Stage one... get RAX file URLs

rax_user_file_set.rb

require "fog"
require "pry"

class RaxUserFileSet

  def initialize(limit = nil)
    conn = Fog::Storage.new({
        :provider => "Rackspace",
        :rackspace_username => RAX_UN,
        :rackspace_api_key => RAX_API_KEY,
        :rackspace_region => :dfw
      })

    @dir = conn.directories.get "teamsnap_production"
    @rax_array = []
    @limit = limit || 10_000
  end

  def retrieve(last_file = nil)
    loop do
      urls = get_user_file_urls(@limit, last_file)
      @rax_array << urls
      @rax_array.flatten!
      last_file = @rax_array.last.split(/rackcdn.com\//).last
      break if urls.count < @limit
    end
    @rax_array.to_set
  end

  private

  def get_user_file_urls(limit, last_file = nil)
    @dir.files.all(
      :limit => limit,
      :marker => last_file || nil,
      :prefix => "user_files/")
      .map(&:public_url)
  end
end

Returns a Set or URLs for later comparison against UserFiles table URL Set.

Example:

#<Set: {"http://49f9ffaf92d711fb5ea1-1b8897185d70b198c119e1d2b7efd8a2.r30.cf1.rackcdn.com/user_files/1/mid
size/ward_icon.jpg", "http://49f9ffaf92d711fb5ea1-1b8897185d70b198c119e1d2b7efd8a2.r30.cf1.rackcdn.com/user_f
iles/1/original/ward_icon.jpg", "http://49f9ffaf92d711fb5ea1-1b8897185d70b198c119e1d2b7efd8a2.r30.cf1.rackcdn
.com/user_files/1/thumb/ward_icon.jpg", "http://49f9ffaf92d711fb5ea1-1b8897185d70b198c119e1d2b7efd8a2.r30.cf1
.rackcdn.com/user_files/10/midsize/DSC_0102.jpg", "http://49f9ffaf92d711fb5ea1-1b8897185d70b198c119e1d2b7efd8
a2.r30.cf1.rackcdn.com/user_files/10/original/DSC_0102.jpg", "http://49f9ffaf92d711fb5ea1-1b8897185d70b198c11
9e1d2b7efd8a2.r30.cf1.rackcdn.com/user_files/10/thumb/DSC_0102.jpg"}>