# Rspamd statistic setup
# Pre-built files could be loaded from:
# http://rspamd.com/rspamd_statistics/bayes.spam.sqlite
#  - and -
# http://rspamd.com/rspamd_statistics/bayes.ham.sqlite

classifier "bayes" {
  tokenizer {
    name = "osb";
  }
  cache {
    path = "${DBDIR}/learn_cache.sqlite";
  }
  min_tokens = 11;
  backend = "sqlite3";
  languages_enabled = true;
  min_learns = 200;

  statfile {
    symbol = "BAYES_HAM";
    path = "${DBDIR}/bayes.ham.sqlite";
    spam = false;
  }
  statfile {
    symbol = "BAYES_SPAM";
    path = "${DBDIR}/bayes.spam.sqlite";
    spam = true;
  }
  learn_condition =<<EOD
return function(task, is_spam, is_unlearn)
  local learn_type = task:get_request_header('Learn-Type')

  if not (learn_type and tostring(learn_type) == 'bulk') then
    local prob = task:get_mempool():get_variable('bayes_prob', 'double')

    if prob then
      local in_class = false
      local cl
      if is_spam then
        cl = 'spam'
        in_class = prob >= 0.95
      else
        cl = 'ham'
        in_class = prob <= 0.05
      end

      if in_class then
        return false,string.format('already in class %s; probability %.2f%%',
          cl, math.abs((prob - 0.5) * 200.0))
      end
    end
  end

  return true
end
EOD

}