Add a /replication API for extracting the updates that happened on

synapse

This is necessary for replicating the data in synapse to be visible to a
separate service because presence and typing notifications aren't stored
in a database so won't be visible to another process.

This API can be used to either get the raw data by requesting the tables
themselves or to just receive notifications for updates by following the
streams meta-stream.

Returns updates for each table requested a JSON array of arrays with a
row for each row in the table.

Each table is prefixed by a header row with the: name of the table,
current stream_id position for the table, number of rows, number of
columns and the names of the columns.
This is followed by the rows that have been added to the server since
the requester last asked.

The API has a timeout and is hooked up to the notifier so that a slave
can long poll for updates.

2 files changed, 33 insertions, 0 deletions

diff --git a/synapse/handlers/presence.py b/synapse/handlers/presence.py
index 08e38cdd25..d98e80086e 100644
--- a/synapse/handlers/presence.py
+++ b/synapse/handlers/presence.py
@@ -774,6 +774,25 @@ class PresenceHandler(BaseHandler):
 
         defer.returnValue(observer_user.to_string() in accepted_observers)
 
+    @defer.inlineCallbacks
+    def get_all_presence_updates(self, last_id, current_id):
+        """
+        Gets a list of presence update rows from between the given stream ids.
+        Each row has:
+        - stream_id(str)
+        - user_id(str)
+        - state(str)
+        - last_active_ts(int)
+        - last_federation_update_ts(int)
+        - last_user_sync_ts(int)
+        - status_msg(int)
+        - currently_active(int)
+        """
+        # TODO(markjh): replicate the unpersisted changes.
+        # This could use the in-memory stores for recent changes.
+        rows = yield self.store.get_all_presence_updates(last_id, current_id)
+        defer.returnValue(rows)
+
 
 def should_notify(old_state, new_state):
     """Decides if a presence state change should be sent to interested parties.
diff --git a/synapse/handlers/typing.py b/synapse/handlers/typing.py
index b16d0017df..8ce27f49ec 100644
--- a/synapse/handlers/typing.py
+++ b/synapse/handlers/typing.py
@@ -25,6 +25,7 @@ from synapse.types import UserID
 import logging
 
 from collections import namedtuple
+import ujson as json
 
 logger = logging.getLogger(__name__)
 
@@ -219,6 +220,19 @@ class TypingNotificationHandler(BaseHandler):
                 "typing_key", self._latest_room_serial, rooms=[room_id]
             )
 
+    def get_all_typing_updates(self, last_id, current_id):
+        # TODO: Work out a way to do this without scanning the entire state.
+        rows = []
+        for room_id, serial in self._room_serials.items():
+            if last_id < serial and serial <= current_id:
+                typing = self._room_typing[room_id]
+                typing_bytes = json.dumps([
+                    u.to_string() for u in typing
+                ], ensure_ascii=False)
+                rows.append((serial, room_id, typing_bytes))
+        rows.sort()
+        return rows
+
 
 class TypingNotificationEventSource(object):
     def __init__(self, hs):