#!/usr/bin/python
# coding=utf8

# Copyright (C) 2007  Mashrab Kuvatov <kmashrab@uni-bremen.de>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.

import sys

def needsPrefix(inStr, curIndx):
  'Returns true if h should be prefixed after s'
  if curIndx > 0:
    return inStr[curIndx - 1] in [u'с', u'С']
  else:
    return False

def isPrevVocal(inStr, curIndx):
  'Returns true if the previous char is vocal'
  vocalChars = [u'а', u'и', u'е', u'о', u'ў', u'у', \
                u'А', u'И', u'Е', u'О', u'Ў', u'У']
  if curIndx > 0:
    return inStr[curIndx - 1] in vocalChars
  else:
    return False

def needsUpperCasing(inStr, curIndx):
  'Returns true if uppercasing is needed'
  prevCharUpper = nextCharUpper = False
  if curIndx > 0:
    prevCharUpper = inStr[curIndx - 1].isupper()
  if prevCharUpper:
    return True
  if curIndx < len(inStr) - 1:
    nextCharUpper = inStr[curIndx + 1].isupper()
  return nextCharUpper

def convertLine(cyr_str):
  'Convert given cyrillic string into latin one'
  lookUpTbl = [u'a', u'b', u'v', u'g', u'd', u'e', u'j', u'z',
               u'i', u'y', u'k', u'l', u'm', u'n', u'o', u'p',
               u'r', u's', u't', u'u', u'f', u'x', u'ts', u'ch',
               u'sh', u'sh', u'ʼ', u'i', u'', u'e', u'yu', u'ya']
  lat_str = u''
  cyr_str_len = len(cyr_str)
  if cyr_str_len == 0:
    return cyr_str
  isWordBegin = True
  # loop over the chars in the string
  for curCyrIndx in range(cyr_str_len):
    curCyrChar = cyr_str[curCyrIndx]
    if (curCyrChar >= u'а' and curCyrChar <= u'я') or  \
       curCyrChar in [u'ў', u'ҳ', u'қ', u'ғ', u'ё'] or \
       (curCyrChar >= u'А' and curCyrChar <= u'Я') or  \
       curCyrChar in [u'Ў', u'Ҳ', u'Қ', u'Ғ', u'Ё']:
      wasCurCharUpper = curCyrChar.isupper()
      curCyrChar = curCyrChar.lower()
      if curCyrChar == u'ў':
        curLatChar = u'oʻ'
      elif curCyrChar == u'ҳ':
        if needsPrefix(cyr_str, curCyrIndx):
          curLatChar = u'ʼh'
        else:
          curLatChar = u'h'
      elif curCyrChar == u'қ':
        curLatChar = u'q'
      elif curCyrChar == u'ғ':
        curLatChar = u'gʻ'
      # TODO: Convert 'ё' properly
      elif curCyrChar == u'ё':
        curLatChar = u'yo'
      elif curCyrChar == u'е' and isWordBegin:
        curLatChar = u'ye'
      elif curCyrChar == u'ц':
        if isWordBegin or not isPrevVocal(cyr_str, curCyrIndx):
          curLatChar = u's'
        else:
          curLatChar = u'ts'
      # TODO: Take care of 'ю' 'я'
      else:
        curLatChar = lookUpTbl[ord(curCyrChar) - ord(u'а')]
      if wasCurCharUpper:
        if curLatChar in [u'ch', u'sh', u'yo', u'yu', u'ya', u'ye', u'ts'] and \
           needsUpperCasing(cyr_str, curCyrIndx):
          curLatChar = curLatChar.upper()
        elif curLatChar == u'ʼh':
          curLatChar = u'ʼH'
        else:
          curLatChar = curLatChar.capitalize()
    else:
      curLatChar = curCyrChar
    lat_str = lat_str + curLatChar
    isWordBegin = not curCyrChar.isalnum()
  return lat_str

# begining of the program

if len(sys.argv) != 3:
  print 'Converts UTF-8 encoded Cyrillic Uzbek text file into',
  print 'Latin Uzbek text file.'
  print 'Usage: %s cyr.txt lat.txt' % sys.argv[0]
  sys.exit(1)
else:
  cyr_filename = sys.argv[1]
  lat_filename = sys.argv[2]
# read
cyr_file = open(cyr_filename, 'r')
latLines = ''
# convert
for eachCyrLine in cyr_file:
  latLines = latLines + convertLine(eachCyrLine.decode('utf-8'))
cyr_file.close()
# save
latLines = latLines.encode('utf-8')
lat_file = open(lat_filename, 'w')
lat_file.write(latLines)
lat_file.close()