eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

printdata.py 1.4KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344
  1. #!/usr/bin/python
  2. # Copyright (C) 2012 Reece H. Dunn
  3. #
  4. # This file is part of ucd-tools.
  5. #
  6. # ucd-tools is free software: you can redistribute it and/or modify
  7. # it under the terms of the GNU General Public License as published by
  8. # the Free Software Foundation, either version 3 of the License, or
  9. # (at your option) any later version.
  10. #
  11. # ucd-tools is distributed in the hope that it will be useful,
  12. # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13. # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14. # GNU General Public License for more details.
  15. #
  16. # You should have received a copy of the GNU General Public License
  17. # along with ucd-tools. If not, see <http://www.gnu.org/licenses/>.
  18. import os
  19. import sys
  20. import ucd
  21. ucd_rootdir = sys.argv[1]
  22. unicode_chars = {}
  23. for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
  24. for codepoint in data['CodePoint']:
  25. unicode_chars[codepoint] = data
  26. null = ucd.CodePoint('0000')
  27. if __name__ == '__main__':
  28. for codepoint in ucd.CodeRange('000000..10FFFF'):
  29. try:
  30. data = unicode_chars[codepoint]
  31. title = data['TitleCase']
  32. upper = data['UpperCase']
  33. lower = data['LowerCase']
  34. if title == null: title = codepoint
  35. if upper == null: upper = codepoint
  36. if lower == null: lower = codepoint
  37. print '%s %s %s %s %s' % (codepoint, data['GeneralCategory'], upper, lower, title)
  38. except KeyError:
  39. print '%s Cn %s %s %s' % (codepoint, codepoint, codepoint, codepoint)