class URLTrimmer::Worker

Constants

URL_REGEXP

Public Class Methods

uniq_by_domain(urls) click to toggle source
# File lib/url_trimmer.rb, line 8
def self.uniq_by_domain(urls)
  urls.map! do |url|
    begin
      url.downcase
    rescue ArgumentError
      url.encode("UTF-8", invalid: :replace, undef: :replace, replace: "").downcase
    end
  end
  urls.select! { |url| url =~ URL_REGEXP }
  urls.uniq! { |url| DomainName(url[URL_REGEXP, 1]).domain }
  urls.sort!
  urls
end