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.
 
 
 
 

67 lines
2.7 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. from __future__ import unicode_literals
  23. import unittest
  24. from mwparserfromhell import parser
  25. from mwparserfromhell.nodes import Template, Text, Wikilink
  26. from mwparserfromhell.nodes.extras import Parameter
  27. from ._test_tree_equality import TreeEqualityTestCase, wrap, wraptext
  28. from .compat import range
  29. class TestParser(TreeEqualityTestCase):
  30. """Tests for the Parser class itself, which tokenizes and builds nodes."""
  31. def test_use_c(self):
  32. """make sure the correct tokenizer is used"""
  33. if parser.use_c:
  34. self.assertTrue(parser.Parser()._tokenizer.USES_C)
  35. parser.use_c = False
  36. self.assertFalse(parser.Parser()._tokenizer.USES_C)
  37. def test_parsing(self):
  38. """integration test for parsing overall"""
  39. text = "this is text; {{this|is=a|template={{with|[[links]]|in}}it}}"
  40. expected = wrap([
  41. Text("this is text; "),
  42. Template(wraptext("this"), [
  43. Parameter(wraptext("is"), wraptext("a")),
  44. Parameter(wraptext("template"), wrap([
  45. Template(wraptext("with"), [
  46. Parameter(wraptext("1"),
  47. wrap([Wikilink(wraptext("links"))]),
  48. showkey=False),
  49. Parameter(wraptext("2"),
  50. wraptext("in"), showkey=False)
  51. ]),
  52. Text("it")
  53. ]))
  54. ])
  55. ])
  56. actual = parser.Parser().parse(text)
  57. self.assertWikicodeEqual(expected, actual)
  58. if __name__ == "__main__":
  59. unittest.main(verbosity=2)