radio/util/translate.py

   1 #!/usr/bin/env python
   2 # -*- coding: utf-8 -*-
   3
   4 # Imports
   5 import argparse
   6 import codecs
   7 import sys
   8
   9 translations = {'cz_reduced': [('\\200', u'á'),
  10                        ('\\201', u'č'),
  11                        ('\\201', u'Č'),
  12                        ('\\202', u'é'),
  13                        ('\\203', u'ě'),
  14                        ('\\203', u'Ě'),
  15                        ('\\204', u'í'),
  16                        ('\\205', u'ó'),
  17                        ('\\206', u'ř'),
  18                        ('\\207', u'š'),
  19                        ('\\207', u'Š'),
  20                        ('\\210', u'ú'),
  21                        ('\\211', u'ů'),
  22                        ('\\212', u'ý'),
  23                        ('\\213', u'Á'),
  24                        ('\\214', u'Í'),
  25                        ('\\215', u'Ř'),
  26                        ('\\216', u'Ý'),
  27                        ('\\217', u'ž'),
  28                        ('\\217', u'Ž'),
  29                        ('\\220', u'É')],
  30
  31                 'cz': [('\\200', u'ě'),
  32                        ('\\201', u'š'),
  33                        ('\\202', u'č'),
  34                        ('\\203', u'ř'),
  35                        ('\\204', u'ž'),
  36                        ('\\205', u'ý'),
  37                        ('\\206', u'á'),
  38                        ('\\207', u'í'),
  39                        ('\\210', u'é'),
  40                        ('\\211', u'ň'),
  41                        ('\\212', u'ó'),
  42                        ('\\213', u'ů'),
  43                        ('\\214', u'ú'),
  44                        ('\\215', u'ď'),
  45                        ('\\216', u'ť'),
  46                        ('\\217', u'Ě'),
  47                        ('\\220', u'Š'),
  48                        ('\\221', u'Č'),
  49                        ('\\222', u'Ř'),
  50                        ('\\223', u'Ž'),
  51                        ('\\224', u'Ý'),
  52                        ('\\225', u'Á'),
  53                        ('\\226', u'Í'),
  54                        ('\\227', u'É'),
  55                        ('\\230', u'Ň'),
  56                        ('\\231', u'Ó'),
  57                        ('\\232', u'Ú'),
  58                        ('\\233', u'Ů'),
  59                        ('\\234', u'Ď'),
  60                        ('\\235', u'Ť')],
  61
  62                 'de': [('\\200', u'Ä'),
  63                        ('\\201', u'ä'),
  64                        ('\\202', u'Ö'),
  65                        ('\\203', u'ö'),
  66                        ('\\204', u'Ü'),
  67                        ('\\205', u'ü'),
  68                        ('\\206', u'ß')],
  69
  70                 'es': [('\\200', u'Ñ'),
  71                        ('\\201', u'ñ')],
  72
  73                 'fi': [('\\200', u'å'),
  74                        ('\\201', u'ä'),
  75                        ('\\202', u'ö'),
  76                        ('\\203', u'Å'),
  77                        ('\\204', u'Ä'),
  78                        ('\\205', u'Ö')],
  79
  80                 'fr': [('\\200', u'é'),
  81                        ('\\201', u'è'),
  82                        ('\\202', u'à'),
  83                        ('\\203', u'î'),
  84                        ('\\204', u'ç')],
  85
  86                 'it': [('\\200', u'à'),
  87                        ('\\201', u'ù')],
  88
  89                 'pl': [('\\200', u'ą'),
  90                        ('\\201', u'ć'),
  91                        ('\\202', u'ę'),
  92                        ('\\203', u'ł'),
  93                        ('\\204', u'ń'),
  94                        ('\\205', u'ó'),
  95                        ('\\206', u'ś'),
  96                        ('\\207', u'ż'),
  97                        ('\\210', u'ź'),
  98                        ('\\211', u'Ą'),
  99                        ('\\212', u'Ć'),
 100                        ('\\213', u'Ę'),
 101                        ('\\214', u'Ł'),
 102                        ('\\215', u'Ń'),
 103                        ('\\216', u'Ó'),
 104                        ('\\217', u'Ś'),
 105                        ('\\220', u'Ż'),
 106                        ('\\221', u'Ź')],
 107
 108                 'pt': [('\\200', u'Á'),
 109                        ('\\201', u'á'),
 110                        ('\\202', u'Â'),
 111                        ('\\203', u'â'),
 112                        ('\\204', u'Ã'),
 113                        ('\\205', u'ã'),
 114                        ('\\206', u'À'),
 115                        ('\\207', u'à'),
 116                        ('\\210', u'Ç'),
 117                        ('\\211', u'ç'),
 118                        ('\\212', u'É'),
 119                        ('\\213', u'é'),
 120                        ('\\214', u'Ê'),
 121                        ('\\215', u'ê'),
 122                        ('\\216', u'Í'),
 123                        ('\\217', u'í'),
 124                        ('\\218', u'Ó'),
 125                        ('\\219', u'ó'),
 126                        ('\\220', u'Ô'),
 127                        ('\\221', u'ô'),
 128                        ('\\222', u'Õ'),
 129                        ('\\223', u'õ'),
 130                        ('\\224', u'Ú'),
 131                        ('\\225', u'ú'), ],
 132
 133                 'se': [('\\200', u'å'),
 134                        ('\\201', u'ä'),
 135                        ('\\202', u'ö'),
 136                        ('\\203', u'Å'),
 137                        ('\\204', u'Ä'),
 138                        ('\\205', u'Ö')],
 139
 140                 'en': [],
 141
 142                 'nl': [],
 143
 144                 'all': [('\\306', u'Δ'),
 145                         ('\\173', u'~'),
 146                         ('\\036', u'\\n'),
 147                         ('\\035', u'\\t')],
 148                 }
 149
 150 # Take care of command line options
 151 parser = argparse.ArgumentParser(description='Encoder for open9x translations')
 152 parser.add_argument('input', action="store", help="Input file name")
 153 parser.add_argument('output', action="store", help="Output file name")
 154 parser.add_argument('language', action="store", help="Two letter language identifier")
 155 parser.add_argument("--reverse", help="Reversed char conversion (from number to char)", action="store_true")
 156 args = parser.parse_args()
 157
 158 if args.language not in translations:
 159     parser.error(args.language + ' is not a supported language. Try one of the supported ones: ' + str(list(translations.keys())))
 160     sys.exit()
 161
 162 if args.reverse:
 163     for translation in translations:
 164         translations[translation] = [(after, before) for (before, after) in translations[translation]]
 165
 166 # Read the input file into a buffer
 167 in_file = codecs.open(args.input, "r", "utf-8")
 168
 169 # Write the result to a temporary file
 170 out_file = codecs.open(args.output, 'w', 'utf-8')
 171
 172 for line in in_file.readlines():
 173     # Do the special chars replacements
 174     for after, before in translations[args.language] + translations["all"]:
 175         line = line.replace(before, after)
 176     if line.startswith("#define ZSTR_"):
 177         before = line[32:-2]
 178         after = ""
 179         for c in before:
 180             if ord(c) >= ord('A') and ord(c) <= ord('Z'):
 181                 c = "\\%03o" % (ord(c) - ord('A') + 1)
 182             elif ord(c) >= ord('a') and ord(c) <= ord('z'):
 183                 c = "\\%03o" % (-ord(c) + ord('a') + 255)
 184             elif ord(c) >= ord('0') and ord(c) <= ord('9'):
 185                 c = "\\%03o" % (ord(c) - ord('0') + 27)
 186             after = after + c
 187         line = line[:32] + after + line[-2:]
 188     out_file.write(line)
 189
 190 out_file.close()
 191 in_file.close()