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.

49 lines
1.8 KiB

4 years ago
  1. ######################## BEGIN LICENSE BLOCK ########################
  2. # The Original Code is mozilla.org code.
  3. #
  4. # The Initial Developer of the Original Code is
  5. # Netscape Communications Corporation.
  6. # Portions created by the Initial Developer are Copyright (C) 1998
  7. # the Initial Developer. All Rights Reserved.
  8. #
  9. # Contributor(s):
  10. # Mark Pilgrim - port to Python
  11. #
  12. # This library is free software; you can redistribute it and/or
  13. # modify it under the terms of the GNU Lesser General Public
  14. # License as published by the Free Software Foundation; either
  15. # version 2.1 of the License, or (at your option) any later version.
  16. #
  17. # This library is distributed in the hope that it will be useful,
  18. # but WITHOUT ANY WARRANTY; without even the implied warranty of
  19. # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  20. # Lesser General Public License for more details.
  21. #
  22. # You should have received a copy of the GNU Lesser General Public
  23. # License along with this library; if not, write to the Free Software
  24. # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
  25. # 02110-1301 USA
  26. ######################### END LICENSE BLOCK #########################
  27. from .chardistribution import EUCKRDistributionAnalysis
  28. from .codingstatemachine import CodingStateMachine
  29. from .mbcharsetprober import MultiByteCharSetProber
  30. from .mbcssm import CP949_SM_MODEL
  31. class CP949Prober(MultiByteCharSetProber):
  32. def __init__(self):
  33. super(CP949Prober, self).__init__()
  34. self.coding_sm = CodingStateMachine(CP949_SM_MODEL)
  35. # NOTE: CP949 is a superset of EUC-KR, so the distribution should be
  36. # not different.
  37. self.distribution_analyzer = EUCKRDistributionAnalysis()
  38. self.reset()
  39. @property
  40. def charset_name(self):
  41. return "CP949"
  42. @property
  43. def language(self):
  44. return "Korean"