# -*- coding: utf-8 -*-
#!/usr/bin/env python
from glob import glob 
from textual import uread, depunctuate
import sys 
files = sys.argv[1:]

def words(text): 
	text = depunctuate(text) 
	text = text.lower() 
	thewords = text.split() 
        return thewords 

def affixiness(text):
	wordlist = words(text)
	numwords = len(wordlist)
	numforms = len(set(wordlist))
	return float(numforms) / float(numwords)

scores = []

for f in files:
	text = uread(f)
	scores.append((affixiness(text), f))

scores.sort()

from ethnologue import code2lang

for score, fname in scores:
    fname = unicode(fname)
    try:
        language = code2lang[fname.replace('udhr/udhr_','').replace('.txt','')]
    except KeyError:
        language = fname
    print score, '\t', language