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.
 
 
 
 

208 lines
6.0 KiB

  1. #
  2. # Copyright (C) 2012-2019 Ben Kurtovic <ben.kurtovic@gmail.com>
  3. #
  4. # Permission is hereby granted, free of charge, to any person obtaining a copy
  5. # of this software and associated documentation files (the "Software"), to deal
  6. # in the Software without restriction, including without limitation the rights
  7. # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  8. # copies of the Software, and to permit persons to whom the Software is
  9. # furnished to do so, subject to the following conditions:
  10. #
  11. # The above copyright notice and this permission notice shall be included in
  12. # all copies or substantial portions of the Software.
  13. #
  14. # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  15. # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  16. # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  17. # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  18. # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  19. # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  20. # SOFTWARE.
  21. """
  22. This module contains various "context" definitions, which are essentially flags
  23. set during the tokenization process, either on the current parse stack (local
  24. contexts) or affecting all stacks (global contexts). They represent the context
  25. the tokenizer is in, such as inside a template's name definition, or inside a
  26. level-two heading. This is used to determine what tokens are valid at the
  27. current point and also if the current parsing route is invalid.
  28. The tokenizer stores context as an integer, with these definitions bitwise OR'd
  29. to set them, AND'd to check if they're set, and XOR'd to unset them. The
  30. advantage of this is that contexts can have sub-contexts (as ``FOO == 0b11``
  31. will cover ``BAR == 0b10`` and ``BAZ == 0b01``).
  32. Local (stack-specific) contexts:
  33. * :const:`TEMPLATE`
  34. * :const:`TEMPLATE_NAME`
  35. * :const:`TEMPLATE_PARAM_KEY`
  36. * :const:`TEMPLATE_PARAM_VALUE`
  37. * :const:`ARGUMENT`
  38. * :const:`ARGUMENT_NAME`
  39. * :const:`ARGUMENT_DEFAULT`
  40. * :const:`WIKILINK`
  41. * :const:`WIKILINK_TITLE`
  42. * :const:`WIKILINK_TEXT`
  43. * :const:`EXT_LINK`
  44. * :const:`EXT_LINK_URI`
  45. * :const:`EXT_LINK_TITLE`
  46. * :const:`HEADING`
  47. * :const:`HEADING_LEVEL_1`
  48. * :const:`HEADING_LEVEL_2`
  49. * :const:`HEADING_LEVEL_3`
  50. * :const:`HEADING_LEVEL_4`
  51. * :const:`HEADING_LEVEL_5`
  52. * :const:`HEADING_LEVEL_6`
  53. * :const:`TAG`
  54. * :const:`TAG_OPEN`
  55. * :const:`TAG_ATTR`
  56. * :const:`TAG_BODY`
  57. * :const:`TAG_CLOSE`
  58. * :const:`STYLE`
  59. * :const:`STYLE_ITALICS`
  60. * :const:`STYLE_BOLD`
  61. * :const:`STYLE_PASS_AGAIN`
  62. * :const:`STYLE_SECOND_PASS`
  63. * :const:`DL_TERM`
  64. * :const:`SAFETY_CHECK`
  65. * :const:`HAS_TEXT`
  66. * :const:`FAIL_ON_TEXT`
  67. * :const:`FAIL_NEXT`
  68. * :const:`FAIL_ON_LBRACE`
  69. * :const:`FAIL_ON_RBRACE`
  70. * :const:`FAIL_ON_EQUALS`
  71. * :const:`HAS_TEMPLATE`
  72. * :const:`TABLE`
  73. * :const:`TABLE_OPEN`
  74. * :const:`TABLE_CELL_OPEN`
  75. * :const:`TABLE_CELL_STYLE`
  76. * :const:`TABLE_TD_LINE`
  77. * :const:`TABLE_TH_LINE`
  78. * :const:`TABLE_CELL_LINE_CONTEXTS`
  79. * :const:`HTML_ENTITY`
  80. Global contexts:
  81. * :const:`GL_HEADING`
  82. Aggregate contexts:
  83. * :const:`FAIL`
  84. * :const:`UNSAFE`
  85. * :const:`DOUBLE`
  86. * :const:`NO_WIKILINKS`
  87. * :const:`NO_EXT_LINKS`
  88. """
  89. # Local contexts:
  90. TEMPLATE_NAME = 1 << 0
  91. TEMPLATE_PARAM_KEY = 1 << 1
  92. TEMPLATE_PARAM_VALUE = 1 << 2
  93. TEMPLATE = TEMPLATE_NAME + TEMPLATE_PARAM_KEY + TEMPLATE_PARAM_VALUE
  94. ARGUMENT_NAME = 1 << 3
  95. ARGUMENT_DEFAULT = 1 << 4
  96. ARGUMENT = ARGUMENT_NAME + ARGUMENT_DEFAULT
  97. WIKILINK_TITLE = 1 << 5
  98. WIKILINK_TEXT = 1 << 6
  99. WIKILINK = WIKILINK_TITLE + WIKILINK_TEXT
  100. EXT_LINK_URI = 1 << 7
  101. EXT_LINK_TITLE = 1 << 8
  102. EXT_LINK = EXT_LINK_URI + EXT_LINK_TITLE
  103. HEADING_LEVEL_1 = 1 << 9
  104. HEADING_LEVEL_2 = 1 << 10
  105. HEADING_LEVEL_3 = 1 << 11
  106. HEADING_LEVEL_4 = 1 << 12
  107. HEADING_LEVEL_5 = 1 << 13
  108. HEADING_LEVEL_6 = 1 << 14
  109. HEADING = (HEADING_LEVEL_1 + HEADING_LEVEL_2 + HEADING_LEVEL_3 +
  110. HEADING_LEVEL_4 + HEADING_LEVEL_5 + HEADING_LEVEL_6)
  111. TAG_OPEN = 1 << 15
  112. TAG_ATTR = 1 << 16
  113. TAG_BODY = 1 << 17
  114. TAG_CLOSE = 1 << 18
  115. TAG = TAG_OPEN + TAG_ATTR + TAG_BODY + TAG_CLOSE
  116. STYLE_ITALICS = 1 << 19
  117. STYLE_BOLD = 1 << 20
  118. STYLE_PASS_AGAIN = 1 << 21
  119. STYLE_SECOND_PASS = 1 << 22
  120. STYLE = STYLE_ITALICS + STYLE_BOLD + STYLE_PASS_AGAIN + STYLE_SECOND_PASS
  121. DL_TERM = 1 << 23
  122. HAS_TEXT = 1 << 24
  123. FAIL_ON_TEXT = 1 << 25
  124. FAIL_NEXT = 1 << 26
  125. FAIL_ON_LBRACE = 1 << 27
  126. FAIL_ON_RBRACE = 1 << 28
  127. FAIL_ON_EQUALS = 1 << 29
  128. HAS_TEMPLATE = 1 << 30
  129. SAFETY_CHECK = (HAS_TEXT + FAIL_ON_TEXT + FAIL_NEXT + FAIL_ON_LBRACE +
  130. FAIL_ON_RBRACE + FAIL_ON_EQUALS + HAS_TEMPLATE)
  131. TABLE_OPEN = 1 << 31
  132. TABLE_CELL_OPEN = 1 << 32
  133. TABLE_CELL_STYLE = 1 << 33
  134. TABLE_ROW_OPEN = 1 << 34
  135. TABLE_TD_LINE = 1 << 35
  136. TABLE_TH_LINE = 1 << 36
  137. TABLE_CELL_LINE_CONTEXTS = TABLE_TD_LINE + TABLE_TH_LINE + TABLE_CELL_STYLE
  138. TABLE = (TABLE_OPEN + TABLE_CELL_OPEN + TABLE_CELL_STYLE + TABLE_ROW_OPEN +
  139. TABLE_TD_LINE + TABLE_TH_LINE)
  140. HTML_ENTITY = 1 << 37
  141. # Global contexts:
  142. GL_HEADING = 1 << 0
  143. # Aggregate contexts:
  144. FAIL = (TEMPLATE + ARGUMENT + WIKILINK + EXT_LINK_TITLE + HEADING + TAG +
  145. STYLE + TABLE)
  146. UNSAFE = (TEMPLATE_NAME + WIKILINK_TITLE + EXT_LINK_TITLE +
  147. TEMPLATE_PARAM_KEY + ARGUMENT_NAME + TAG_CLOSE)
  148. DOUBLE = TEMPLATE_PARAM_KEY + TAG_CLOSE + TABLE_ROW_OPEN
  149. NO_WIKILINKS = TEMPLATE_NAME + ARGUMENT_NAME + WIKILINK_TITLE + EXT_LINK_URI
  150. NO_EXT_LINKS = TEMPLATE_NAME + ARGUMENT_NAME + WIKILINK_TITLE + EXT_LINK
  151. def describe(context):
  152. """Return a string describing the given context value, for debugging."""
  153. flags = []
  154. for name, value in globals().items():
  155. if not isinstance(value, int) or name.startswith("GL_"):
  156. continue
  157. if bin(value).count("1") != 1:
  158. continue # Hacky way to skip aggregate contexts
  159. if context & value:
  160. flags.append((name, value))
  161. flags.sort(key=lambda it: it[1])
  162. return "|".join(it[0] for it in flags)