A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
Nie możesz wybrać więcej, niż 25 tematów Tematy muszą się zaczynać od litery lub cyfry, mogą zawierać myślniki ('-') i mogą mieć do 35 znaków.
 
 
 
 

165 wiersze
4.8 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 Node
  23. from mwparserfromhell.nodes.extras import Attribute
  24. __all__ = ["Tag"]
  25. class Tag(Node):
  26. TAG_UNKNOWN = 0
  27. # Basic HTML:
  28. TAG_ITALIC = 1
  29. TAG_BOLD = 2
  30. TAG_UNDERLINE = 3
  31. TAG_STRIKETHROUGH = 4
  32. TAG_UNORDERED_LIST = 5
  33. TAG_ORDERED_LIST = 6
  34. TAG_DEF_TERM = 7
  35. TAG_DEF_ITEM = 8
  36. TAG_BLOCKQUOTE = 9
  37. TAG_RULE = 10
  38. TAG_BREAK = 11
  39. TAG_ABBR = 12
  40. TAG_PRE = 13
  41. TAG_MONOSPACE = 14
  42. TAG_CODE = 15
  43. TAG_SPAN = 16
  44. TAG_DIV = 17
  45. TAG_FONT = 18
  46. TAG_SMALL = 19
  47. TAG_BIG = 20
  48. TAG_CENTER = 21
  49. # MediaWiki parser hooks:
  50. TAG_REF = 101
  51. TAG_GALLERY = 102
  52. TAG_MATH = 103
  53. TAG_NOWIKI = 104
  54. TAG_NOINCLUDE = 105
  55. TAG_INCLUDEONLY = 106
  56. TAG_ONLYINCLUDE = 107
  57. # Additional parser hooks:
  58. TAG_SYNTAXHIGHLIGHT = 201
  59. TAG_POEM = 202
  60. # Lists of tags:
  61. TAGS_INVISIBLE = set((TAG_REF, TAG_GALLERY, TAG_MATH, TAG_NOINCLUDE))
  62. TAGS_VISIBLE = set(range(300)) - TAGS_INVISIBLE
  63. def __init__(self, type_, tag, contents, attrs=None, showtag=True,
  64. self_closing=False, open_padding=0, close_padding=0):
  65. self._type = type_
  66. self._tag = tag
  67. self._contents = contents
  68. if attrs:
  69. self._attrs = attrs
  70. else:
  71. self._attrs = []
  72. self._showtag = showtag
  73. self._self_closing = self_closing
  74. self._open_padding = open_padding
  75. self._close_padding = close_padding
  76. def __unicode__(self):
  77. if not self.showtag:
  78. open_, close = self._translate()
  79. if self.self_closing:
  80. return _open
  81. else:
  82. return open_ + unicode(self.contents) + close
  83. result = "<" + unicode(self.tag)
  84. if self.attrs:
  85. result += " " + u" ".join([unicode(attr) for attr in self.attrs])
  86. if self.self_closing:
  87. result += " " * self.open_padding + "/>"
  88. else:
  89. result += " " * self.open_padding + ">" + unicode(self.contents)
  90. result += "</" + unicode(self.tag) + " " * self.close_padding + ">"
  91. return result
  92. def __iternodes__(self, getter):
  93. yield None, self
  94. if self.showtag:
  95. for child in getter(self.tag):
  96. yield self.tag, tag
  97. for attr in self.attrs:
  98. for child in getter(attr.name):
  99. yield attr.name, child
  100. if attr.value:
  101. for child in getter(attr.value):
  102. yield attr.value, child
  103. for child in getter(self.contents):
  104. yield self.contents, child
  105. def __strip__(self, normalize, collapse):
  106. if self.type in self.TAGS_VISIBLE:
  107. return self.contents.strip_code(normalize, collapse)
  108. return None
  109. def translate(self):
  110. translations = {
  111. self.TAG_ITALIC: ("''", "''"),
  112. self.TAG_BOLD: ("'''", "'''"),
  113. self.TAG_UNORDERED_LIST: ("*", ""),
  114. self.TAG_ORDERED_LIST: ("#", ""),
  115. self.TAG_DEF_TERM: (";", ""),
  116. self.TAG_DEF_ITEM: (":", ""),
  117. self.TAG_RULE: ("----", ""),
  118. }
  119. return translations[self.type]
  120. @property
  121. def type(self):
  122. return self._type
  123. @property
  124. def tag(self):
  125. return self._tag
  126. @property
  127. def contents(self):
  128. return self._contents
  129. @property
  130. def attrs(self):
  131. return self._attrs
  132. @property
  133. def showtag(self):
  134. return self._showtag
  135. @property
  136. def self_closing(self):
  137. return self._self_closing
  138. @property
  139. def open_padding(self):
  140. return self._open_padding
  141. @property
  142. def close_padding(self):
  143. return self._close_padding