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.
This commit is contained in:
Mark Haines 2016-03-01 14:49:41 +00:00
parent 742ec37ca3
commit 60a0f81c7a
15 changed files with 846 additions and 4 deletions

View file

@ -0,0 +1,67 @@
import requests
import collections
import sys
import time
import json
Entry = collections.namedtuple("Entry", "name position rows")
ROW_TYPES = {}
def row_type_for_columns(name, column_names):
column_names = tuple(column_names)
row_type = ROW_TYPES.get((name, column_names))
if row_type is None:
row_type = collections.namedtuple(name, column_names)
ROW_TYPES[(name, column_names)] = row_type
return row_type
def parse_response(content):
streams = json.loads(content)
result = {}
for name, value in streams.items():
row_type = row_type_for_columns(name, value["field_names"])
position = value["position"]
rows = [row_type(*row) for row in value["rows"]]
result[name] = Entry(name, position, rows)
return result
def replicate(server, streams):
return parse_response(requests.get(
server + "/_synapse/replication",
verify=False,
params=streams
).content)
def main():
server = sys.argv[1]
streams = None
while not streams:
try:
streams = {
row.name: row.position
for row in replicate(server, {"streams":"-1"})["streams"].rows
}
except requests.exceptions.ConnectionError as e:
time.sleep(0.1)
while True:
try:
results = replicate(server, streams)
except:
sys.stdout.write("connection_lost("+ repr(streams) + ")\n")
break
for update in results.values():
for row in update.rows:
sys.stdout.write(repr(row) + "\n")
streams[update.name] = update.position
if __name__=='__main__':
main()