A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
Nelze vybrat více než 25 témat Téma musí začínat písmenem nebo číslem, může obsahovat pomlčky („-“) a může být dlouhé až 35 znaků.
 
 
 
 

128 řádky
4.9 KiB

  1. # Copyright (C) 2012-2020 Ben Kurtovic <ben.kurtovic@gmail.com>
  2. #
  3. # Permission is hereby granted, free of charge, to any person obtaining a copy
  4. # of this software and associated documentation files (the "Software"), to deal
  5. # in the Software without restriction, including without limitation the rights
  6. # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  7. # copies of the Software, and to permit persons to whom the Software is
  8. # furnished to do so, subject to the following conditions:
  9. #
  10. # The above copyright notice and this permission notice shall be included in
  11. # all copies or substantial portions of the Software.
  12. #
  13. # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  14. # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  15. # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  16. # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  17. # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  18. # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  19. # SOFTWARE.
  20. """
  21. Integration test cases for mwparserfromhell's documentation.
  22. """
  23. import json
  24. from io import StringIO
  25. import os
  26. from urllib.parse import urlencode
  27. from urllib.request import urlopen
  28. import pytest
  29. import mwparserfromhell
  30. def assert_print(value, output):
  31. """Assertion check that *value*, when printed, produces *output*."""
  32. buff = StringIO()
  33. print(value, end="", file=buff)
  34. buff.seek(0)
  35. assert output == buff.read()
  36. def test_readme_1():
  37. """test a block of example code in the README"""
  38. text = "I has a template! {{foo|bar|baz|eggs=spam}} See it?"
  39. wikicode = mwparserfromhell.parse(text)
  40. assert_print(wikicode, "I has a template! {{foo|bar|baz|eggs=spam}} See it?")
  41. templates = wikicode.filter_templates()
  42. assert_print(templates, "['{{foo|bar|baz|eggs=spam}}']")
  43. template = templates[0]
  44. assert_print(template.name, "foo")
  45. assert_print(template.params, "['bar', 'baz', 'eggs=spam']")
  46. assert_print(template.get(1).value, "bar")
  47. assert_print(template.get("eggs").value, "spam")
  48. def test_readme_2():
  49. """test a block of example code in the README"""
  50. text = "{{foo|{{bar}}={{baz|{{spam}}}}}}"
  51. temps = mwparserfromhell.parse(text).filter_templates()
  52. res = "['{{foo|{{bar}}={{baz|{{spam}}}}}}', '{{bar}}', '{{baz|{{spam}}}}', '{{spam}}']"
  53. assert_print(temps, res)
  54. def test_readme_3():
  55. """test a block of example code in the README"""
  56. code = mwparserfromhell.parse("{{foo|this {{includes a|template}}}}")
  57. assert_print(
  58. code.filter_templates(recursive=False),
  59. "['{{foo|this {{includes a|template}}}}']",
  60. )
  61. foo = code.filter_templates(recursive=False)[0]
  62. assert_print(foo.get(1).value, "this {{includes a|template}}")
  63. assert_print(foo.get(1).value.filter_templates()[0], "{{includes a|template}}")
  64. assert_print(foo.get(1).value.filter_templates()[0].get(1).value, "template")
  65. def test_readme_4():
  66. """test a block of example code in the README"""
  67. text = "{{cleanup}} '''Foo''' is a [[bar]]. {{uncategorized}}"
  68. code = mwparserfromhell.parse(text)
  69. for template in code.filter_templates():
  70. if template.name.matches("Cleanup") and not template.has("date"):
  71. template.add("date", "July 2012")
  72. res = "{{cleanup|date=July 2012}} '''Foo''' is a [[bar]]. {{uncategorized}}"
  73. assert_print(code, res)
  74. code.replace("{{uncategorized}}", "{{bar-stub}}")
  75. res = "{{cleanup|date=July 2012}} '''Foo''' is a [[bar]]. {{bar-stub}}"
  76. assert_print(code, res)
  77. res = "['{{cleanup|date=July 2012}}', '{{bar-stub}}']"
  78. assert_print(code.filter_templates(), res)
  79. text = str(code)
  80. res = "{{cleanup|date=July 2012}} '''Foo''' is a [[bar]]. {{bar-stub}}"
  81. assert_print(text, res)
  82. assert text == code
  83. @pytest.mark.skipif("NOWEB" in os.environ, reason="web test disabled by environ var")
  84. def test_readme_5():
  85. """test a block of example code in the README; includes a web call"""
  86. url1 = "https://en.wikipedia.org/w/api.php"
  87. url2 = "https://en.wikipedia.org/w/index.php?title={0}&action=raw"
  88. title = "Test"
  89. data = {
  90. "action": "query",
  91. "prop": "revisions",
  92. "rvprop": "content",
  93. "rvslots": "main",
  94. "rvlimit": 1,
  95. "titles": title,
  96. "format": "json",
  97. "formatversion": "2",
  98. }
  99. try:
  100. raw = urlopen(url1, urlencode(data).encode("utf8")).read()
  101. except OSError:
  102. pytest.skip("cannot continue because of unsuccessful web call")
  103. res = json.loads(raw.decode("utf8"))
  104. revision = res["query"]["pages"][0]["revisions"][0]
  105. text = revision["slots"]["main"]["content"]
  106. try:
  107. expected = urlopen(url2.format(title)).read().decode("utf8")
  108. except OSError:
  109. pytest.skip("cannot continue because of unsuccessful web call")
  110. actual = mwparserfromhell.parse(text)
  111. assert expected == actual