Rails model relations depending on count of nested relations - ruby-on-rails

Question

I am putting together a messaging system for a rails app I am working on.
I am building it in a similar fashion to facebook's system, so messages are grouped into threads, etc.
My related models are:
MsgThread - main container of a thread
Message - each message/reply in thread
Recipience - ties to user to define which users should subscribe to this thread
Read - determines whether or not a user has read a specific message
My relationships look like
class User < ActiveRecord::Base
#stuff...
has_many :msg_threads, :foreign_key => 'originator_id' #threads the user has started
has_many :recipiences
has_many :subscribed_threads, :through => :recipiences, :source => :msg_thread #threads the user is subscribed to
end
class MsgThread < ActiveRecord::Base
has_many :messages
has_many :recipiences
belongs_to :originator, :class_name => "User", :foreign_key => "originator_id"
end
class Recipience < ActiveRecord::Base
belongs_to :user
belongs_to :msg_thread
end
class Message < ActiveRecord::Base
belongs_to :msg_thread
belongs_to :author, :class_name => "User", :foreign_key => "author_id"
end
class Read < ActiveRecord::Base
belongs_to :user
belongs_to :message
end
I'd like to create a new selector in the user sort of like:
has_many :updated_threads, :through => :recipiencies, :source => :msg_thread, :conditions => {THREAD CONTAINS MESSAGES WHICH ARE UNREAD (have no 'read' models tying a user to a message)}
I was thinking of either writing a long condition with multiple joins, or possibly writing giving the model an updated_threads method to return this, but I'd like to see if there is an easier way first. Am I able to pass some kind of nested hash into the conditions instead of a string?
Any ideas? Also, if there is something fundamentally wrong with my structure for this functionality let me know! Thanks!!
UPDATE:
While I would still appreciate input on better possibilities if they exist, this is what I have gotten working now:
class User < ActiveRecord::Base
# stuff...
def updated_threads
MsgThread.find_by_sql("
SELECT msg_threads.* FROM msg_threads
INNER JOIN messages ON messages.msg_thread_id = msg_threads.id
INNER JOIN recipiences ON recipiences.msg_thread_id = msg_threads.id
WHERE (SELECT COUNT(*) FROM `reads` WHERE reads.message_id = messages.id AND reads.user_id = #{self.id}) = 0
AND (SELECT COUNT(*) FROM recipiences WHERE recipiences.user_id = #{self.id} AND recipiences.msg_thread_id = msg_threads.id) > 0
")
end
end
Seems to be working fine!
Also to check if a specific thread (and message) are read:
class Message < ActiveRecord::Base
# stuff...
def read?(user_id)
Read.exists?(:user_id => user_id, :message_id => self.id)
end
end
class MsgThread < ActiveRecord::Base
# stuff...
def updated?(user_id)
updated = false
self.messages.each { |m| updated = true if !m.read?(user_id) }
updated
end
end
Any suggestions to improve this?

Answer 1

Add a named_scope to the MsgThread model:
class MsgThread < ActiveRecord::Base
named_scope :unread_threads, lambda { |user|
{
:include => [{:messages=>[:reads]}, recipiencies],
:conditions => ["recipiences.user_id = ? AND reads.message_id IS NULL",
user.id],
:group => "msg_threads.id"
}}
end
Note: Rails uses LEFT OUTER JOIN for :include. Hence the IS NULL check works.
Now you can do the following:
MsgThread.unread_threads(current_user)
Second part can be written as:
class Message
has_many :reads
def read?(usr)
reads.exists?(:user_id => usr.id)
end
end
class MsgThread < ActiveRecord::Base
def updated?(usr)
messages.first(:joins => :reads,
:conditions => ["reads.user_id = ? ", usr.id]
) != nil
end
end

Answer 2

You might want to take a look at Arel, which can help with complex SQL queries. I believe (don't quote me) this is already baked into Rails3.