A Python parser for MediaWiki wikicode https://mwparserfromhell.readthedocs.io/
No puede seleccionar más de 25 temas Los temas deben comenzar con una letra o número, pueden incluir guiones ('-') y pueden tener hasta 35 caracteres de largo.
 
 
 
 

107 líneas
3.8 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. import htmlentitydefs
  23. from . import Node
  24. __all__ = ["HTMLEntity"]
  25. class HTMLEntity(Node):
  26. def __init__(self, value, named=None, hexadecimal=False, hex_char="x"):
  27. self._value = value
  28. if named is None: # Try to guess whether or not the entity is named
  29. try:
  30. int(value)
  31. self._named = False
  32. self._hexadecimal = False
  33. except ValueError:
  34. try:
  35. int(value, 16)
  36. self._named = False
  37. self._hexadecimal = True
  38. except ValueError:
  39. self._named = True
  40. self._hexadecimal = False
  41. else:
  42. self._named = named
  43. self._hexadecimal = hexadecimal
  44. self._hex_char = hex_char
  45. def __unicode__(self):
  46. if self.named:
  47. return u"&{0};".format(self.value)
  48. if self.hexadecimal:
  49. return u"&#{0}{1};".format(self.hex_char, self.value)
  50. return u"&#{0};".format(self.value)
  51. def __strip__(self, normalize, collapse):
  52. if normalize:
  53. return self.normalize()
  54. return self
  55. def _unichr(self, value):
  56. """Implement the builtin unichr() with support for non-BMP code points.
  57. On wide Python builds, this functions like the normal unichr(). On
  58. narrow builds, this returns the value's corresponding surrogate pair.
  59. """
  60. try:
  61. return unichr(value)
  62. except ValueError:
  63. # Test whether we're on the wide or narrow Python build. Check the
  64. # length of a non-BMP code point (U+1F64A, SPEAK-NO-EVIL MONKEY):
  65. if len(u"\U0001F64A") == 2:
  66. # Ensure this is within the range we can encode:
  67. if value > 0x10FFFF:
  68. raise ValueError("unichr() arg not in range(0x110000)")
  69. code = value - 0x10000
  70. if value < 0: # Invalid code point
  71. raise
  72. lead = 0xD800 + (code >> 10)
  73. trail = 0xDC00 + (code % (1 << 10))
  74. return unichr(lead) + unichr(trail)
  75. raise
  76. @property
  77. def value(self):
  78. return self._value
  79. @property
  80. def named(self):
  81. return self._named
  82. @property
  83. def hexadecimal(self):
  84. return self._hexadecimal
  85. @property
  86. def hex_char(self):
  87. return self._hex_char
  88. def normalize(self):
  89. if self.named:
  90. return unichr(htmlentitydefs.name2codepoint[self.value])
  91. if self.hexadecimal:
  92. return self._unichr(int(self.value, 16))
  93. return self._unichr(int(self.value))