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.
 
 
 
 

72 lines
3.1 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. """
  23. This module contains accessory functions that wrap around existing ones to
  24. provide additional functionality.
  25. """
  26. from __future__ import unicode_literals
  27. import mwparserfromhell
  28. from .compat import bytes, str
  29. from .nodes import Node
  30. from .smart_list import SmartList
  31. def parse_anything(value):
  32. """Return a :py:class:`~mwparserfromhell.wikicode.Wikicode` for *value*.
  33. This differs from :py:func:`mwparserfromhell.parse` in that we accept more
  34. than just a string to be parsed. Unicode objects (strings in py3k), strings
  35. (bytes in py3k), integers (converted to strings), ``None``, existing
  36. :py:class:`~mwparserfromhell.nodes.Node` or
  37. :py:class:`~mwparserfromhell.wikicode.Wikicode` objects, as well as an
  38. iterable of these types, are supported. This is used to parse input
  39. on-the-fly by various methods of
  40. :py:class:`~mwparserfromhell.wikicode.Wikicode` and others like
  41. :py:class:`~mwparserfromhell.nodes.template.Template`, such as
  42. :py:meth:`wikicode.insert() <mwparserfromhell.wikicode.Wikicode.insert>`
  43. or setting :py:meth:`template.name
  44. <mwparserfromhell.nodes.template.Template.name>`.
  45. """
  46. wikicode = mwparserfromhell.wikicode.Wikicode
  47. if isinstance(value, wikicode):
  48. return value
  49. elif isinstance(value, Node):
  50. return wikicode(SmartList([value]))
  51. elif isinstance(value, str):
  52. return mwparserfromhell.parse(value)
  53. elif isinstance(value, bytes):
  54. return mwparserfromhell.parse(value.decode("utf8"))
  55. elif isinstance(value, int):
  56. return mwparserfromhell.parse(str(value))
  57. elif value is None:
  58. return wikicode(SmartList())
  59. try:
  60. nodelist = SmartList()
  61. for item in value:
  62. nodelist += parse_anything(item).nodes
  63. except TypeError:
  64. error = "Needs string, Node, Wikicode, int, None, or iterable of these, but got {0}: {1}"
  65. raise ValueError(error.format(type(value).__name__, value))
  66. return wikicode(nodelist)