build/escape_unicode.py

   1 #!/usr/bin/env python
   2 # Copyright (c) 2011 The Chromium Authors. All rights reserved.
   3 # Use of this source code is governed by a BSD-style license that can be
   4 # found in the LICENSE file.
   5
   6 """Convert any unicode characters found in the input file to C literals."""
   7
   8 import codecs
   9 import optparse
  10 import os
  11 import sys
  12
  13
  14 def main(argv):
  15   parser = optparse.OptionParser()
  16   usage = 'Usage: %prog -o <output_dir> <input_file>'
  17   parser.set_usage(usage)
  18   parser.add_option('-o', dest='output_dir')
  19
  20   options, arglist = parser.parse_args(argv)
  21
  22   if not options.output_dir:
  23     print "output_dir required"
  24     return 1
  25
  26   if len(arglist) != 2:
  27     print "input_file required"
  28     return 1
  29
  30   in_filename = arglist[1]
  31
  32   if not in_filename.endswith('.utf8'):
  33     print "input_file should end in .utf8"
  34     return 1
  35
  36   out_filename = os.path.join(options.output_dir, os.path.basename(
  37       os.path.splitext(in_filename)[0]))
  38
  39   WriteEscapedFile(in_filename, out_filename)
  40   return 0
  41
  42
  43 def WriteEscapedFile(in_filename, out_filename):
  44   input_data = codecs.open(in_filename, 'r', 'utf8').read()
  45   with codecs.open(out_filename, 'w', 'ascii') as out_file:
  46     for i, char in enumerate(input_data):
  47       if ord(char) > 127:
  48         out_file.write(repr(char.encode('utf8'))[1:-1])
  49         if input_data[i + 1:i + 2] in '0123456789abcdefABCDEF':
  50           out_file.write('""')
  51       else:
  52         out_file.write(char.encode('ascii'))
  53
  54
  55 if __name__ == '__main__':
  56   sys.exit(main(sys.argv))