activitypub-academy/app/services/batched_remove_status_service.rb

158 lines
5.1 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
class BatchedRemoveStatusService < BaseService
include StreamEntryRenderer
# Delete given statuses and reblogs of them
# Dispatch PuSH updates of the deleted statuses, but only local ones
# Dispatch Salmon deletes, unique per domain, of the deleted statuses, but only local ones
# Remove statuses from home feeds
# Push delete events to streaming API for home feeds and public feeds
# @param [Status] statuses A preferably batched array of statuses
def call(statuses)
statuses = Status.where(id: statuses.map(&:id)).includes(:account, :stream_entry).flat_map { |status| [status] + status.reblogs.includes(:account, :stream_entry).to_a }
@mentions = statuses.map { |s| [s.id, s.mentions.includes(:account).to_a] }.to_h
@tags = statuses.map { |s| [s.id, s.tags.pluck(:name)] }.to_h
@stream_entry_batches = []
@salmon_batches = []
@activity_json_batches = []
Change IDs to strings rather than numbers in API JSON output (#5019) * Fix JavaScript interface with long IDs Somewhat predictably, the JS interface handled IDs as numbers, which in JS are IEEE double-precision floats. This loses some precision when working with numbers as large as those generated by the new ID scheme, so we instead handle them here as strings. This is relatively simple, and doesn't appear to have caused any problems, but should definitely be tested more thoroughly than the built-in tests. Several days of use appear to support this working properly. BREAKING CHANGE: The major(!) change here is that IDs are now returned as strings by the REST endpoints, rather than as integers. In practice, relatively few changes were required to make the existing JS UI work with this change, but it will likely hit API clients pretty hard: it's an entirely different type to consume. (The one API client I tested, Tusky, handles this with no problems, however.) Twitter ran into this issue when introducing Snowflake IDs, and decided to instead introduce an `id_str` field in JSON responses. I have opted to *not* do that, and instead force all IDs to 64-bit integers represented by strings in one go. (I believe Twitter exacerbated their problem by rolling out the changes three times: once for statuses, once for DMs, and once for user IDs, as well as by leaving an integer ID value in JSON. As they said, "If you’re using the `id` field with JSON in a Javascript-related language, there is a very high likelihood that the integers will be silently munged by Javascript interpreters. In most cases, this will result in behavior such as being unable to load or delete a specific direct message, because the ID you're sending to the API is different than the actual identifier associated with the message." [1]) However, given that this is a significant change for API users, alternatives or a transition time may be appropriate. 1: https://blog.twitter.com/developer/en_us/a/2011/direct-messages-going-snowflake-on-sep-30-2011.html * Additional fixes for stringified IDs in JSON These should be the last two. These were identified using eslint to try to identify any plain casts to JavaScript numbers. (Some such casts are legitimate, but these were not.) Adding the following to .eslintrc.yml will identify casts to numbers: ~~~ no-restricted-syntax: - warn - selector: UnaryExpression[operator='+'] > :not(Literal) message: Avoid the use of unary + - selector: CallExpression[callee.name='Number'] message: Casting with Number() may coerce string IDs to numbers ~~~ The remaining three casts appear legitimate: two casts to array indices, one in a server to turn an environment variable into a number. * Back out RelationshipsController Change This was made to make a test a bit less flakey, but has nothing to do with this branch. * Change internal streaming payloads to stringified IDs as well Per https://github.com/tootsuite/mastodon/pull/5019#issuecomment-330736452 we need these changes to send deleted status IDs as strings, not integers.
2017-09-20 21:53:48 +09:00
@json_payloads = statuses.map { |s| [s.id, Oj.dump(event: :delete, payload: s.id.to_s)] }.to_h
@activity_json = {}
@activity_xml = {}
# Ensure that rendered XML reflects destroyed state
statuses.each(&:destroy)
# Batch by source account
statuses.group_by(&:account_id).each do |_, account_statuses|
account = account_statuses.first.account
unpush_from_home_timelines(account_statuses)
if account.local?
batch_stream_entries(account, account_statuses)
batch_activity_json(account, account_statuses)
end
end
# Cannot be batched
statuses.each do |status|
unpush_from_public_timelines(status)
batch_salmon_slaps(status) if status.local?
end
Pubsubhubbub::RawDistributionWorker.push_bulk(@stream_entry_batches) { |batch| batch }
NotificationWorker.push_bulk(@salmon_batches) { |batch| batch }
ActivityPub::DeliveryWorker.push_bulk(@activity_json_batches) { |batch| batch }
end
private
def batch_stream_entries(account, statuses)
statuses.each do |status|
@stream_entry_batches << [build_xml(status.stream_entry), account.id]
end
end
def batch_activity_json(account, statuses)
account.followers.inboxes.each do |inbox_url|
statuses.each do |status|
@activity_json_batches << [build_json(status), account.id, inbox_url]
end
end
statuses.each do |status|
other_recipients = (status.mentions + status.reblogs).map(&:account).reject(&:local?).select(&:activitypub?).uniq(&:id)
other_recipients.each do |target_account|
@activity_json_batches << [build_json(status), account.id, target_account.inbox_url]
end
end
end
def unpush_from_home_timelines(statuses)
account = statuses.first.account
recipients = account.followers.local.pluck(:id)
recipients << account.id if account.local?
recipients.each do |follower_id|
unpush(follower_id, statuses)
end
end
def unpush_from_public_timelines(status)
return unless status.public_visibility?
payload = @json_payloads[status.id]
redis.pipelined do
redis.publish('timeline:public', payload)
redis.publish('timeline:public:local', payload) if status.local?
@tags[status.id].each do |hashtag|
redis.publish("timeline:hashtag:#{hashtag}", payload)
redis.publish("timeline:hashtag:#{hashtag}:local", payload) if status.local?
end
end
end
def batch_salmon_slaps(status)
return if @mentions[status.id].empty?
recipients = @mentions[status.id].map(&:account).reject(&:local?).select(&:ostatus?).uniq(&:domain).map(&:id)
recipients.each do |recipient_id|
@salmon_batches << [build_xml(status.stream_entry), status.account_id, recipient_id]
end
end
def unpush(follower_id, statuses)
key = FeedManager.instance.key(:home, follower_id)
originals = statuses.reject(&:reblog?)
2017-07-31 22:19:13 +09:00
reblogs = statuses.select(&:reblog?)
# Quickly remove all originals
redis.pipelined do
originals.each do |status|
redis.zremrangebyscore(key, status.id, status.id)
redis.publish("timeline:#{follower_id}", @json_payloads[status.id])
end
end
# For reblogs, re-add original status to feed, unless the reblog
# was not in the feed in the first place
reblogs.each do |status|
redis.zadd(key, status.reblog_of_id, status.reblog_of_id) unless redis.zscore(key, status.reblog_of_id).nil?
redis.publish("timeline:#{follower_id}", @json_payloads[status.id])
end
end
def redis
Redis.current
end
def build_json(status)
return @activity_json[status.id] if @activity_json.key?(status.id)
@activity_json[status.id] = sign_json(status, ActiveModelSerializers::SerializableResource.new(
status,
serializer: status.reblog? ? ActivityPub::UndoAnnounceSerializer : ActivityPub::DeleteSerializer,
adapter: ActivityPub::Adapter
).as_json)
end
def build_xml(stream_entry)
return @activity_xml[stream_entry.id] if @activity_xml.key?(stream_entry.id)
@activity_xml[stream_entry.id] = stream_entry_to_xml(stream_entry)
end
def sign_json(status, json)
Oj.dump(ActivityPub::LinkedDataSignature.new(json).sign!(status.account))
end
end