# Contains all the methods for finding and replacing wiki words
module WikiWords
  # In order of appearance: Latin, greek, cyrillian, armenian
  I18N_HIGHER_CASE_LETTERS =
    "ÀÃ?ÂÃÄÅĀĄĂÆÇĆČĈĊĎÄ?ÈÉÊËĒĘĚĔĖĜĞĠĢĤĦÌÃ?ÃŽÃ?ĪĨĬĮİIJĴĶÅ?ĽĹĻĿÑŃŇŅŊÒÓÔÕÖØŌÅ?ŎŒŔŘŖŚŠŞŜȘŤŢŦȚÙÚÛÜŪŮŰŬŨŲŴÃ?ŶŸŹŽŻ" + 
    "ΑΒΓΔΕΖΗΘΙΚΛΜÎ?ΞΟΠΡΣΤΥΦΧΨΩ" + 
    "ΆΈΉΊΌΎÎ?ѠѢѤѦѨѪѬѮѰѲѴѶѸѺѼѾҀҊҌҎÒ?ҒҔҖҘҚҜҞҠҢҤҦҨҪҬҮҰҲҴҶҸҺҼҾÓ?ÓƒÓ…Ó‡Ó‰Ó‹Ó?Ó?ӒӔӖӘӚӜӞӠӢӤӦӨӪӬӮӰӲӴӸЖ" +
    "Ô±Ô²Ô³Ô´ÔµÔ¶Ô·Ô¸Ô¹ÔºÔ»Ô¼Ô½Ô¾Ô¿Õ€Õ?Õ‚ÕƒÕ„Õ…Õ†Õ‡ÕˆÕ‰ÕŠÕ‹ÕŒÕ?Õ?Õ?Õ‘Õ’Õ“Õ”Õ•Õ–"

  I18N_LOWER_CASE_LETTERS =
    "àáâãäåÄ?ąăæçćÄ?ĉċÄ?đèéêëēęěĕėƒÄ?ğġģĥħìíîïīĩĭįıijĵķĸłľĺļŀñńňņʼnŋòóôõöøÅ?Å‘Å?œŕřŗśšşÅ?șťţŧțùúûüūůűŭũųŵýÿŷžżźÞþßſÃ?ð" +
    "άέήίΰαβγδεζηθικλμνξοπÏ?ςστυφχψωϊϋόÏ?ÏŽÎ?" +
    "абвгдежзийклмнопрÑ?туфхцчшщъыьÑ?ÑŽÑ?Ñ?ёђѓєѕіїјљћќÑ?ўџѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿÒ?Ò‹Ò?Ò?Ò‘Ò“Ò•Ò—Ò™Ò›Ò?ҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӀӂӄӆӈӊӌӎӑӓӕӗәӛÓ?ÓŸÓ¡Ó£Ó¥Ó§Ó©Ó«Ó­Ó¯Ó±Ó³ÓµÓ¹" +
    "Õ¡Õ¢Õ£Õ¤Õ¥Õ¦Õ§Õ¨Õ©ÕªÕ«Õ¬Õ­Õ®Õ¯Õ°Õ±Õ²Õ³Õ´ÕµÕ¶Õ·Õ¸Õ¹ÕºÕ»Õ¼Õ½Õ¾Õ¿Ö€Ö?Ö‚ÖƒÖ„Ö…Ö†Ö‡"

  DIGITS = "0123456789"

  WIKI_WORD_PATTERN = '[A-Z' + I18N_HIGHER_CASE_LETTERS + ']+[a-z' + I18N_LOWER_CASE_LETTERS + ']+[a-z' + I18N_LOWER_CASE_LETTERS + DIGITS + ']*[A-Z' + I18N_HIGHER_CASE_LETTERS + DIGITS + ']\w+'
  CAMEL_CASED_WORD_BORDER = /([a-z#{I18N_LOWER_CASE_LETTERS}#{DIGITS}]|[A-Z#{I18N_HIGHER_CASE_LETTERS}]{2,})(?=[A-Z#{I18N_HIGHER_CASE_LETTERS}]\B)/u

  def self.separate(wiki_word, ignore_separation = false)
    if ignore_separation or wiki_word.match(/^[A-Z#{I18N_HIGHER_CASE_LETTERS}]+$/) or wiki_word.match(/\s/)
      wiki_word
    else
      wiki_word.gsub(CAMEL_CASED_WORD_BORDER, '\1 \2').gsub(/(.)(\d+)/u) { $1 == '_' ? "#$1#$2" : "#$1 #$2" }
    end
  end
end