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.
 
 
 
 

77 lines
3.3 KiB

  1. # -*- coding: utf-8 -*-
  2. #
  3. # Copyright (C) 2012-2013 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. """
  23. This module contains accessory functions that wrap around existing ones to
  24. provide additional functionality.
  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):
  32. """Return a :py:class:`~.Wikicode` for *value*, allowing multiple types.
  33. This differs from :py:meth:`.Parser.parse` in that we accept more than just
  34. a string to be parsed. Unicode objects (strings in py3k), strings (bytes in
  35. py3k), integers (converted to strings), ``None``, existing
  36. :py:class:`~.Node` or :py:class:`~.Wikicode` objects, as well as an
  37. iterable of these types, are supported. This is used to parse input
  38. on-the-fly by various methods of :py:class:`~.Wikicode` and others like
  39. :py:class:`~.Template`, such as :py:meth:`wikicode.insert()
  40. <.Wikicode.insert>` or setting :py:meth:`template.name <.Template.name>`.
  41. If given, *context* will be passed as a starting context to the parser.
  42. This is helpful when this function is used inside node attribute setters.
  43. For example, :py:class:`~.ExternalLink`\ 's :py:attr:`~.ExternalLink.url`
  44. setter sets *context* to :py:mod:`contexts.EXT_LINK_URI <.contexts>` to
  45. prevent the URL itself from becoming an :py:class:`~.ExternalLink`.
  46. """
  47. from .parser import Parser
  48. from .wikicode import Wikicode
  49. if isinstance(value, Wikicode):
  50. return value
  51. elif isinstance(value, Node):
  52. return Wikicode(SmartList([value]))
  53. elif isinstance(value, str):
  54. return Parser().parse(value, context)
  55. elif isinstance(value, bytes):
  56. return Parser().parse(value.decode("utf8"), context)
  57. elif isinstance(value, int):
  58. return Parser().parse(str(value), context)
  59. elif value is None:
  60. return Wikicode(SmartList())
  61. try:
  62. nodelist = SmartList()
  63. for item in value:
  64. nodelist += parse_anything(item, context).nodes
  65. except TypeError:
  66. error = "Needs string, Node, Wikicode, int, None, or iterable of these, but got {0}: {1}"
  67. raise ValueError(error.format(type(value).__name__, value))
  68. return Wikicode(nodelist)