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.
 
 
 
 

76 lines
3.1 KiB

  1. #
  2. # Copyright (C) 2012-2016 Ben Kurtovic <ben.kurtovic@gmail.com>
  3. #
  4. # Permission is hereby granted, free of charge, to any person obtaining a copy
  5. # of this software and associated documentation files (the "Software"), to deal
  6. # in the Software without restriction, including without limitation the rights
  7. # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  8. # copies of the Software, and to permit persons to whom the Software is
  9. # furnished to do so, subject to the following conditions:
  10. #
  11. # The above copyright notice and this permission notice shall be included in
  12. # all copies or substantial portions of the Software.
  13. #
  14. # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  15. # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  16. # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  17. # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  18. # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  19. # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  20. # SOFTWARE.
  21. """
  22. This package contains :class:`.Wikicode` "nodes", which represent a single unit
  23. of wikitext, such as a Template, an HTML tag, a Heading, or plain text. The
  24. node "tree" is far from flat, as most types can contain additional
  25. :class:`.Wikicode` types within them - and with that, more nodes. For example,
  26. the name of a :class:`.Template` is a :class:`.Wikicode` object that can
  27. contain text or more templates.
  28. """
  29. from ..string_mixin import StringMixIn
  30. __all__ = ["Argument", "Comment", "ExternalLink", "HTMLEntity", "Heading",
  31. "Node", "Tag", "Template", "Text", "Wikilink"]
  32. class Node(StringMixIn):
  33. """Represents the base Node type, demonstrating the methods to override.
  34. :meth:`__unicode__` must be overridden. It should return a ``unicode`` or
  35. (``str`` in py3k) representation of the node. If the node contains
  36. :class:`.Wikicode` objects inside of it, :meth:`__children__` should be a
  37. generator that iterates over them. If the node is printable
  38. (shown when the page is rendered), :meth:`__strip__` should return its
  39. printable version, stripping out any formatting marks. It does not have to
  40. return a string, but something that can be converted to a string with
  41. ``str()``. Finally, :meth:`__showtree__` can be overridden to build a
  42. nice tree representation of the node, if desired, for
  43. :meth:`~.Wikicode.get_tree`.
  44. """
  45. def __unicode__(self):
  46. raise NotImplementedError()
  47. def __children__(self):
  48. return
  49. # pylint: disable=unreachable
  50. yield # pragma: no cover (this is a generator that yields nothing)
  51. def __strip__(self, **kwargs):
  52. return None
  53. def __showtree__(self, write, get, mark):
  54. write(str(self))
  55. from . import extras
  56. from .text import Text
  57. from .argument import Argument
  58. from .comment import Comment
  59. from .external_link import ExternalLink
  60. from .heading import Heading
  61. from .html_entity import HTMLEntity
  62. from .tag import Tag
  63. from .template import Template
  64. from .wikilink import Wikilink