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 2.2KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263
  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. csur_rootdir = 'data/csur'
  23. unicode_chars = {}
  24. for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
  25. for codepoint in data['CodePoint']:
  26. unicode_chars[codepoint] = data
  27. unicode_chars[codepoint]['Properties'] = []
  28. for data in ucd.parse_ucd_data(ucd_rootdir, 'PropList'):
  29. if data['Property'] in ['White_Space']:
  30. for codepoint in data['Range']:
  31. unicode_chars[codepoint]['Properties'].append(data['Property'])
  32. for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
  33. for codepoint in data['Range']:
  34. unicode_chars[codepoint]['Script'] = data['Script']
  35. if '--with-csur' in sys.argv:
  36. for csur in ['Klingon']:
  37. for data in ucd.parse_ucd_data('data/csur', csur):
  38. for codepoint in data['CodePoint']:
  39. unicode_chars[codepoint] = data
  40. null = ucd.CodePoint('0000')
  41. if __name__ == '__main__':
  42. for codepoint in ucd.CodeRange('000000..10FFFF'):
  43. try:
  44. data = unicode_chars[codepoint]
  45. except KeyError:
  46. data = {}
  47. script = data.get('Script', 'Zzzz')
  48. title = data.get('TitleCase', codepoint)
  49. upper = data.get('UpperCase', codepoint)
  50. lower = data.get('LowerCase', codepoint)
  51. if title == null: title = codepoint
  52. if upper == null: upper = codepoint
  53. if lower == null: lower = codepoint
  54. print('%s %s %s %s %s %s %s %s' % (
  55. codepoint, script,
  56. data.get('GeneralCategory', 'Cn')[0], data.get('GeneralCategory', 'Cn'),
  57. upper, lower, title,
  58. ' '.join(data.get('Properties', []))))