/** This file demonstrates sorting strings lexicographically according to the
    rules defined by different natural languages. 
*/

/* Spanish.  Huh.  I was wondering why none of this was sorting according
   to the rules I learned in school and after much beating my head on it, I
   learned:

   "Spanish treated (until 1994) "CH" and "LL" as single letters,
   giving an ordering of cinco, credo, chispa and lomo, luz, llama.  This is
   not true anymore since in 1994 the RAE adopted the more conventional usage,
   and now LL is collated between LK and LM, and CH between CG and CI. The six
   characters with diacritics Á, É, Í, Ó, Ú, Ü are treated as the original
   letters A, E, I, O, U, for example: radio, ráfaga, rana, rápido, rastrillo.
   The only Spanish-specific collating question is Ñ (eñe) as a different
   letter collated after N."

   https://en.wikipedia.org/wiki/Alphabetical_order
*/ 

//a = ["jueves", "verde", "amarillo", "blanco", "lima", "llave", "llover", "loma", "cinco", "domingo", "rojo", "crudo", "chile", "casa", "chalina", "curioso", "llama", "luz", "alos", "alla", "ala", "eñe", "ene", "enne"]

a = ["ökonomisch", "offenbar", "olfaktorisch", "Arg", "Ärgerlich", "Arm", "Assistent", "Aßlar", "Assoziation", "eñe", "ene", "enne"]

println["Dumb sort: " + sort[a]]
println["Default:   " + lexicalSort[a]]
println["English:   " + lexicalSort[a, "en"]]
println["Spanish:   " + lexicalSort[a, "es"]]  // As of 1994, only new rule is ñ sorted after n
println["German:    " + lexicalSort[a, "de"]]  // "offenbar", "ökonomisch", "olfaktorisch"
println["Turkish:   " + lexicalSort[a, "tr"]]  // ö is sorted after o