#!/usr/bin/env python
# coding: utf-8
import sys
import codecs
cylex = open('cy_lex.txt').read().decode('utf-8')

alpha, beta = sys.argv[1], sys.argv[2]

id = [line for line in cylex.splitlines() if line.startswith(alpha)]
en = [line for line in cylex.splitlines() if line.startswith(beta)]

def lexify(lines):
 lex = {}
 for line in lines:
  bits = line.split('\t')
  if len(bits) == 3:
   lex[bits[1]] = bits[2]
 return lex

enlex = lexify(en)
idlex = lexify(id)

enid = []

for cy in idlex:
 if cy in enlex:
  enid.append((idlex[cy], enlex[cy]))

def dump(lex):
 filename = "%s2%s.txt" % (alpha, beta)
 out = codecs.open(filename,mode='w',encoding="utf-8")
 for i, e in enid: 
  if i != e and ':' not in i and ':' not in e:
   out.write("%s\t%s\n" % (i, e))
 out.close()

dump(enid)