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.
 
 
 
 

232 řádky
6.0 KiB

  1. # Copyright (C) 2012-2019 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. This module contains various "context" definitions, which are essentially flags
  22. set during the tokenization process, either on the current parse stack (local
  23. contexts) or affecting all stacks (global contexts). They represent the context
  24. the tokenizer is in, such as inside a template's name definition, or inside a
  25. level-two heading. This is used to determine what tokens are valid at the
  26. current point and also if the current parsing route is invalid.
  27. The tokenizer stores context as an integer, with these definitions bitwise OR'd
  28. to set them, AND'd to check if they're set, and XOR'd to unset them. The
  29. advantage of this is that contexts can have sub-contexts (as ``FOO == 0b11``
  30. will cover ``BAR == 0b10`` and ``BAZ == 0b01``).
  31. Local (stack-specific) contexts:
  32. * :const:`TEMPLATE`
  33. * :const:`TEMPLATE_NAME`
  34. * :const:`TEMPLATE_PARAM_KEY`
  35. * :const:`TEMPLATE_PARAM_VALUE`
  36. * :const:`ARGUMENT`
  37. * :const:`ARGUMENT_NAME`
  38. * :const:`ARGUMENT_DEFAULT`
  39. * :const:`WIKILINK`
  40. * :const:`WIKILINK_TITLE`
  41. * :const:`WIKILINK_TEXT`
  42. * :const:`EXT_LINK`
  43. * :const:`EXT_LINK_URI`
  44. * :const:`EXT_LINK_TITLE`
  45. * :const:`HEADING`
  46. * :const:`HEADING_LEVEL_1`
  47. * :const:`HEADING_LEVEL_2`
  48. * :const:`HEADING_LEVEL_3`
  49. * :const:`HEADING_LEVEL_4`
  50. * :const:`HEADING_LEVEL_5`
  51. * :const:`HEADING_LEVEL_6`
  52. * :const:`TAG`
  53. * :const:`TAG_OPEN`
  54. * :const:`TAG_ATTR`
  55. * :const:`TAG_BODY`
  56. * :const:`TAG_CLOSE`
  57. * :const:`STYLE`
  58. * :const:`STYLE_ITALICS`
  59. * :const:`STYLE_BOLD`
  60. * :const:`STYLE_PASS_AGAIN`
  61. * :const:`STYLE_SECOND_PASS`
  62. * :const:`DL_TERM`
  63. * :const:`SAFETY_CHECK`
  64. * :const:`HAS_TEXT`
  65. * :const:`FAIL_ON_TEXT`
  66. * :const:`FAIL_NEXT`
  67. * :const:`FAIL_ON_LBRACE`
  68. * :const:`FAIL_ON_RBRACE`
  69. * :const:`FAIL_ON_EQUALS`
  70. * :const:`HAS_TEMPLATE`
  71. * :const:`TABLE`
  72. * :const:`TABLE_OPEN`
  73. * :const:`TABLE_CELL_OPEN`
  74. * :const:`TABLE_CELL_STYLE`
  75. * :const:`TABLE_TD_LINE`
  76. * :const:`TABLE_TH_LINE`
  77. * :const:`TABLE_CELL_LINE_CONTEXTS`
  78. * :const:`HTML_ENTITY`
  79. Global contexts:
  80. * :const:`GL_HEADING`
  81. Aggregate contexts:
  82. * :const:`FAIL`
  83. * :const:`UNSAFE`
  84. * :const:`DOUBLE`
  85. * :const:`NO_WIKILINKS`
  86. * :const:`NO_EXT_LINKS`
  87. """
  88. # Local contexts:
  89. TEMPLATE_NAME = 1 << 0
  90. TEMPLATE_PARAM_KEY = 1 << 1
  91. TEMPLATE_PARAM_VALUE = 1 << 2
  92. TEMPLATE = TEMPLATE_NAME + TEMPLATE_PARAM_KEY + TEMPLATE_PARAM_VALUE
  93. ARGUMENT_NAME = 1 << 3
  94. ARGUMENT_DEFAULT = 1 << 4
  95. ARGUMENT = ARGUMENT_NAME + ARGUMENT_DEFAULT
  96. WIKILINK_TITLE = 1 << 5
  97. WIKILINK_TEXT = 1 << 6
  98. WIKILINK = WIKILINK_TITLE + WIKILINK_TEXT
  99. EXT_LINK_URI = 1 << 7
  100. EXT_LINK_TITLE = 1 << 8
  101. EXT_LINK = EXT_LINK_URI + EXT_LINK_TITLE
  102. HEADING_LEVEL_1 = 1 << 9
  103. HEADING_LEVEL_2 = 1 << 10
  104. HEADING_LEVEL_3 = 1 << 11
  105. HEADING_LEVEL_4 = 1 << 12
  106. HEADING_LEVEL_5 = 1 << 13
  107. HEADING_LEVEL_6 = 1 << 14
  108. HEADING = (
  109. HEADING_LEVEL_1
  110. + HEADING_LEVEL_2
  111. + HEADING_LEVEL_3
  112. + HEADING_LEVEL_4
  113. + HEADING_LEVEL_5
  114. + HEADING_LEVEL_6
  115. )
  116. TAG_OPEN = 1 << 15
  117. TAG_ATTR = 1 << 16
  118. TAG_BODY = 1 << 17
  119. TAG_CLOSE = 1 << 18
  120. TAG = TAG_OPEN + TAG_ATTR + TAG_BODY + TAG_CLOSE
  121. STYLE_ITALICS = 1 << 19
  122. STYLE_BOLD = 1 << 20
  123. STYLE_PASS_AGAIN = 1 << 21
  124. STYLE_SECOND_PASS = 1 << 22
  125. STYLE = STYLE_ITALICS + STYLE_BOLD + STYLE_PASS_AGAIN + STYLE_SECOND_PASS
  126. DL_TERM = 1 << 23
  127. HAS_TEXT = 1 << 24
  128. FAIL_ON_TEXT = 1 << 25
  129. FAIL_NEXT = 1 << 26
  130. FAIL_ON_LBRACE = 1 << 27
  131. FAIL_ON_RBRACE = 1 << 28
  132. FAIL_ON_EQUALS = 1 << 29
  133. HAS_TEMPLATE = 1 << 30
  134. SAFETY_CHECK = (
  135. HAS_TEXT
  136. + FAIL_ON_TEXT
  137. + FAIL_NEXT
  138. + FAIL_ON_LBRACE
  139. + FAIL_ON_RBRACE
  140. + FAIL_ON_EQUALS
  141. + HAS_TEMPLATE
  142. )
  143. TABLE_OPEN = 1 << 31
  144. TABLE_CELL_OPEN = 1 << 32
  145. TABLE_CELL_STYLE = 1 << 33
  146. TABLE_ROW_OPEN = 1 << 34
  147. TABLE_TD_LINE = 1 << 35
  148. TABLE_TH_LINE = 1 << 36
  149. TABLE_CELL_LINE_CONTEXTS = TABLE_TD_LINE + TABLE_TH_LINE + TABLE_CELL_STYLE
  150. TABLE = (
  151. TABLE_OPEN
  152. + TABLE_CELL_OPEN
  153. + TABLE_CELL_STYLE
  154. + TABLE_ROW_OPEN
  155. + TABLE_TD_LINE
  156. + TABLE_TH_LINE
  157. )
  158. HTML_ENTITY = 1 << 37
  159. # Global contexts:
  160. GL_HEADING = 1 << 0
  161. # Aggregate contexts:
  162. FAIL = TEMPLATE + ARGUMENT + WIKILINK + EXT_LINK_TITLE + HEADING + TAG + STYLE + TABLE
  163. UNSAFE = (
  164. TEMPLATE_NAME
  165. + WIKILINK_TITLE
  166. + EXT_LINK_TITLE
  167. + TEMPLATE_PARAM_KEY
  168. + ARGUMENT_NAME
  169. + TAG_CLOSE
  170. )
  171. DOUBLE = TEMPLATE_PARAM_KEY + TAG_CLOSE + TABLE_ROW_OPEN
  172. NO_WIKILINKS = TEMPLATE_NAME + ARGUMENT_NAME + WIKILINK_TITLE + EXT_LINK_URI
  173. NO_EXT_LINKS = TEMPLATE_NAME + ARGUMENT_NAME + WIKILINK_TITLE + EXT_LINK
  174. def describe(context):
  175. """Return a string describing the given context value, for debugging."""
  176. flags = []
  177. for name, value in globals().items():
  178. if not isinstance(value, int) or name.startswith("GL_"):
  179. continue
  180. if bin(value).count("1") != 1:
  181. continue # Hacky way to skip aggregate contexts
  182. if context & value:
  183. flags.append((name, value))
  184. flags.sort(key=lambda it: it[1])
  185. return "|".join(it[0] for it in flags)