A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
25'ten fazla konu seçemezsiniz Konular bir harf veya rakamla başlamalı, kısa çizgiler ('-') içerebilir ve en fazla 35 karakter uzunluğunda olabilir.
 
 
 
 

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