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.
 
 
 
 

125 líneas
4.7 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 __future__ import unicode_literals
  23. from . import Node
  24. from ..compat import htmlentities
  25. __all__ = ["HTMLEntity"]
  26. class HTMLEntity(Node):
  27. """Represents an HTML entity, like ``&nbsp;``, either named or unnamed."""
  28. def __init__(self, value, named=None, hexadecimal=False, hex_char="x"):
  29. super(HTMLEntity, self).__init__()
  30. self._value = value
  31. if named is None: # Try to guess whether or not the entity is named
  32. try:
  33. int(value)
  34. self._named = False
  35. self._hexadecimal = False
  36. except ValueError:
  37. try:
  38. int(value, 16)
  39. self._named = False
  40. self._hexadecimal = True
  41. except ValueError:
  42. self._named = True
  43. self._hexadecimal = False
  44. else:
  45. self._named = named
  46. self._hexadecimal = hexadecimal
  47. self._hex_char = hex_char
  48. def __unicode__(self):
  49. if self.named:
  50. return "&{0};".format(self.value)
  51. if self.hexadecimal:
  52. return "&#{0}{1};".format(self.hex_char, self.value)
  53. return "&#{0};".format(self.value)
  54. def __strip__(self, normalize, collapse):
  55. if normalize:
  56. return self.normalize()
  57. return self
  58. def _unichr(self, value):
  59. """Implement the builtin unichr() with support for non-BMP code points.
  60. On wide Python builds, this functions like the normal unichr(). On
  61. narrow builds, this returns the value's corresponding surrogate pair.
  62. """
  63. try:
  64. return unichr(value)
  65. except ValueError:
  66. # Test whether we're on the wide or narrow Python build. Check the
  67. # length of a non-BMP code point (U+1F64A, SPEAK-NO-EVIL MONKEY):
  68. if len("\U0001F64A") == 2:
  69. # Ensure this is within the range we can encode:
  70. if value > 0x10FFFF:
  71. raise ValueError("unichr() arg not in range(0x110000)")
  72. code = value - 0x10000
  73. if value < 0: # Invalid code point
  74. raise
  75. lead = 0xD800 + (code >> 10)
  76. trail = 0xDC00 + (code % (1 << 10))
  77. return unichr(lead) + unichr(trail)
  78. raise
  79. @property
  80. def value(self):
  81. """The string value of the HTML entity."""
  82. return self._value
  83. @property
  84. def named(self):
  85. """Whether the entity is a string name for a codepoint or an integer.
  86. For example, ``&Sigma;``, ``&#931;``, and ``&#x3a3;`` refer to the same
  87. character, but only the first is "named", while the others are integer
  88. representations of the codepoint.
  89. """
  90. return self._named
  91. @property
  92. def hexadecimal(self):
  93. """If unnamed, this is whether the value is hexadecimal or decimal."""
  94. return self._hexadecimal
  95. @property
  96. def hex_char(self):
  97. """If the value is hexadecimal, this is the letter denoting that.
  98. For example, the hex_char of ``"&#x1234;"`` is ``"x"``, whereas the
  99. hex_char of ``"&#X1234;"`` is ``"X"``. Lowercase and uppercase ``x``
  100. are the only values supported.
  101. """
  102. return self._hex_char
  103. def normalize(self):
  104. """Return the unicode character represented by the HTML entity."""
  105. if self.named:
  106. return unichr(htmlentities.name2codepoint[self.value])
  107. if self.hexadecimal:
  108. return self._unichr(int(self.value, 16))
  109. return self._unichr(int(self.value))