experimental statistical language classification system

This commit is contained in:
Kyle Drake 2015-12-28 14:32:43 -06:00
parent 9cc85a48bb
commit 242cc6e92d
15 changed files with 178 additions and 37 deletions

View file

@ -1,4 +1,9 @@
require 'sanitize'
require 'linnaeus'
class SiteFile < Sequel::Model
CLASSIFIER_LIMIT = 1_000_000.freeze
CLASSIFIER_WORD_LIMIT = 25.freeze
unrestrict_primary_key
plugin :update_primary_key
many_to_one :site