A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
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.
 
 
 
 

82 lines
3.3 KiB

  1. # -*- coding: utf-8 -*-
  2. #
  3. # Copyright (C) 2012 Ben Kurtovic <ben.kurtovic@verizon.net>
  4. #
  5. # Permission is hereby granted, free of charge, to any person obtaining a copy
  6. # of this software and associated documentation files (the "Software"), to deal
  7. # in the Software without restriction, including without limitation the rights
  8. # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  9. # copies of the Software, and to permit persons to whom the Software is
  10. # furnished to do so, subject to the following conditions:
  11. #
  12. # The above copyright notice and this permission notice shall be included in
  13. # all copies or substantial portions of the Software.
  14. #
  15. # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  16. # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  17. # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  18. # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  19. # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  20. # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  21. # SOFTWARE.
  22. __all__ = ["Token"]
  23. class Token(object):
  24. def __init__(self, **kwargs):
  25. super(Token, self).__setattr__("_kwargs", kwargs)
  26. def __repr__(self):
  27. args = []
  28. for key, value in self._kwargs.iteritems():
  29. if isinstance(value, basestring) and len(value) > 100:
  30. args.append(key + "=" + repr(value[:97] + "..."))
  31. else:
  32. args.append(key + "=" + repr(value))
  33. return u"{0}({1})".format(type(self).__name__, u", ".join(args))
  34. def __eq__(self, other):
  35. if isinstance(other, type(self)):
  36. return self._kwargs == other._kwargs
  37. return False
  38. def __getattr__(self, key):
  39. return self._kwargs[key]
  40. def __setattr__(self, key, value):
  41. self._kwargs[key] = value
  42. def __delattr__(self, key):
  43. del self._kwargs[key]
  44. def make(name):
  45. __all__.append(name)
  46. return type(name, (Token,), {})
  47. Text = make("Text")
  48. TemplateOpen = make("TemplateOpen") # {{
  49. TemplateParamSeparator = make("TemplateParamSeparator") # |
  50. TemplateParamEquals = make("TemplateParamEquals") # =
  51. TemplateClose = make("TemplateClose") # }}
  52. HTMLEntityStart = make("HTMLEntityStart") # &
  53. HTMLEntityNumeric = make("HTMLEntityNumeric") # #
  54. HTMLEntityHex = make("HTMLEntityHex") # x
  55. HTMLEntityEnd = make("HTMLEntityEnd") # ;
  56. HeadingStart = make("HeadingStart") # =...
  57. HeadingEnd = make("HeadingEnd") # =...
  58. TagOpenOpen = make("TagOpenOpen") # <
  59. TagAttrStart = make("TagAttrStart")
  60. TagAttrEquals = make("TagAttrEquals") # =
  61. TagAttrQuote = make("TagAttrQuote") # "
  62. TagCloseOpen = make("TagCloseOpen") # >
  63. TagCloseSelfclose = make("TagCloseSelfclose") # />
  64. TagOpenClose = make("TagOpenClose") # </
  65. TagCloseClose = make("TagCloseClose") # >
  66. del make