[]):
             node = cache.get(key, None)
             if node is not None:
-                if value != node.value:
+                # We sometimes store large objects, e.g. dicts, which cause
+                # the inequality check to take a long time. So let's only do
+                # the check if we have some callbacks to call.
+                if node.callbacks and value != node.value:
                     for cb in node.callbacks:
                         cb()
                     node.callbacks.clear()
 
-                    if size_callback:
-                        cached_cache_len[0] -= size_callback(node.value)
-                        cached_cache_len[0] += size_callback(value)
+                # We don't bother to protect this by value != node.value as
+                # generally size_callback will be cheap compared with equality
+                # checks. (For example, taking the size of two dicts is quicker
+                # than comparing them for equality.)
+                if size_callback:
+                    cached_cache_len[0] -= size_callback(node.value)
+                    cached_cache_len[0] += size_callback(value)
 
                 node.callbacks.update(callbacks)