#!/usr/bin/env python
# -*- coding: utf-8 -*-
import align

entext = '/home/pat/l/udhr/data/udhr_eng.txt'
pttext = '/home/pat/l/udhr/data/udhr_por.txt'


entext = 'data/faq-fr.txt'
pttext = 'data/faq-en.txt'

entext = 'data/gainsbourg-en.txt'
pttext = 'data/gainsbourg-fr.txt'


entext = 'data/mis/en.txt'
pttext = 'data/mis/fr.txt'

entext = 'data/notredame/en.txt'
pttext = 'data/notredame/fr.txt'


entext = "/home/pat/l/pt/doingbusinessinbrazil/brazilbiz-en.txt"
pttext = "/home/pat/l/pt/doingbusinessinbrazil/brazilbiz-pt.txt"

entext = 'data/a.txt'
pttext = 'data/b.txt'

endex = align.Collection()
ptdex = align.Collection()

en = align.UnicodeDammit(open(entext, 'U').read()).unicode
pt = align.UnicodeDammit(open(pttext, 'U').read()).unicode

entokens = en.split()
pttokens = pt.split()
enwords = set(entokens)
ptwords = set(pttokens)

for i,w in enumerate(entokens):
 endex[w] = i

for i,w in enumerate(pttokens):
 ptdex[w] = i

def normalize(seq): 
 maximum = max(seq)
 return [ int(float(n)/maximum * 100) for n in seq]

def hitfreq(word, langdex): 
 return align.freq(normalize(langdex[word]))

def compare(ptwd, enwd):
 ptvec = hitfreq(ptwd, ptdex)
 envec = hitfreq(enwd, endex)
 answer = align.sim(ptvec, envec)
 if answer > 0: return answer

def findsims(enword):
 sims = []
 for ptword in list(ptwords)[:8000]:
  res = (compare(ptword, enword), enword, ptword)
  sims.append(res)
 return sorted(sims)

def top(n, dictionary):
 vals = set(dictionary.values())
 tops = sorted(list(vals))[-n:]
 return [k for k in dictionary if dictionary[k] in tops]
 

if __name__ == "__main__":
 import sys
 query = unicode(sys.argv[1])
 biz = findsims(query)
 for x, e, p  in biz[-10:]: 
  print "» %f\t%s\t%s" % (x, e, p)
 print u"out of " + unicode(len(endex[query]))