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