table_sync 6.0.4 → 6.1.0

data/lib/table_sync/publishing/message/raw.rb

@@ -4,8 +4,11 @@ module TableSync::Publishing::Message
   class Raw
     include Tainbox
 
-    attribute :object_class
+    attribute :model_name
+    attribute :table_name
+    attribute :schema_name
     attribute :original_attributes
+
     attribute :routing_key
     attribute :headers
 
@@ -21,18 +24,14 @@ module TableSync::Publishing::Message
 
     def notify!
       TableSync::Instrument.notify(
-        table: model_naming.table,
-        schema: model_naming.schema,
+        table: table_name,
+        schema: schema_name,
         event: event,
         count: original_attributes.count,
         direction: :publish,
       )
     end
 
-    def model_naming
-      TableSync.publishing_adapter.model_naming(object_class.constantize)
-    end
-
     # MESSAGE PARAMS
 
     def message_params
@@ -41,13 +40,13 @@ module TableSync::Publishing::Message
 
     def data
       TableSync::Publishing::Data::Raw.new(
-        object_class: object_class, attributes_for_sync: original_attributes, event: event,
+        model_name: model_name, attributes_for_sync: original_attributes, event: event,
       ).construct
     end
 
     def params
       TableSync::Publishing::Params::Raw.new(
-        attributes.slice(:object_class, :headers, :routing_key).compact,
+        attributes.slice(:model_name, :headers, :routing_key).compact,
       ).construct
     end
   end

data/lib/table_sync/publishing/params/raw.rb

@@ -2,6 +2,8 @@
 
 module TableSync::Publishing::Params
   class Raw < Batch
-    # FOR NAMING CONSISTENCY
+    attribute :model_name
+
+    alias_method :object_class, :model_name
   end
 end

data/lib/table_sync/publishing/raw.rb

@@ -3,7 +3,9 @@
 class TableSync::Publishing::Raw
   include Tainbox
 
-  attribute :object_class
+  attribute :model_name
+  attribute :table_name
+  attribute :schema_name
   attribute :original_attributes
 
   attribute :routing_key

data/lib/table_sync/receiving/config.rb

@@ -101,12 +101,12 @@ exactly_hash = proc do |block_for_keys, block_for_values|
       raise TableSync::WrongOptionValue.new(model, option_name, new_value)
     end
 
-    new_value.to_a.map do |key, value|
+    new_value.to_a.to_h do |key, value|
       [
         instance_exec("#{option_name} keys", key, &block_for_keys),
         instance_exec("#{option_name} values", value, &block_for_values),
       ]
-    end.to_h
+    end
   end
 end
 

data/lib/table_sync/receiving/handler.rb

@@ -77,7 +77,7 @@ class TableSync::Receiving::Handler < Rabbit::EventHandler
   end
 
   def processed_data(config)
-    data.map do |row|
+    data.filter_map do |row|
       next if config.skip(row: row)
 
       row = row.dup
@@ -97,7 +97,7 @@ class TableSync::Receiving::Handler < Rabbit::EventHandler
       (row[rest_key] ||= {}).merge!(rest) if rest_key
 
       row
-    end.compact
+    end
   end
 
   def validate_data(data, target_keys:)
@@ -115,7 +115,7 @@ class TableSync::Receiving::Handler < Rabbit::EventHandler
 
     keys_sample = data[0].keys
     keys_diff = data.each_with_object(Set.new) do |row, set|
-      (row.keys - keys_sample | keys_sample - row.keys).each { |x| set.add(x) }
+      ((row.keys - keys_sample) | (keys_sample - row.keys)).each { |x| set.add(x) }
     end
 
     unless keys_diff.empty?

data/lib/table_sync/receiving/model/active_record.rb

@@ -60,7 +60,7 @@ module TableSync::Receiving::Model
     end
 
     def upsert(data:, target_keys:, version_key:, default_values:)
-      data.map do |datum|
+      data.filter_map do |datum|
         conditions = datum.select { |k| target_keys.include?(k) }
 
         row = raw_model.lock("FOR NO KEY UPDATE").where(conditions)
@@ -81,7 +81,7 @@ module TableSync::Receiving::Model
         end
 
         row_to_hash(row)
-      end.compact
+      end
     end
 
     def destroy(data:, target_keys:, version_key:)

data/lib/table_sync/receiving/model/sequel.rb

@@ -77,7 +77,7 @@ module TableSync::Receiving::Model
     end
 
     def update_spec(keys)
-      keys.map { |key| [key, ::Sequel[:excluded][key]] }.to_h
+      keys.to_h { |key| [key, ::Sequel[:excluded][key]] }
     end
   end
 end

data/lib/table_sync/setup/active_record.rb

@@ -1,4 +1,4 @@
-# frozen-string_literal: true
+# frozen_string_literal: true
 
 module TableSync::Setup
   class ActiveRecord < Base

data/lib/table_sync/setup/base.rb

@@ -1,4 +1,4 @@
-# frozen-string_literal: true
+# frozen_string_literal: true
 
 module TableSync::Setup
   class Base

data/lib/table_sync/setup/sequel.rb

@@ -1,4 +1,4 @@
-# frozen-string_literal: true
+# frozen_string_literal: true
 
 module TableSync::Setup
   class Sequel < Base

data/lib/table_sync/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module TableSync
-  VERSION = "6.0.4"
+  VERSION = "6.1.0"
 end

data/lib/table_sync.rb

@@ -37,12 +37,13 @@ module TableSync
     attr_accessor :routing_key_callable
     attr_accessor :exchange_name
     attr_accessor :headers_callable
-    attr_accessor :notifier
+    attr_accessor :notify
 
     attr_reader :orm
     attr_reader :publishing_adapter
     attr_reader :receiving_model
     attr_reader :setup
+    attr_reader :notifier
 
     def sync(object_class, **options)
       setup.new(
@@ -70,5 +71,15 @@ module TableSync
 
       @orm = val
     end
+
+    def notifier=(value)
+      self.notify = true if notify.nil?
+
+      @notifier = value
+    end
+
+    def notify?
+      !!notify
+    end
   end
 end

data/table_sync.gemspec

@@ -5,7 +5,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "table_sync/version"
 
 Gem::Specification.new do |spec|
-  spec.required_ruby_version = ">= 2.5.6"
+  spec.required_ruby_version = ">= 2.7.0"
 
   spec.name        = "table_sync"
   spec.version     = TableSync::VERSION

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: table_sync
 version: !ruby/object:Gem::Version
-  version: 6.0.4
+  version: 6.1.0
 platform: ruby
 authors:
 - Umbrellio
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-02-07 00:00:00.000000000 Z
+date: 2023-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: memery
@@ -268,13 +268,6 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
-- docs/message_protocol.md
-- docs/notifications.md
-- docs/publishing.md
-- docs/publishing/configuration.md
-- docs/publishing/manual.md
-- docs/publishing/publishers.md
-- docs/receiving.md
 - lib/table_sync.rb
 - lib/table_sync/errors.rb
 - lib/table_sync/event.rb
@@ -331,14 +324,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.5.6
+      version: 2.7.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.0.dev
+rubygems_version: 3.4.6
 signing_key:
 specification_version: 4
 summary: DB Table synchronization between microservices based on Model's event system

data/docs/message_protocol.md

@@ -1,24 +0,0 @@
-# Messages protocol
-
-```json
-{
-  "project_id": "pid",
-  "data": {
-    "event": "update",
-    "model": "User",
-    "version": 1.23,
-    "attributes": [
-      {
-        "id": "1",
-        "name": "user1",
-        "email": "user1@example.com"
-      },
-      {
-        "id": "2",
-        "name": "user2",
-        "email": "user2@example.com"
-      }
-    ]
-  }
-}
-```

data/docs/notifications.md

@@ -1,45 +0,0 @@
-### Notifications
-
-#### ActiveSupport adapter
-
-You can use an already existing ActiveSupport adapter:
-```ruby
-  TableSync.notifier = TableSync::InstrumentAdapter::ActiveSupport
-```
-
-This instrumentation API is provided by Active Support. It allows to subscribe to notifications:
-
-```ruby
-ActiveSupport::Notifications.subscribe(/tablesync/) do |name, start, finish, id, payload|
-  # do something
-end
-```
-
-Types of events available:
-`"tablesync.receive.update"`, `"tablesync.receive.destroy"`, `"tablesync.publish.update"`
-and `"tablesync.publish.destroy"`.
-
-You have access to the payload, which contains  `event`, `direction`, `table`, `schema` and `count`.
-
-```
-{
-  :event => :update,       # one of update / destroy
-  :direction => :publish,  # one of publish / receive
-  :table => "users",
-  :schema => "public",
-  :count => 1
-}
-```
-
- See more at https://guides.rubyonrails.org/active_support_instrumentation.html
-
-
-#### Custom adapters
-
-You can also create a custom adapter. It is expected to respond to the following method:
-
-```ruby
-  def notify(table:, event:, direction:, count:)
-    # processes data about table_sync event
-  end
-```

data/docs/publishing/configuration.md

@@ -1,143 +0,0 @@
-# Configuration
-
-Customization, configuration and other options.
-
-## Model Customization
-
-There are methods you can define on a synched model to customize published messages for it.
-
-### `#attributes_for_sync`
-
-Models can implement `#attributes_for_sync` to override which attributes are published for `update` and `create` events. If not present, all attributes are published.
-
-### `#attributes_for_destroy`
-
-Models can implement `#attributes_for_destroy` to override which attributes are published for `destroy` events. If not present, `needle` (primary key) is published.
-
-### `#attributes_for_routing_key`
-
-Models can implement `#attributes_for_routing_key` to override which attributes are given to the `routing_key_callable`. If not present, published attributes are given.
-
-### `#attributes_for_headers`
-
-Models can implement `#attributes_for_headers` to override which attributes are given to the `headers_callable`. If not present, published attributes are given.
-
-### `.table_sync_model_name`
-
-Models can implement `.table_sync_model_name` class method to override the model name used for publishing events. Default is a model class name.
-
-## Callables
-
-Callables are defined once. TableSync will use them to dynamically resolve things like jobs, routing_key and headers.
-
-### Single publishing job (required for automatic and delayed publishing)
-
-- `TableSync.single_publishing_job_class_callable` is a callable which should resolve to a class that calls TableSync back to actually publish changes.
-
-It is expected to have `.perform_at(hash_with_options)` and it will be passed a hash with the following keys:
-
-- `original_attributes` - serialized `original_attributes`
-- `object_class` - model name
-- `debounce_time` - pause between publishing messages
-- `event` - type of event that happened to synched entity
-- `perform_at` - time to perform the job at (depends on debounce)
-
-Example:
-
-```ruby
-TableSync.single_publishing_job_class_callable = -> { TableSync::Job }
-
-class TableSync::Job < ActiveJob::Base
-  def perform(jsoned_attributes)
-    TableSync::Publishing::Single.new(
-      JSON.parse(jsoned_attributes),
-    ).publish_now
-  end
-
-  def self.perform_at(attributes)
-    set(wait_until: attributes.delete(:perform_at))
-      .perform_later(attributes.to_json)
-  end
-end
-
-# will enqueue the job described above
-
-TableSync::Publishing::Single.new(
-  object_class: "User",
-  original_attributes: { id: 1, name: "Mark" }, # will be serialized!
-  debounce_time: 60,
-  event: :update,
-).publish_later
-```
-
-### Batch publishing job (required only for `TableSync::Publishing::Batch#publish_later`)
-
-- `TableSync.batch_publishing_job_class_callable` is a callable which should resolve to a class that calls TableSync back to actually publish changes.
-
-It is expected to have `.perform_later(hash_with_options)` and it will be passed a hash with the following keys:
-
-- `original_attributes` - array of serialized `original_attributes`
-- `object_class` - model name
-- `event` - type of event that happened to synched entity
-- `routing_key` - custom routing_key (optional)
-- `headers` - custom headers (optional)
-
-More often than not this job is not very useful, since it makes more sense to use `#publish_now` from an already existing job that does a lot of things (not just publishing messages).
-
-### Example
-
-```ruby
-TableSync.batch_publishing_job_class_callable = -> { TableSync::BatchJob }
-
-class TableSync::BatchJob < ActiveJob::Base
-  def perform(jsoned_attributes)
-    TableSync::Publishing::Batch.new(
-      JSON.parse(jsoned_attributes),
-    ).publish_now
-  end
-
-  def self.perform_later(attributes)
-    super(attributes.to_json)
-  end
-end
-
-TableSync::Publishing::Batch.new(
-  object_class: "User",
-  original_attributes: [{ id: 1, name: "Mark" }, { id: 2, name: "Bob" }], # will be serialized!
-  event: :create,
-  routing_key: :custom_key,   # optional
-  headers: { type: "admin" }, # optional
-).publish_later
-```
-
-### Routing key callable (required)
-
-- `TableSync.routing_key_callable` is a callable that resolves which routing key to use when publishing changes. It receives object class and published attributes or `#attributes_for_routing_key` (if defined).
-
-Example:
-
-```ruby
-TableSync.routing_key_callable = -> (klass, attributes) { klass.gsub('::', '_').tableize }
-```
-
-### Headers callable (required)
-
-- `TableSync.headers_callable` is a callable that adds RabbitMQ headers which can be used in routing. It receives object class and published attributes or `#attributes_for_headers` (if defined).
-
-One possible way of using it is defining a headers exchange and routing rules based on key-value pairs (which correspond to sent headers).
-
-Example:
-
-```ruby
-TableSync.headers_callable = -> (klass, attributes) { attributes.slice("project_id") }
-```
-
-## Other
-
-- `TableSync.exchange_name` defines the exchange name used for publishing (optional, falls back to default Rabbit gem configuration).
-
-- `TableSync.notifier` is a module that provides publish and recieve notifications.
-
-- `TableSync.raise_on_empty_message` - raises an error on empty message if set to true.
-
-- `TableSync.orm` - set ORM (ActiveRecord or Sequel) used to process given entities. Required!

data/docs/publishing/manual.md

@@ -1,155 +0,0 @@
-# Manual Sync
-
-There are two ways you can manually publish large amounts of data.
-
-### `TableSync::Publishing:Batch`
-
-Easier to use, but does a lot of DB queries. May filter out invalid PK values.
-
-#### Pros:
-
-- requires less work
-- it will automatically use methods for data customization (`#attributes_for_sync`, `#attributes_for_destroy`)
-- you can be sure that data you publish is valid (more or less)
-- serializes values for (`#publish_later`)
-
-#### Cons:
-
-- it queries database for each entity in batch (for `create` and `update`)
-- it may also do a lot of queries if `#attributes_for_sync` contains additional data from other connected entities
-- serializes values for (`#publish_later`); if your PK contains invalid values (ex. Date) they will be filtered out
-
-### `TableSync::Publishing:Raw`
-
-More complex to use, but requires very few DB queries.
-You are responsible for the data you send!
-
-#### Pros:
-
-- very customizable; only requirement - `object_class` must exist
-- you can send whatever data you want
-
-#### Cons:
-
-- you have to manually prepare data for publishing
-- you have to be really sure you are sending valid data
-
-## Tips
-
-- **Don't make data batches too large!**
-
-It may result in failure to process them. Good rule is to send approx. 5000 rows in one batch.
-
-- **Make pauses between publishing data batches!**
-
-Publishing without pause may overwhelm the receiving side. Either their background job processor (ex. Sidekiq) may clog with jobs, or their consumers may not be able to get messages from Rabbit server fast enough.
-
-1 or 2 seconds is a good wait period.
-
-- **Do not use `TableSync::Publishing:Single` to send millions or even thousands of rows of data.**
-
-Or just calling update on rows with automatic sync.
-It WILL overwhelm the receiving side. Especially if they have some additional receiving logic.
-
-- **On the receiving side don't create job with custom logic (if it exists) for every row in a batch.**
-
-Better to process it whole. Otherwise three batches of 5000 will result in 15000 new jobs.
-
-- **Send one test batch before publishing the rest of the data.**
-
-Make sure it was received properly. This way you won't send a lot invalid messages.
-
-- **Check the other arguments.**
-
-    - Ensure the routing_key is correct if you are using a custom one. Remember, that batch publishing ignores `#attributes_for_routing_key` on a model.
-    - Ensure that `object_class` is correct. And it belongs to entities you want to send.
-    - Ensure that you chose the correct event.
-    - If you have some logic depending on headers, ensure they are also correct. Remember, that batch publishing ignores `#attributes_for_headers` on a model.
-
-- **You can check what you send before publishing with:**
-
-```ruby
-TableSync::Publishing:Batch.new(...).message.message_params
-
-TableSync::Publishing:Raw.new(...).message.message_params
-```
-
-## Examples
-
-### `TableSync::Publishing:Raw`
-
-```ruby
-  # For Sequel
-  # gem 'sequel-batches' or equivalent that will allow you to chunk data somehow
-  # or #each_page from Sequel
-
-  # this is a simple query
-  # they can be much more complex, with joins and other things
-  # just make sure that it results in a set of data you expect
-  data = User.in_batches(of: 5000).naked.select(:id, :name, :email)
-
-  data.each_with_index do |batch, i|
-    TableSync::Publishing::Raw.new(
-      object_class: "User",
-      original_attributes: batch,
-      event: :create,
-      routing_key: :custom_key,   # optional
-      headers: { type: "admin" }, # optional
-    ).publish_now
-
-    # make a pause between batches
-    sleep 1
-
-    # for when you are sending from terminal
-    # allows you to keep an eye on progress
-    # you can create more complex output
-    puts "Batch #{i} sent!"
-  end
-
-```
-
-#### Another way to gather data
-
-If you don't want to create a data query (maybe it's too complex) but there is a lot of quereing in `#attributes_for_sync` and you are willing to trade a little bit of perfomance, you can try the following.
-
-```ruby
-class User < Sequel
-  one_to_many :user_info
-
-  # For example our receiving side wants to know the ips user logged in under
-  # But doesn't want to sync the user_info
-  def attributes_for_sync
-    attributes.merge(
-      ips: user_info.ips
-    )
-  end
-end
-
-# to prevent the need to query for every piece of additional data we can user eager load
-# and construct published data by calling #attributes_for_sync
-# don't forget to chunk it into more managable sizes before trying to send
-data = User.eager(:statuses).map { |user| user.attributes_for_sync }
-```
-This way it will not make unnecessary queries.
-
-### `TableSync::Publishing::Batch`
-
-Remember, it will query or initialize each row.
-
-```ruby
-  # You can just send ids.
-  data = User.in_batches(of: 5000).naked.select(:id)
-
-  data.each_with_index do |data, i|
-    TableSync::Publishing::Batch.new(
-      object_class: "User",
-      original_attributes: data,
-      event: :create,
-      routing_key: :custom_key,   # optional
-      headers: { type: "admin" }, # optional
-    ).publish_now
-
-    sleep 1
-    puts "Batch #{i} sent!"
-  end
-```