Merge branch 'develop' of github.com:matrix-org/synapse into erikj/split_out_fed_txn

10 files changed, 396 insertions, 25 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 1ce58632b8..a1a0624674 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -1,3 +1,31 @@
+Changes in synapse v0.18.4 (2016-11-22)
+=======================================
+
+Bug fixes:
+
+* Add workaround for buggy clients that the fail to register (PR #1632)
+
+
+Changes in synapse v0.18.4-rc1 (2016-11-14)
+===========================================
+
+Changes:
+
+* Various database efficiency improvements (PR #1188, #1192)
+* Update default config to blacklist more internal IPs, thanks to Euan Kemp (PR
+  #1198)
+* Allow specifying duration in minutes in config, thanks to Daniel Dent (PR
+  #1625)
+
+
+Bug fixes:
+
+* Fix media repo to set CORs headers on responses (PR #1190)
+* Fix registration to not error on non-ascii passwords (PR #1191)
+* Fix create event code to limit the number of prev_events (PR #1615)
+* Fix bug in transaction ID deduplication (PR #1624)
+
+
 Changes in synapse v0.18.3 (2016-11-08)
 =======================================
 
diff --git a/synapse/__init__.py b/synapse/__init__.py
index d366b69dab..432567a110 100644
--- a/synapse/__init__.py
+++ b/synapse/__init__.py
@@ -16,4 +16,4 @@
 """ This is a reference implementation of a Matrix home server.
 """
 
-__version__ = "0.18.3"
+__version__ = "0.18.4"
diff --git a/synapse/api/errors.py b/synapse/api/errors.py
index 0041646858..921c457738 100644
--- a/synapse/api/errors.py
+++ b/synapse/api/errors.py
@@ -39,6 +39,7 @@ class Codes(object):
     CAPTCHA_NEEDED = "M_CAPTCHA_NEEDED"
     CAPTCHA_INVALID = "M_CAPTCHA_INVALID"
     MISSING_PARAM = "M_MISSING_PARAM"
+    INVALID_PARAM = "M_INVALID_PARAM"
     TOO_LARGE = "M_TOO_LARGE"
     EXCLUSIVE = "M_EXCLUSIVE"
     THREEPID_AUTH_FAILED = "M_THREEPID_AUTH_FAILED"
diff --git a/synapse/api/filtering.py b/synapse/api/filtering.py
index 3b3ef70750..fb291d7fb9 100644
--- a/synapse/api/filtering.py
+++ b/synapse/api/filtering.py
@@ -71,6 +71,21 @@ class Filtering(object):
                 if key in user_filter_json["room"]:
                     self._check_definition(user_filter_json["room"][key])
 
+        if "event_fields" in user_filter_json:
+            if type(user_filter_json["event_fields"]) != list:
+                raise SynapseError(400, "event_fields must be a list of strings")
+            for field in user_filter_json["event_fields"]:
+                if not isinstance(field, basestring):
+                    raise SynapseError(400, "Event field must be a string")
+                # Don't allow '\\' in event field filters. This makes matching
+                # events a lot easier as we can then use a negative lookbehind
+                # assertion to split '\.' If we allowed \\ then it would
+                # incorrectly split '\\.' See synapse.events.utils.serialize_event
+                if r'\\' in field:
+                    raise SynapseError(
+                        400, r'The escape character \ cannot itself be escaped'
+                    )
+
     def _check_definition_room_lists(self, definition):
         """Check that "rooms" and "not_rooms" are lists of room ids if they
         are present
@@ -152,6 +167,7 @@ class FilterCollection(object):
         self.include_leave = filter_json.get("room", {}).get(
             "include_leave", False
         )
+        self.event_fields = filter_json.get("event_fields", [])
 
     def __repr__(self):
         return "<FilterCollection %s>" % (json.dumps(self._filter_json),)
@@ -186,6 +202,26 @@ class FilterCollection(object):
     def filter_room_account_data(self, events):
         return self._room_account_data.filter(self._room_filter.filter(events))
 
+    def blocks_all_presence(self):
+        return (
+            self._presence_filter.filters_all_types() or
+            self._presence_filter.filters_all_senders()
+        )
+
+    def blocks_all_room_ephemeral(self):
+        return (
+            self._room_ephemeral_filter.filters_all_types() or
+            self._room_ephemeral_filter.filters_all_senders() or
+            self._room_ephemeral_filter.filters_all_rooms()
+        )
+
+    def blocks_all_room_timeline(self):
+        return (
+            self._room_timeline_filter.filters_all_types() or
+            self._room_timeline_filter.filters_all_senders() or
+            self._room_timeline_filter.filters_all_rooms()
+        )
+
 
 class Filter(object):
     def __init__(self, filter_json):
@@ -202,6 +238,15 @@ class Filter(object):
 
         self.contains_url = self.filter_json.get("contains_url", None)
 
+    def filters_all_types(self):
+        return "*" in self.not_types
+
+    def filters_all_senders(self):
+        return "*" in self.not_senders
+
+    def filters_all_rooms(self):
+        return "*" in self.not_rooms
+
     def check(self, event):
         """Checks whether the filter matches the given event.
 
diff --git a/synapse/events/utils.py b/synapse/events/utils.py
index 0e9fd902af..5bbaef8187 100644
--- a/synapse/events/utils.py
+++ b/synapse/events/utils.py
@@ -16,6 +16,17 @@
 from synapse.api.constants import EventTypes
 from . import EventBase
 
+from frozendict import frozendict
+
+import re
+
+# Split strings on "." but not "\." This uses a negative lookbehind assertion for '\'
+# (?<!stuff) matches if the current position in the string is not preceded
+# by a match for 'stuff'.
+# TODO: This is fast, but fails to handle "foo\\.bar" which should be treated as
+#       the literal fields "foo\" and "bar" but will instead be treated as "foo\\.bar"
+SPLIT_FIELD_REGEX = re.compile(r'(?<!\\)\.')
+
 
 def prune_event(event):
     """ Returns a pruned version of the given event, which removes all keys we
@@ -97,6 +108,83 @@ def prune_event(event):
     )
 
 
+def _copy_field(src, dst, field):
+    """Copy the field in 'src' to 'dst'.
+
+    For example, if src={"foo":{"bar":5}} and dst={}, and field=["foo","bar"]
+    then dst={"foo":{"bar":5}}.
+
+    Args:
+        src(dict): The dict to read from.
+        dst(dict): The dict to modify.
+        field(list<str>): List of keys to drill down to in 'src'.
+    """
+    if len(field) == 0:  # this should be impossible
+        return
+    if len(field) == 1:  # common case e.g. 'origin_server_ts'
+        if field[0] in src:
+            dst[field[0]] = src[field[0]]
+        return
+
+    # Else is a nested field e.g. 'content.body'
+    # Pop the last field as that's the key to move across and we need the
+    # parent dict in order to access the data. Drill down to the right dict.
+    key_to_move = field.pop(-1)
+    sub_dict = src
+    for sub_field in field:  # e.g. sub_field => "content"
+        if sub_field in sub_dict and type(sub_dict[sub_field]) in [dict, frozendict]:
+            sub_dict = sub_dict[sub_field]
+        else:
+            return
+
+    if key_to_move not in sub_dict:
+        return
+
+    # Insert the key into the output dictionary, creating nested objects
+    # as required. We couldn't do this any earlier or else we'd need to delete
+    # the empty objects if the key didn't exist.
+    sub_out_dict = dst
+    for sub_field in field:
+        sub_out_dict = sub_out_dict.setdefault(sub_field, {})
+    sub_out_dict[key_to_move] = sub_dict[key_to_move]
+
+
+def only_fields(dictionary, fields):
+    """Return a new dict with only the fields in 'dictionary' which are present
+    in 'fields'.
+
+    If there are no event fields specified then all fields are included.
+    The entries may include '.' charaters to indicate sub-fields.
+    So ['content.body'] will include the 'body' field of the 'content' object.
+    A literal '.' character in a field name may be escaped using a '\'.
+
+    Args:
+        dictionary(dict): The dictionary to read from.
+        fields(list<str>): A list of fields to copy over. Only shallow refs are
+        taken.
+    Returns:
+        dict: A new dictionary with only the given fields. If fields was empty,
+        the same dictionary is returned.
+    """
+    if len(fields) == 0:
+        return dictionary
+
+    # for each field, convert it:
+    # ["content.body.thing\.with\.dots"] => [["content", "body", "thing\.with\.dots"]]
+    split_fields = [SPLIT_FIELD_REGEX.split(f) for f in fields]
+
+    # for each element of the output array of arrays:
+    # remove escaping so we can use the right key names.
+    split_fields[:] = [
+        [f.replace(r'\.', r'.') for f in field_array] for field_array in split_fields
+    ]
+
+    output = {}
+    for field_array in split_fields:
+        _copy_field(dictionary, output, field_array)
+    return output
+
+
 def format_event_raw(d):
     return d
 
@@ -137,7 +225,7 @@ def format_event_for_client_v2_without_room_id(d):
 
 def serialize_event(e, time_now_ms, as_client_event=True,
                     event_format=format_event_for_client_v1,
-                    token_id=None):
+                    token_id=None, only_event_fields=None):
     # FIXME(erikj): To handle the case of presence events and the like
     if not isinstance(e, EventBase):
         return e
@@ -164,6 +252,12 @@ def serialize_event(e, time_now_ms, as_client_event=True,
                 d["unsigned"]["transaction_id"] = txn_id
 
     if as_client_event:
-        return event_format(d)
-    else:
-        return d
+        d = event_format(d)
+
+    if only_event_fields:
+        if (not isinstance(only_event_fields, list) or
+                not all(isinstance(f, basestring) for f in only_event_fields)):
+            raise TypeError("only_event_fields must be a list of strings")
+        d = only_fields(d, only_event_fields)
+
+    return d
diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py
index 1f910ff814..a86996689c 100644
--- a/synapse/handlers/sync.py
+++ b/synapse/handlers/sync.py
@@ -277,6 +277,7 @@ class SyncHandler(object):
         """
         with Measure(self.clock, "load_filtered_recents"):
             timeline_limit = sync_config.filter_collection.timeline_limit()
+            block_all_timeline = sync_config.filter_collection.blocks_all_room_timeline()
 
             if recents is None or newly_joined_room or timeline_limit < len(recents):
                 limited = True
@@ -293,7 +294,7 @@ class SyncHandler(object):
             else:
                 recents = []
 
-            if not limited:
+            if not limited or block_all_timeline:
                 defer.returnValue(TimelineBatch(
                     events=recents,
                     prev_batch=now_token,
@@ -531,9 +532,14 @@ class SyncHandler(object):
         )
         newly_joined_rooms, newly_joined_users = res
 
-        yield self._generate_sync_entry_for_presence(
-            sync_result_builder, newly_joined_rooms, newly_joined_users
+        block_all_presence_data = (
+            since_token is None and
+            sync_config.filter_collection.blocks_all_presence()
         )
+        if not block_all_presence_data:
+            yield self._generate_sync_entry_for_presence(
+                sync_result_builder, newly_joined_rooms, newly_joined_users
+            )
 
         yield self._generate_sync_entry_for_to_device(sync_result_builder)
 
@@ -709,13 +715,20 @@ class SyncHandler(object):
             `(newly_joined_rooms, newly_joined_users)`
         """
         user_id = sync_result_builder.sync_config.user.to_string()
-
-        now_token, ephemeral_by_room = yield self.ephemeral_by_room(
-            sync_result_builder.sync_config,
-            now_token=sync_result_builder.now_token,
-            since_token=sync_result_builder.since_token,
+        block_all_room_ephemeral = (
+            sync_result_builder.since_token is None and
+            sync_result_builder.sync_config.filter_collection.blocks_all_room_ephemeral()
         )
-        sync_result_builder.now_token = now_token
+
+        if block_all_room_ephemeral:
+            ephemeral_by_room = {}
+        else:
+            now_token, ephemeral_by_room = yield self.ephemeral_by_room(
+                sync_result_builder.sync_config,
+                now_token=sync_result_builder.now_token,
+                since_token=sync_result_builder.since_token,
+            )
+            sync_result_builder.now_token = now_token
 
         ignored_account_data = yield self.store.get_global_account_data_by_type_for_user(
             "m.ignored_user_list", user_id=user_id,
diff --git a/synapse/rest/client/v2_alpha/register.py b/synapse/rest/client/v2_alpha/register.py
index 68d18a9b82..6cfb20866b 100644
--- a/synapse/rest/client/v2_alpha/register.py
+++ b/synapse/rest/client/v2_alpha/register.py
@@ -169,6 +169,17 @@ class RegisterRestServlet(RestServlet):
 
         guest_access_token = body.get("guest_access_token", None)
 
+        if (
+            'initial_device_display_name' in body and
+            'password' not in body
+        ):
+            # ignore 'initial_device_display_name' if sent without
+            # a password to work around a client bug where it sent
+            # the 'initial_device_display_name' param alone, wiping out
+            # the original registration params
+            logger.warn("Ignoring initial_device_display_name without password")
+            del body['initial_device_display_name']
+
         session_id = self.auth_handler.get_session_id(body)
         registered_user_id = None
         if session_id:
diff --git a/synapse/rest/client/v2_alpha/sync.py b/synapse/rest/client/v2_alpha/sync.py
index 6fc63715aa..7199ec883a 100644
--- a/synapse/rest/client/v2_alpha/sync.py
+++ b/synapse/rest/client/v2_alpha/sync.py
@@ -162,7 +162,7 @@ class SyncRestServlet(RestServlet):
         time_now = self.clock.time_msec()
 
         joined = self.encode_joined(
-            sync_result.joined, time_now, requester.access_token_id
+            sync_result.joined, time_now, requester.access_token_id, filter.event_fields
         )
 
         invited = self.encode_invited(
@@ -170,7 +170,7 @@ class SyncRestServlet(RestServlet):
         )
 
         archived = self.encode_archived(
-            sync_result.archived, time_now, requester.access_token_id
+            sync_result.archived, time_now, requester.access_token_id, filter.event_fields
         )
 
         response_content = {
@@ -197,7 +197,7 @@ class SyncRestServlet(RestServlet):
             formatted.append(event)
         return {"events": formatted}
 
-    def encode_joined(self, rooms, time_now, token_id):
+    def encode_joined(self, rooms, time_now, token_id, event_fields):
         """
         Encode the joined rooms in a sync result
 
@@ -208,7 +208,8 @@ class SyncRestServlet(RestServlet):
                 calculations
             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.
         Returns:
             dict[str, dict[str, object]]: the joined rooms list, in our
                 response format
@@ -216,7 +217,7 @@ class SyncRestServlet(RestServlet):
         joined = {}
         for room in rooms:
             joined[room.room_id] = self.encode_room(
-                room, time_now, token_id
+                room, time_now, token_id, only_fields=event_fields
             )
 
         return joined
@@ -253,7 +254,7 @@ class SyncRestServlet(RestServlet):
 
         return invited
 
-    def encode_archived(self, rooms, time_now, token_id):
+    def encode_archived(self, rooms, time_now, token_id, event_fields):
         """
         Encode the archived rooms in a sync result
 
@@ -264,7 +265,8 @@ class SyncRestServlet(RestServlet):
                 calculations
             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.
         Returns:
             dict[str, dict[str, object]]: The invited rooms list, in our
                 response format
@@ -272,13 +274,13 @@ class SyncRestServlet(RestServlet):
         joined = {}
         for room in rooms:
             joined[room.room_id] = self.encode_room(
-                room, time_now, token_id, joined=False
+                room, time_now, token_id, joined=False, only_fields=event_fields
             )
 
         return joined
 
     @staticmethod
-    def encode_room(room, time_now, token_id, joined=True):
+    def encode_room(room, time_now, token_id, joined=True, only_fields=None):
         """
         Args:
             room (JoinedSyncResult|ArchivedSyncResult): sync result for a
@@ -289,7 +291,7 @@ class SyncRestServlet(RestServlet):
                 of transaction IDs
             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.
         Returns:
             dict[str, object]: the room, encoded in our response format
         """
@@ -298,6 +300,7 @@ class SyncRestServlet(RestServlet):
             return serialize_event(
                 event, time_now, token_id=token_id,
                 event_format=format_event_for_client_v2_without_room_id,
+                only_event_fields=only_fields,
             )
 
         state_dict = room.state
diff --git a/synapse/storage/filtering.py b/synapse/storage/filtering.py
index 5248736816..a2ccc66ea7 100644
--- a/synapse/storage/filtering.py
+++ b/synapse/storage/filtering.py
@@ -16,6 +16,7 @@
 from twisted.internet import defer
 
 from ._base import SQLBaseStore
+from synapse.api.errors import SynapseError, Codes
 from synapse.util.caches.descriptors import cachedInlineCallbacks
 
 import simplejson as json
@@ -24,6 +25,13 @@ import simplejson as json
 class FilteringStore(SQLBaseStore):
     @cachedInlineCallbacks(num_args=2)
     def get_user_filter(self, user_localpart, filter_id):
+        # filter_id is BIGINT UNSIGNED, so if it isn't a number, fail
+        # with a coherent error message rather than 500 M_UNKNOWN.
+        try:
+            int(filter_id)
+        except ValueError:
+            raise SynapseError(400, "Invalid filter ID", Codes.INVALID_PARAM)
+
         def_json = yield self._simple_select_one_onecol(
             table="user_filters",
             keyvalues={
diff --git a/tests/events/test_utils.py b/tests/events/test_utils.py
index fb0953c4ec..29f068d1f1 100644
--- a/tests/events/test_utils.py
+++ b/tests/events/test_utils.py
@@ -17,7 +17,11 @@
 from .. import unittest
 
 from synapse.events import FrozenEvent
-from synapse.events.utils import prune_event
+from synapse.events.utils import prune_event, serialize_event
+
+
+def MockEvent(**kwargs):
+    return FrozenEvent(kwargs)
 
 
 class PruneEventTestCase(unittest.TestCase):
@@ -114,3 +118,167 @@ class PruneEventTestCase(unittest.TestCase):
                 'unsigned': {},
             }
         )
+
+
+class SerializeEventTestCase(unittest.TestCase):
+
+    def serialize(self, ev, fields):
+        return serialize_event(ev, 1479807801915, only_event_fields=fields)
+
+    def test_event_fields_works_with_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar"
+                ),
+                ["room_id"]
+            ),
+            {
+                "room_id": "!foo:bar",
+            }
+        )
+
+    def test_event_fields_works_with_nested_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "body": "A message",
+                    },
+                ),
+                ["content.body"]
+            ),
+            {
+                "content": {
+                    "body": "A message",
+                }
+            }
+        )
+
+    def test_event_fields_works_with_dot_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "key.with.dots": {},
+                    },
+                ),
+                ["content.key\.with\.dots"]
+            ),
+            {
+                "content": {
+                    "key.with.dots": {},
+                }
+            }
+        )
+
+    def test_event_fields_works_with_nested_dot_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "not_me": 1,
+                        "nested.dot.key": {
+                            "leaf.key": 42,
+                            "not_me_either": 1,
+                        },
+                    },
+                ),
+                ["content.nested\.dot\.key.leaf\.key"]
+            ),
+            {
+                "content": {
+                    "nested.dot.key": {
+                        "leaf.key": 42,
+                    },
+                }
+            }
+        )
+
+    def test_event_fields_nops_with_unknown_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "foo": "bar",
+                    },
+                ),
+                ["content.foo", "content.notexists"]
+            ),
+            {
+                "content": {
+                    "foo": "bar",
+                }
+            }
+        )
+
+    def test_event_fields_nops_with_non_dict_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "foo": ["I", "am", "an", "array"],
+                    },
+                ),
+                ["content.foo.am"]
+            ),
+            {}
+        )
+
+    def test_event_fields_nops_with_array_keys(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    sender="@alice:localhost",
+                    room_id="!foo:bar",
+                    content={
+                        "foo": ["I", "am", "an", "array"],
+                    },
+                ),
+                ["content.foo.1"]
+            ),
+            {}
+        )
+
+    def test_event_fields_all_fields_if_empty(self):
+        self.assertEquals(
+            self.serialize(
+                MockEvent(
+                    room_id="!foo:bar",
+                    content={
+                        "foo": "bar",
+                    },
+                ),
+                []
+            ),
+            {
+                "room_id": "!foo:bar",
+                "content": {
+                    "foo": "bar",
+                },
+                "unsigned": {}
+            }
+        )
+
+    def test_event_fields_fail_if_fields_not_str(self):
+        with self.assertRaises(TypeError):
+            self.serialize(
+                MockEvent(
+                    room_id="!foo:bar",
+                    content={
+                        "foo": "bar",
+                    },
+                ),
+                ["room_id", 4]
+            )