[Sommaire] [Imprimer]

   1  # Transformation formats
   2  # CF = CF...           : Map from one char to one or more chars  (map)
   3  # CF - CF = CF...      : Map range of chars to one or more chars (replace)
   4  # CF - CF +- xx        : Transpose several chars by value xx     (transpose)
   5  # CF - CF % yy +- xx   : Transpose several chars by value xx, yy denotes skip value
   6  #                        yy equal to 1 is the same as 'transpose' (transpose-modulo)
   7  # TI[,TI...]           :
   8  #
   9  # CF = Character Format
  10  # TI = Transform Identifier
  11  #
  12  # Character formats:
  13  # U+xxxx : Unicode value in hexadecimal
  14  # xx: Ascii value in hexadecimal
  15  # remove : Remove character from result, can only be used in destination
  16  # keep : Keep character as it is, can only be used in destination
  17  # "xxxx" : Multiple characters as a string, can only be used in destination, \\ means \ and \" means "
  18  #
  19  #
  20  #
  21  
  22  space_normalize:
  23  U+202F = U+00A0 # Narrow no-break space => No-break space
  24  U+FEFF = U+00A0 # Zero width no-break space => No-break space
  25  U+00A0 = U+0020 # Turn non-breaking-space into normal space
  26  #U+00BC - U+00B = U+0020 # test of parser error detection
  27  #U+0041 - U+005G + 20 # test of parser error detection
  28  
  29  hyphen_normalize:
  30  U+007E = U+002D # tilde/swung dash into hyphen-minus
  31  U+00AD = remove # Soft hyphens are only meant for helping with wordbreaking
  32  
  33  apostrophe_normalize:
  34  # Turn special accents into apostrophe which is defined in ASCII
  35  U+0060 = U+0027 # Grave accent
  36  U+00B4 = U+0027 # Acute accent
  37  U+02CA = U+0027 # Modified letter acute accent
  38  U+02CB = U+0027 # Modified letter grave accent
  39  U+02CF = U+0027 # Modified letter low acute accent
  40  U+02CE = U+0027 # Modified letter low grave accent
  41  
  42  doublequote_normalize:
  43  # Turns fancy double quote into ASCII double quote
  44  U+00AB = U+0022 # left-pointing double angle quotation mark
  45  U+00BB = U+0022 # right-pointing double angle quotation mark
  46  U+02DD = U+0027 # double accute accent
  47  
  48  apostrophe_to_doublequote:
  49  # Turns apostrophe into doublequote
  50  U+0027 = U+0022
  51  
  52  special_decompose:
  53  U+00A9 = "(C)" # Copyright sign
  54  U+00AE = "(R)" # Registered sign
  55  U+00B1 = "+-"  # Plus/minus sign
  56  U+00B2 = "2"   # Superscript two
  57  U+00B3 = "3"   # Superscript three
  58  U+00B9 = "1"   # Superscript one
  59  U+00BA = "1"   # Superscript one
  60  U+00BC = "1/4"   # Vulgar fraction one quarter
  61  U+00BD = "1/2"   # Vulgar fraction one half
  62  U+00BE = "3/4"   # Vulgar fraction three quarter
  63