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.
 
 
 
 

70 lines
2.9 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 mwparserfromhell.smart_list import SmartList
  28. from mwparserfromhell.wikicode import Wikicode
  29. from ._test_tree_equality import TreeEqualityTestCase
  30. from .compat import range
  31. class TestParser(TreeEqualityTestCase):
  32. """Tests for the Parser class itself, which tokenizes and builds nodes."""
  33. def test_use_c(self):
  34. """make sure the correct tokenizer is used"""
  35. if parser.use_c:
  36. self.assertTrue(parser.Parser(None)._tokenizer.USES_C)
  37. parser.use_c = False
  38. self.assertFalse(parser.Parser(None)._tokenizer.USES_C)
  39. def test_parsing(self):
  40. """integration test for parsing overall"""
  41. text = "this is text; {{this|is=a|template={{with|[[links]]|in}}it}}"
  42. wrap = lambda L: Wikicode(SmartList(L))
  43. expected = wrap([
  44. Text("this is text; "),
  45. Template(wrap([Text("this")]), [
  46. Parameter(wrap([Text("is")]), wrap([Text("a")])),
  47. Parameter(wrap([Text("template")]), wrap([
  48. Template(wrap([Text("with")]), [
  49. Parameter(wrap([Text("1")]),
  50. wrap([Wikilink(wrap([Text("links")]))]),
  51. showkey=False),
  52. Parameter(wrap([Text("2")]),
  53. wrap([Text("in")]), showkey=False)
  54. ]),
  55. Text("it")
  56. ]))
  57. ])
  58. ])
  59. actual = parser.Parser(text).parse()
  60. self.assertWikicodeEqual(expected, actual)
  61. if __name__ == "__main__":
  62. unittest.main(verbosity=2)