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.
 
 
 
 

98 lines
4.3 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.compat import range
  26. from mwparserfromhell.nodes import Template, Text, Wikilink
  27. from mwparserfromhell.nodes.extras import Parameter
  28. from mwparserfromhell.smart_list import SmartList
  29. from mwparserfromhell.wikicode import Wikicode
  30. class TestParser(unittest.TestCase):
  31. """Tests for the Parser class itself, which tokenizes and builds nodes."""
  32. def assertNodesEqual(self, expected, actual):
  33. """Assert that two Nodes are the same type and have the same data."""
  34. self.assertIs(type(expected), type(actual))
  35. if isinstance(expected, Text):
  36. self.assertEqual(expected.value, actual.value)
  37. elif isinstance(expected, Template):
  38. self.assertWikicodeEqual(expected.name, actual.name)
  39. length = len(expected.params)
  40. self.assertEqual(length, len(actual.params))
  41. for i in range(length):
  42. exp_param = expected.params[i]
  43. act_param = actual.params[i]
  44. self.assertWikicodeEqual(exp_param.name, act_param.name)
  45. self.assertWikicodeEqual(exp_param.value, act_param.value)
  46. self.assertIs(exp_param.showkey, act_param.showkey)
  47. elif isinstance(expected, Wikilink):
  48. self.assertWikicodeEqual(expected.title, actual.title)
  49. if expected.text is not None:
  50. self.assertWikicodeEqual(expected.text, actual.text)
  51. else:
  52. self.assertIs(None, actual.text)
  53. def assertWikicodeEqual(self, expected, actual):
  54. """Assert that two Wikicode objects have the same data."""
  55. self.assertIsInstance(actual, Wikicode)
  56. length = len(expected.nodes)
  57. self.assertEqual(length, len(actual.nodes))
  58. for i in range(length):
  59. self.assertNodesEqual(expected.get(i), actual.get(i))
  60. def test_use_c(self):
  61. """make sure the correct tokenizer is used"""
  62. if parser.use_c:
  63. self.assertTrue(parser.Parser(None)._tokenizer.USES_C)
  64. parser.use_c = False
  65. self.assertFalse(parser.Parser(None)._tokenizer.USES_C)
  66. def test_parsing(self):
  67. """integration test for parsing overall"""
  68. text = "this is text; {{this|is=a|template={{with|[[links]]|in}}it}}"
  69. wrap = lambda L: Wikicode(SmartList(L))
  70. expected = wrap([
  71. Text("this is text; "),
  72. Template(wrap([Text("this")]), [
  73. Parameter(wrap([Text("is")]), wrap([Text("a")])),
  74. Parameter(wrap([Text("template")]), wrap([
  75. Template(wrap([Text("with")]), [
  76. Parameter(wrap([Text("1")]),
  77. wrap([Wikilink(wrap([Text("links")]))]),
  78. showkey=False),
  79. Parameter(wrap([Text("2")]),
  80. wrap([Text("in")]), showkey=False)
  81. ]),
  82. Text("it")
  83. ]))
  84. ])
  85. ])
  86. actual = parser.Parser(text).parse()
  87. self.assertWikicodeEqual(expected, actual)
  88. if __name__ == "__main__":
  89. unittest.main(verbosity=2)