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.
 
 
 
 

75 lines
3.2 KiB

  1. # -*- coding: utf-8 -*-
  2. #
  3. # Copyright (C) 2012-2019 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 accessory functions for other parts of the library. Parser
  24. users generally won't need stuff from here.
  25. """
  26. from __future__ import unicode_literals
  27. from .compat import bytes, str
  28. from .nodes import Node
  29. from .smart_list import SmartList
  30. __all__ = ["parse_anything"]
  31. def parse_anything(value, context=0, skip_style_tags=False):
  32. """Return a :class:`.Wikicode` for *value*, allowing multiple types.
  33. This differs from :meth:`.Parser.parse` in that we accept more than just a
  34. string to be parsed. Unicode objects (strings in py3k), strings (bytes in
  35. py3k), integers (converted to strings), ``None``, existing :class:`.Node`
  36. or :class:`.Wikicode` objects, as well as an iterable of these types, are
  37. supported. This is used to parse input on-the-fly by various methods of
  38. :class:`.Wikicode` and others like :class:`.Template`, such as
  39. :meth:`wikicode.insert() <.Wikicode.insert>` or setting
  40. :meth:`template.name <.Template.name>`.
  41. Additional arguments are passed directly to :meth:`.Parser.parse`.
  42. """
  43. from .parser import Parser
  44. from .wikicode import Wikicode
  45. if isinstance(value, Wikicode):
  46. return value
  47. elif isinstance(value, Node):
  48. return Wikicode(SmartList([value]))
  49. elif isinstance(value, str):
  50. return Parser().parse(value, context, skip_style_tags)
  51. elif isinstance(value, bytes):
  52. return Parser().parse(value.decode("utf8"), context, skip_style_tags)
  53. elif isinstance(value, int):
  54. return Parser().parse(str(value), context, skip_style_tags)
  55. elif value is None:
  56. return Wikicode(SmartList())
  57. elif hasattr(value, "read"):
  58. return parse_anything(value.read(), context, skip_style_tags)
  59. try:
  60. nodelist = SmartList()
  61. for item in value:
  62. nodelist += parse_anything(item, context, skip_style_tags).nodes
  63. return Wikicode(nodelist)
  64. except TypeError:
  65. error = "Needs string, Node, Wikicode, file, int, None, or iterable of these, but got {0}: {1}"
  66. raise ValueError(error.format(type(value).__name__, value))