add rake task for dumping fa user info

Gemfile

@@ -111,6 +111,7 @@ gem "good_job"
 gem "neighbor"
 gem "disco"
 gem "faiss"
+gem "progressbar"
 
 group :production, :staging do
   gem "rails_semantic_logger"

Gemfile.lock

@@ -201,6 +201,7 @@ GEM
     pluck_each (0.2.0)
       activerecord (> 3.2.0)
       activesupport (> 3.0.0)
+    progressbar (1.13.0)
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
@@ -371,6 +372,7 @@ DEPENDENCIES
   nokogiri
   pg
   pluck_each
+  progressbar
   pry
   pry-stack_explorer
   puma (~> 5.0)

rake/fa.rake

@@ -1,4 +1,36 @@
 namespace :fa do
+  desc "dump FurAffinity users into json file, sorted by name"
+  task :dump_users => [:set_logger_stdout, :environment] do
+    out_file = ENV["out"] || raise("`out` file not specified (json)")
+    print "counting users... "
+    total = Domain::Fa::User.count
+    puts "#{total}"
+    progress = ProgressBar.create(total: total, throttle_rate: 0.2)
+    columns = {
+      name: "name of the FurAffinity user",
+      url_name: "identifier used in URLs to refer to the user, e.g. https://www.furaffinity.net/user/test",
+      num_submissions: "number of submissions the user has made, as per the user page",
+      num_comments_recieved: "number of comments the user's posts have received, as per the user page",
+      num_comments_given: "number of comments the user has made on other posts, as per the user page",
+      num_journals: "number of journals the user has made, as per the user page",
+      num_favorites: "number of posts the user has favorited, as per the user page",
+      num_pageviews: "number of pageviews of the user's page, as per the user page",
+      registered_at: "when the account was registered, as per the user page",
+    }
+    model_ids = Domain::Fa::User.order(url_name: :asc).pluck(:id)
+    File.open(out_file, "wt") do |file|
+      file.write(JSON.dump(columns))
+      model_ids.in_groups_of(100, false).each do |ids_batch|
+        rows = Domain::Fa::User.where(id: ids_batch).order(:url_name).pluck(*columns.keys)
+        rows.each do |row|
+          file << JSON.dump(columns.keys.zip(row).to_h)
+          file << "\n"
+        end
+        progress.progress += ids_batch.size
+      end
+    end
+  end
+
   desc "enqueue waiting posts"
   task :enqueue_waiting_posts => [:set_logger_stdout, :environment] do |t, args|
     start_at = (ENV["start_at"] || 0).to_i