Merge branch 'develop' of github.com:matrix-org/synapse into t3chguy/default_inviter_display_name_3pid

1 files changed, 229 insertions, 101 deletions

diff --git a/synapse/visibility.py b/synapse/visibility.py
index c4dd9ae2c7..d4680863d3 100644
--- a/synapse/visibility.py
+++ b/synapse/visibility.py
@@ -13,14 +13,17 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from twisted.internet import defer
-
-from synapse.api.constants import Membership, EventTypes
+import logging
+import operator
 
-from synapse.util.logcontext import preserve_fn, preserve_context_over_deferred
+from six import iteritems, itervalues
+from six.moves import map
 
-import logging
+from twisted.internet import defer
 
+from synapse.api.constants import EventTypes, Membership
+from synapse.events.utils import prune_event
+from synapse.types import get_domain_from_id
 
 logger = logging.getLogger(__name__)
 
@@ -43,53 +46,66 @@ MEMBERSHIP_PRIORITY = (
 
 
 @defer.inlineCallbacks
-def filter_events_for_clients(store, user_tuples, events, event_id_to_state):
-    """ Returns dict of user_id -> list of events that user is allowed to
-    see.
+def filter_events_for_client(store, user_id, events, is_peeking=False,
+                             always_include_ids=frozenset()):
+    """
+    Check which events a user is allowed to see
 
     Args:
-        user_tuples (str, bool): (user id, is_peeking) for each user to be
-            checked. is_peeking should be true if:
-            * the user is not currently a member of the room, and:
-            * the user has not been a member of the room since the
-            given events
-        events ([synapse.events.EventBase]): list of events to filter
-    """
-    forgotten = yield preserve_context_over_deferred(defer.gatherResults([
-        defer.maybeDeferred(
-            preserve_fn(store.who_forgot_in_room),
-            room_id,
-        )
-        for room_id in frozenset(e.room_id for e in events)
-    ], consumeErrors=True))
+        store (synapse.storage.DataStore): our datastore (can also be a worker
+            store)
+        user_id(str): user id to be checked
+        events(list[synapse.events.EventBase]): sequence of events to be checked
+        is_peeking(bool): should be True if:
+          * the user is not currently a member of the room, and:
+          * the user has not been a member of the room since the given
+            events
+        always_include_ids (set(event_id)): set of event ids to specifically
+            include (unless sender is ignored)
 
-    # Set of membership event_ids that have been forgotten
-    event_id_forgotten = frozenset(
-        row["event_id"] for rows in forgotten for row in rows
+    Returns:
+        Deferred[list[synapse.events.EventBase]]
+    """
+    types = (
+        (EventTypes.RoomHistoryVisibility, ""),
+        (EventTypes.Member, user_id),
+    )
+    event_id_to_state = yield store.get_state_for_events(
+        frozenset(e.event_id for e in events),
+        types=types,
     )
 
-    ignore_dict_content = yield store.get_global_account_data_by_type_for_users(
-        "m.ignored_user_list", user_ids=[user_id for user_id, _ in user_tuples]
+    ignore_dict_content = yield store.get_global_account_data_by_type_for_user(
+        "m.ignored_user_list", user_id,
     )
 
     # FIXME: This will explode if people upload something incorrect.
-    ignore_dict = {
-        user_id: frozenset(
-            content.get("ignored_users", {}).keys() if content else []
-        )
-        for user_id, content in ignore_dict_content.items()
-    }
+    ignore_list = frozenset(
+        ignore_dict_content.get("ignored_users", {}).keys()
+        if ignore_dict_content else []
+    )
+
+    erased_senders = yield store.are_users_erased((e.sender for e in events))
 
-    def allowed(event, user_id, is_peeking, ignore_list):
+    def allowed(event):
         """
         Args:
             event (synapse.events.EventBase): event to check
-            user_id (str)
-            is_peeking (bool)
-            ignore_list (list): list of users to ignore
+
+        Returns:
+            None|EventBase:
+               None if the user cannot see this event at all
+
+               a redacted copy of the event if they can only see a redacted
+               version
+
+               the original event if they can see it as normal.
         """
         if not event.is_state() and event.sender in ignore_list:
-            return False
+            return None
+
+        if event.event_id in always_include_ids:
+            return event
 
         state = event_id_to_state[event.event_id]
 
@@ -103,10 +119,6 @@ def filter_events_for_clients(store, user_tuples, events, event_id_to_state):
         if visibility not in VISIBILITY_PRIORITY:
             visibility = "shared"
 
-        # if it was world_readable, it's easy: everyone can read it
-        if visibility == "world_readable":
-            return True
-
         # Always allow history visibility events on boundaries. This is done
         # by setting the effective visibility to the least restrictive
         # of the old vs new.
@@ -140,7 +152,7 @@ def filter_events_for_clients(store, user_tuples, events, event_id_to_state):
             if membership == "leave" and (
                 prev_membership == "join" or prev_membership == "invite"
             ):
-                return True
+                return event
 
             new_priority = MEMBERSHIP_PRIORITY.index(membership)
             old_priority = MEMBERSHIP_PRIORITY.index(prev_membership)
@@ -151,87 +163,203 @@ def filter_events_for_clients(store, user_tuples, events, event_id_to_state):
         if membership is None:
             membership_event = state.get((EventTypes.Member, user_id), None)
             if membership_event:
-                if membership_event.event_id not in event_id_forgotten:
-                    membership = membership_event.membership
+                membership = membership_event.membership
 
         # if the user was a member of the room at the time of the event,
         # they can see it.
         if membership == Membership.JOIN:
-            return True
+            return event
+
+        # otherwise, it depends on the room visibility.
 
         if visibility == "joined":
             # we weren't a member at the time of the event, so we can't
             # see this event.
-            return False
+            return None
 
         elif visibility == "invited":
             # user can also see the event if they were *invited* at the time
             # of the event.
-            return membership == Membership.INVITE
-
-        else:
-            # visibility is shared: user can also see the event if they have
-            # become a member since the event
+            return (
+                event if membership == Membership.INVITE else None
+            )
+
+        elif visibility == "shared" and is_peeking:
+            # if the visibility is shared, users cannot see the event unless
+            # they have *subequently* joined the room (or were members at the
+            # time, of course)
             #
             # XXX: if the user has subsequently joined and then left again,
             # ideally we would share history up to the point they left. But
-            # we don't know when they left.
-            return not is_peeking
+            # we don't know when they left. We just treat it as though they
+            # never joined, and restrict access.
+            return None
 
-    defer.returnValue({
-        user_id: [
-            event
-            for event in events
-            if allowed(event, user_id, is_peeking, ignore_dict.get(user_id, []))
-        ]
-        for user_id, is_peeking in user_tuples
-    })
+        # the visibility is either shared or world_readable, and the user was
+        # not a member at the time. We allow it, provided the original sender
+        # has not requested their data to be erased, in which case, we return
+        # a redacted version.
+        if erased_senders[event.sender]:
+            return prune_event(event)
 
+        return event
 
-@defer.inlineCallbacks
-def filter_events_for_clients_context(store, user_tuples, events, event_id_to_context):
-    user_ids = set(u[0] for u in user_tuples)
-    event_id_to_state = {}
-    for event_id, context in event_id_to_context.items():
-        state = yield store.get_events([
-            e_id
-            for key, e_id in context.current_state_ids.iteritems()
-            if key == (EventTypes.RoomHistoryVisibility, "")
-            or (key[0] == EventTypes.Member and key[1] in user_ids)
-        ])
-        event_id_to_state[event_id] = state
-
-    res = yield filter_events_for_clients(
-        store, user_tuples, events, event_id_to_state
-    )
-    defer.returnValue(res)
+    # check each event: gives an iterable[None|EventBase]
+    filtered_events = map(allowed, events)
 
+    # remove the None entries
+    filtered_events = filter(operator.truth, filtered_events)
 
-@defer.inlineCallbacks
-def filter_events_for_client(store, user_id, events, is_peeking=False):
-    """
-    Check which events a user is allowed to see
+    # we turn it into a list before returning it.
+    defer.returnValue(list(filtered_events))
 
-    Args:
-        user_id(str): user id to be checked
-        events([synapse.events.EventBase]): list of events to be checked
-        is_peeking(bool): should be True if:
-          * the user is not currently a member of the room, and:
-          * the user has not been a member of the room since the given
-            events
 
-    Returns:
-        [synapse.events.EventBase]
-    """
-    types = (
-        (EventTypes.RoomHistoryVisibility, ""),
-        (EventTypes.Member, user_id),
+@defer.inlineCallbacks
+def filter_events_for_server(store, server_name, events):
+    # Whatever else we do, we need to check for senders which have requested
+    # erasure of their data.
+    erased_senders = yield store.are_users_erased(
+        e.sender for e in events,
     )
-    event_id_to_state = yield store.get_state_for_events(
+
+    def redact_disallowed(event, state):
+        # if the sender has been gdpr17ed, always return a redacted
+        # copy of the event.
+        if erased_senders[event.sender]:
+            logger.info(
+                "Sender of %s has been erased, redacting",
+                event.event_id,
+            )
+            return prune_event(event)
+
+        # state will be None if we decided we didn't need to filter by
+        # room membership.
+        if not state:
+            return event
+
+        history = state.get((EventTypes.RoomHistoryVisibility, ''), None)
+        if history:
+            visibility = history.content.get("history_visibility", "shared")
+            if visibility in ["invited", "joined"]:
+                # We now loop through all state events looking for
+                # membership states for the requesting server to determine
+                # if the server is either in the room or has been invited
+                # into the room.
+                for ev in itervalues(state):
+                    if ev.type != EventTypes.Member:
+                        continue
+                    try:
+                        domain = get_domain_from_id(ev.state_key)
+                    except Exception:
+                        continue
+
+                    if domain != server_name:
+                        continue
+
+                    memtype = ev.membership
+                    if memtype == Membership.JOIN:
+                        return event
+                    elif memtype == Membership.INVITE:
+                        if visibility == "invited":
+                            return event
+                else:
+                    # server has no users in the room: redact
+                    return prune_event(event)
+
+        return event
+
+    # Next lets check to see if all the events have a history visibility
+    # of "shared" or "world_readable". If thats the case then we don't
+    # need to check membership (as we know the server is in the room).
+    event_to_state_ids = yield store.get_state_ids_for_events(
         frozenset(e.event_id for e in events),
-        types=types
+        types=(
+            (EventTypes.RoomHistoryVisibility, ""),
+        )
     )
-    res = yield filter_events_for_clients(
-        store, [(user_id, is_peeking)], events, event_id_to_state
+
+    visibility_ids = set()
+    for sids in itervalues(event_to_state_ids):
+        hist = sids.get((EventTypes.RoomHistoryVisibility, ""))
+        if hist:
+            visibility_ids.add(hist)
+
+    # If we failed to find any history visibility events then the default
+    # is "shared" visiblity.
+    if not visibility_ids:
+        all_open = True
+    else:
+        event_map = yield store.get_events(visibility_ids)
+        all_open = all(
+            e.content.get("history_visibility") in (None, "shared", "world_readable")
+            for e in itervalues(event_map)
+        )
+
+    if all_open:
+        # all the history_visibility state affecting these events is open, so
+        # we don't need to filter by membership state. We *do* need to check
+        # for user erasure, though.
+        if erased_senders:
+            events = [
+                redact_disallowed(e, None)
+                for e in events
+            ]
+
+        defer.returnValue(events)
+
+    # Ok, so we're dealing with events that have non-trivial visibility
+    # rules, so we need to also get the memberships of the room.
+
+    # first, for each event we're wanting to return, get the event_ids
+    # of the history vis and membership state at those events.
+    event_to_state_ids = yield store.get_state_ids_for_events(
+        frozenset(e.event_id for e in events),
+        types=(
+            (EventTypes.RoomHistoryVisibility, ""),
+            (EventTypes.Member, None),
+        )
     )
-    defer.returnValue(res.get(user_id, []))
+
+    # We only want to pull out member events that correspond to the
+    # server's domain.
+    #
+    # event_to_state_ids contains lots of duplicates, so it turns out to be
+    # cheaper to build a complete set of unique
+    # ((type, state_key), event_id) tuples, and then filter out the ones we
+    # don't want.
+    #
+    state_key_to_event_id_set = {
+        e
+        for key_to_eid in itervalues(event_to_state_ids)
+        for e in key_to_eid.items()
+    }
+
+    def include(typ, state_key):
+        if typ != EventTypes.Member:
+            return True
+
+        # we avoid using get_domain_from_id here for efficiency.
+        idx = state_key.find(":")
+        if idx == -1:
+            return False
+        return state_key[idx + 1:] == server_name
+
+    event_map = yield store.get_events([
+        e_id
+        for key, e_id in state_key_to_event_id_set
+        if include(key[0], key[1])
+    ])
+
+    event_to_state = {
+        e_id: {
+            key: event_map[inner_e_id]
+            for key, inner_e_id in iteritems(key_to_eid)
+            if inner_e_id in event_map
+        }
+        for e_id, key_to_eid in iteritems(event_to_state_ids)
+    }
+
+    defer.returnValue([
+        redact_disallowed(e, event_to_state[e.event_id])
+        for e in events
+    ])