A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
Não pode escolher mais do que 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
 
 
 
 

112 linhas
4.3 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. from mwparserfromhell.nodes import HTMLEntity, Node
  23. from mwparserfromhell.nodes.extras import Parameter
  24. from mwparserfromhell.utils import parse_anything
  25. __all__ = ["Template"]
  26. class Template(Node):
  27. def __init__(self, name, params=None):
  28. self._name = name
  29. if params:
  30. self._params = params
  31. else:
  32. self._params = []
  33. def __unicode__(self):
  34. if self.params:
  35. params = u"|".join([unicode(param) for param in self.params])
  36. return "{{" + unicode(self.name) + "|" + params + "}}"
  37. else:
  38. return "{{" + unicode(self.name) + "}}"
  39. def _surface_escape(self, code, char):
  40. replacement = HTMLEntity(value=ord(char))
  41. for node in code.filter_text(recursive=False):
  42. if char in node:
  43. code.replace(node, node.replace(char, replacement))
  44. def _blank_param_value(self, value): # TODO
  45. pass # MAKE VALUE CONTAIN ABSOLUTELY TWO TEXT NODES: FIRST IS SPACING BEFORE CHUNK AND SECOND IS SPACING AFTER CHUNK
  46. @property
  47. def name(self):
  48. return self._name
  49. @property
  50. def params(self):
  51. return self._params
  52. def has_param(self, name):
  53. name = name.strip() if isinstance(name, basestring) else unicode(name)
  54. for param in self.params:
  55. if param.name.strip() == name:
  56. return True
  57. return False
  58. def get(self, name):
  59. name = name.strip() if isinstance(name, basestring) else unicode(name)
  60. for param in self.params:
  61. if param.name.strip() == name:
  62. return param
  63. raise ValueError(name)
  64. def add(self, name, value, showkey=None):
  65. name, value = parse_anything(name), parse_anything(value)
  66. self._surface_escape(value, "|")
  67. if self.has_param(name):
  68. self.remove(name, keep_field=True)
  69. existing = self.get(name)
  70. if showkey is None: # Infer showkey from current value
  71. showkey = existing.showkey
  72. if not showkey:
  73. self._surface_escape(value, "=")
  74. nodes = existing.value.nodes
  75. existing.value = parse_anything([nodes[0], value, nodes[1]])
  76. return existing
  77. if showkey is None:
  78. try:
  79. int(name)
  80. except ValueError:
  81. showkey = False
  82. else:
  83. showkey = True
  84. if not showkey:
  85. self._surface_escape(value, "=")
  86. param = Parameter(name, value, showkey) # CONFORM TO FORMATTING CONVENTIONS?
  87. self.params.append(param)
  88. return param
  89. def remove(self, name, keep_field=False): # DON'T MESS UP NUMBERING WITH show_key = False AND keep_field = False
  90. name = name.strip() if isinstance(name, basestring) else unicode(name)
  91. for param in self.params:
  92. if param.name.strip() == name:
  93. if keep_field:
  94. return self._blank_param_value(param.value)
  95. else:
  96. return self.params.remove(param)
  97. raise ValueError(name)