#!/usr/bin/env python
# -*- coding: utf-8 -*-
from unicodedata import name,category
import hrm 

"""
we want to see what the ratios of the frequencies
of the the first to second most frequent words is
for all languages in the udhr
"""

huu = hrm.udhr['huu']
hits = [(float(lang.wordfreq[lang.topword])/lang.wordfreq[lang.secondword]) for k,lang in hrm.udhr.items()]

for x in sorted(hits): print x

[(lang.code, lang.language) for x,lang in hrm.udhr.items() if (float(lang.wordfreq[lang.topword]) == lang.wordfreq[lang.secondword])]
[(len(lang.text), lang.language) for x,lang in hrm.udhr.items() if (float(lang.wordfreq[lang.topword]) == lang.wordfreq[lang.secondword])]

for lg,first,second,  [(len(lang.text), lang.language) for x,lang in hrm.udhr.items() if (float(lang.wordfreq[lang.topword]) == lang.wordfreq[lang.secondword])]
for c in u"        እያንዳንዱ፡ሰው፡የራሱ፡ነጻነትና፡ሙሉ፡መሻሻል፡በሚያገኝበት፡ኀብረሰብ፡ውስጥ፡የሚፈጽማቸው፡ግዴታዎች፡ይኖሩበታል።": print c, name(c), category(c)