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.
 
 
 
 

61 lines
2.4 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 package contains the actual wikicode parser, split up into two main
  24. modules: the :py:mod:`~mwparserfromhell.parser.tokenizer` and the
  25. :py:mod:`~mwparserfromhell.parser.builder`. This module joins them together
  26. under one interface.
  27. """
  28. try:
  29. from ._builder import CBuilder as Builder
  30. from ._tokenizer import CTokenizer as Tokenizer
  31. except ImportError:
  32. from .builder import Builder
  33. from .tokenizer import Tokenizer
  34. __all__ = ["Parser"]
  35. class Parser(object):
  36. """Represents a parser for wikicode.
  37. Actual parsing is a two-step process: first, the text is split up into a
  38. series of tokens by the
  39. :py:class:`~mwparserfromhell.parser.tokenizer.Tokenizer`, and then the
  40. tokens are converted into trees of
  41. :py:class:`~mwparserfromhell.wikicode.Wikicode` objects and
  42. :py:class:`~mwparserfromhell.nodes.Node`\ s by the
  43. :py:class:`~mwparserfromhell.parser.builder.Builder`.
  44. """
  45. def __init__(self, text):
  46. self.text = text
  47. self._tokenizer = Tokenizer()
  48. self._builder = Builder()
  49. def parse(self):
  50. """Return a string as a parsed ``Wikicode`` object tree."""
  51. tokens = self._tokenizer.tokenize(self.text)
  52. code = self._builder.build(tokens)
  53. return code