A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
Вы не можете выбрать более 25 тем Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
 
 
 
 

110 строки
4.6 KiB

  1. # -*- coding: utf-8 -*-
  2. #
  3. # Copyright (C) 2012-2016 Ben Kurtovic <ben.kurtovic@gmail.com>
  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. """
  23. This module contains the token definitions that are used as an intermediate
  24. parsing data type - they are stored in a flat list, with each token being
  25. identified by its type and optional attributes. The token list is generated in
  26. a syntactically valid form by the :class:`.Tokenizer`, and then converted into
  27. the :class`.Wikicode` tree by the :class:`.Builder`.
  28. """
  29. from __future__ import unicode_literals
  30. from ..compat import py3k, str
  31. __all__ = ["Token"]
  32. class Token(dict):
  33. """A token stores the semantic meaning of a unit of wikicode."""
  34. def __repr__(self):
  35. args = []
  36. for key, value in self.items():
  37. if isinstance(value, str) and len(value) > 100:
  38. args.append(key + "=" + repr(value[:97] + "..."))
  39. else:
  40. args.append(key + "=" + repr(value))
  41. return "{}({})".format(type(self).__name__, ", ".join(args))
  42. def __eq__(self, other):
  43. return isinstance(other, type(self)) and dict.__eq__(self, other)
  44. def __ne__(self, other):
  45. return not self.__eq__(other)
  46. def __getattr__(self, key):
  47. return self.get(key)
  48. def __setattr__(self, key, value):
  49. self[key] = value
  50. def __delattr__(self, key):
  51. del self[key]
  52. def make(name):
  53. """Create a new Token class using ``type()`` and add it to ``__all__``."""
  54. __all__.append(name)
  55. return type(name if py3k else name.encode("utf8"), (Token,), {})
  56. Text = make("Text")
  57. TemplateOpen = make("TemplateOpen") # {{
  58. TemplateParamSeparator = make("TemplateParamSeparator") # |
  59. TemplateParamEquals = make("TemplateParamEquals") # =
  60. TemplateClose = make("TemplateClose") # }}
  61. ArgumentOpen = make("ArgumentOpen") # {{{
  62. ArgumentSeparator = make("ArgumentSeparator") # |
  63. ArgumentClose = make("ArgumentClose") # }}}
  64. WikilinkOpen = make("WikilinkOpen") # [[
  65. WikilinkSeparator = make("WikilinkSeparator") # |
  66. WikilinkClose = make("WikilinkClose") # ]]
  67. ExternalLinkOpen = make("ExternalLinkOpen") # [
  68. ExternalLinkSeparator = make("ExternalLinkSeparator") #
  69. ExternalLinkClose = make("ExternalLinkClose") # ]
  70. HTMLEntityStart = make("HTMLEntityStart") # &
  71. HTMLEntityNumeric = make("HTMLEntityNumeric") # #
  72. HTMLEntityHex = make("HTMLEntityHex") # x
  73. HTMLEntityEnd = make("HTMLEntityEnd") # ;
  74. HeadingStart = make("HeadingStart") # =...
  75. HeadingEnd = make("HeadingEnd") # =...
  76. CommentStart = make("CommentStart") # <!--
  77. CommentEnd = make("CommentEnd") # -->
  78. TagOpenOpen = make("TagOpenOpen") # <
  79. TagAttrStart = make("TagAttrStart")
  80. TagAttrEquals = make("TagAttrEquals") # =
  81. TagAttrQuote = make("TagAttrQuote") # ", '
  82. TagCloseOpen = make("TagCloseOpen") # >
  83. TagCloseSelfclose = make("TagCloseSelfclose") # />
  84. TagOpenClose = make("TagOpenClose") # </
  85. TagCloseClose = make("TagCloseClose") # >
  86. del make