[Sommaire] [Imprimer]

   1  # Search normalization rules
   2  #
   3  # See basic.tr for formatting options
   4  #
   5  # The rest of search handling is done in the various larger alphabet groups
   6  # e.g latin.tr and cyrillic.tr
   7  # They will have rules called <identifier>_search_cleanup
   8  
   9  endline_search_normalize:
  10  # Turns endlines \n, \r and \r\n into a space
  11  U+000A = U+0020
  12  U+000D = U+0020
  13  
  14  tab_search_normalize:
  15  # Turns tabs \t into a space
  16  U+0008 = U+0020
  17  
  18  specialwords_search_normalize:
  19  U+00AA = "a"  # feminine ordinal indicator (spanish)
  20  U+00BA = "o"  # masculine ordinal indicator (spanish)
  21  
  22  punctuation_normalize:
  23  # Turn some symbols which are considered punctuations marks into
  24  # the ASCII punctuation U+002E
  25  U+0021 = U+002E # exclamation mark !
  26  U+003F = U+002E # question mark ?
  27  U+002C = U+002E # comma ,
  28  
  29  latin_search_decompose:
  30  U+00B1 = "+-"    # Plus/minus sign
  31  U+00B2 = "2"     # Superscript two
  32  U+00B3 = "3"     # Superscript three
  33  U+00B9 = "1"     # Superscript one
  34  U+00BA = "1"     # Superscript one
  35  U+00BC = "1/4"   # Vulgar fraction one quarter
  36  U+00BD = "1/2"   # Vulgar fraction one half
  37  U+00BE = "3/4"   # Vulgar fraction three quarter
  38