#
# convert1.py -- Simple program to convert a simple text file.
# Written Dec 18 2006 and placed in Public Domain.
#
# Usage:
# from convert1 import *

# convfile('gencode2.txt') # (for example...)


import os
import re
from math import *


def floor_log2(n):
  '''See http://www.research.att.com/~njas/sequences/A000523'''
  if n < 1: return(0)
  else: return(int(log(n)/log(2)))


# The output is written to similarly named file,
# with the extension replaced by a new extension ".sol"

# Read stuff like this:
# UGG W Trp
# CAU,CAC H His
# UAU,UAC Y Tyr
# AUU,AUC,AUA I Ile
# GUU,GUC,GUA,GUG V Val
# UAG,UGA,UAA - Stop

def convfile(filename):
  '''Opens file "filename" for reading and similar file with extension ".out" for writing.'''
  infp = open(filename,'r')
  try:
    lastdot = filename.rindex('.')
    outfilename = filename[:lastdot] + ".out"
  except ValueError: # There were no dot in the filename
    outfilename = filename + ".out"

  outfp = open(outfilename,'w')
  permlinepat = re.compile(r'^([UCAG,]*)\s+(.*)')
  sols = 0
  firstmax = 0
  for line in infp.xreadlines(): 
    m = permlinepat.match(line)
    if(m):
      codestr = m.group(1) #
      names = m.group(2) #
      codes = codestr.split(',')

      print "codestr=",codestr,"\n"
      for code in codes:
        numcode = code
        numcode = numcode.replace('U','0')
        numcode = numcode.replace('C','1')
        numcode = numcode.replace('A','2')
        numcode = numcode.replace('G','3')
        print numcode,names
        outfp.write(numcode + " " + names + "\n")

  outfp.close()




# This module ends here.