import std/text/unicode

// Join combining characters with their base into a grapheme.
fun join-combining( cs : list<char>, comb : list<char> = [], acc : list<grapheme> = []) : list<grapheme> {
  match(cs) {
    Cons(zwj, cc) | zwj.int == 0x200D -> // Add zero width joiner
      match cc
        Cons(c, cc') -> cc'.join-combining(Cons(c, Cons(zwj,comb)), acc)
        Nil -> cc.join-combining(Cons(zwj, comb), acc)
    Cons(c,cc) -> if (c.is-combining2)
                   then cc.join-combining( Cons(c,comb), acc )
                   else cc.join-combining( [c], consrev(comb,acc) )
    Nil        -> consrev(comb,acc).reverse
  }
}
fun consrev(xs,xss) {
  if (xs.is-nil) then xss else Cons(xs.reverse.string,xss)
}

pub fun is-combining2( c : char ) : bool {
  val i = c.int
  ((i >= 0x0300 && i <= 0x036F) ||
   (i >= 0x1AB0 && i <= 0x1AFF) ||
   (i >= 0x1DC0 && i <= 0x1DFF) ||
   (i >= 0x20D0 && i <= 0x20FF) ||
   (i >= 0xFE20 && i <= 0xFE2F) ||
   (i >= 0xFE00 && i <= 0xFE0F)) // Added variation selectors
}

fun main()
  "Utf16 code points".println
  "hi❤️‍🔥".list.map(show).join(",").println
  "NFC".println // This is the normalization that graphemes gives you
  "hi❤️‍🔥".normalize(NFC).list.join-combining.join(",").println
  "NFD".println
  "hi❤️‍🔥".normalize(NFD).list.join-combining.join(",").println
  "NFKC".println
  "hi❤️‍🔥".normalize(NFKC).list.join-combining.join(",").println
  "NFKD".println
  "hi❤️‍🔥".normalize(NFKD).list.join-combining.join(",").println

// Grapheme's are an alias for `:string`.
// Each grapheme is a self-contained symbol consisting of
// a unicode character followed by combining characters and/or
// combining marks.
pub alias grapheme = string