gcc/ada/a-zchuni.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT RUN-TIME COMPONENTS                         --
   4 --                                                                          --
   5 --    A D A . W I D E _ W I D E _ C H A R A C T E R T S . U N I C O D E    --
   6 --                                                                          --
   7 --                                 S p e c                                  --
   8 --                                                                          --
   9 --          Copyright (C) 2005-2009, Free Software Foundation, Inc.         --
  10 --                                                                          --
  11 -- GNAT is free software;  you can  redistribute it  and/or modify it under --
  12 -- terms of the  GNU General Public License as published  by the Free Soft- --
  13 -- ware  Foundation;  either version 3,  or (at your option) any later ver- --
  14 -- sion.  GNAT is distributed in the hope that it will be useful, but WITH- --
  15 -- OUT ANY WARRANTY;  without even the  implied warranty of MERCHANTABILITY --
  16 -- or FITNESS FOR A PARTICULAR PURPOSE.                                     --
  17 --                                                                          --
  18 -- As a special exception under Section 7 of GPL version 3, you are granted --
  19 -- additional permissions described in the GCC Runtime Library Exception,   --
  20 -- version 3.1, as published by the Free Software Foundation.               --
  21 --                                                                          --
  22 -- You should have received a copy of the GNU General Public License and    --
  23 -- a copy of the GCC Runtime Library Exception along with this program;     --
  24 -- see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see    --
  25 -- <http://www.gnu.org/licenses/>.                                          --
  26 --                                                                          --
  27 -- GNAT was originally developed  by the GNAT team at  New York University. --
  28 -- Extensive contributions were provided by Ada Core Technologies Inc.      --
  29 --                                                                          --
  30 ------------------------------------------------------------------------------
  31
  32 --  Unicode categorization routines for Wide_Wide_Character
  33
  34 with System.UTF_32;
  35
  36 package Ada.Wide_Wide_Characters.Unicode is
  37
  38    --  The following type defines the categories from the unicode definitions.
  39    --  The one addition we make is Fe, which represents the characters FFFE
  40    --  and FFFF in any of the planes.
  41
  42    type Category is new System.UTF_32.Category;
  43    --  Cc   Other, Control
  44    --  Cf   Other, Format
  45    --  Cn   Other, Not Assigned
  46    --  Co   Other, Private Use
  47    --  Cs   Other, Surrogate
  48    --  Ll   Letter, Lowercase
  49    --  Lm   Letter, Modifier
  50    --  Lo   Letter, Other
  51    --  Lt   Letter, Titlecase
  52    --  Lu   Letter, Uppercase
  53    --  Mc   Mark, Spacing Combining
  54    --  Me   Mark, Enclosing
  55    --  Mn   Mark, Nonspacing
  56    --  Nd   Number, Decimal Digit
  57    --  Nl   Number, Letter
  58    --  No   Number, Other
  59    --  Pc   Punctuation, Connector
  60    --  Pd   Punctuation, Dash
  61    --  Pe   Punctuation, Close
  62    --  Pf   Punctuation, Final quote
  63    --  Pi   Punctuation, Initial quote
  64    --  Po   Punctuation, Other
  65    --  Ps   Punctuation, Open
  66    --  Sc   Symbol, Currency
  67    --  Sk   Symbol, Modifier
  68    --  Sm   Symbol, Math
  69    --  So   Symbol, Other
  70    --  Zl   Separator, Line
  71    --  Zp   Separator, Paragraph
  72    --  Zs   Separator, Space
  73    --  Fe   relative position FFFE/FFFF in plane
  74
  75    function Get_Category (U : Wide_Wide_Character) return Category;
  76    pragma Inline (Get_Category);
  77    --  Given a Wide_Wide_Character, returns corresponding Category, or Cn if
  78    --  the code does not have an assigned unicode category.
  79
  80    --  The following functions perform category tests corresponding to lexical
  81    --  classes defined in the Ada standard. There are two interfaces for each
  82    --  function. The second takes a Category (e.g. returned by Get_Category).
  83    --  The first takes a Wide_Wide_Character. The form taking the
  84    --  Wide_Wide_Character is typically more efficient than calling
  85    --  Get_Category, but if several different tests are to be performed on the
  86    --  same code, it is more efficient to use Get_Category to get the category,
  87    --  then test the resulting category.
  88
  89    function Is_Letter (U : Wide_Wide_Character) return Boolean;
  90    function Is_Letter (C : Category)            return Boolean;
  91    pragma Inline (Is_Letter);
  92    --  Returns true iff U is a letter that can be used to start an identifier,
  93    --  or if C is one of the corresponding categories, which are the following:
  94    --    Letter, Uppercase (Lu)
  95    --    Letter, Lowercase (Ll)
  96    --    Letter, Titlecase (Lt)
  97    --    Letter, Modifier  (Lm)
  98    --    Letter, Other     (Lo)
  99    --    Number, Letter    (Nl)
 100
 101    function Is_Digit (U : Wide_Wide_Character) return Boolean;
 102    function Is_Digit (C : Category)            return Boolean;
 103    pragma Inline (Is_Digit);
 104    --  Returns true iff U is a digit that can be used to extend an identifer,
 105    --  or if C is one of the corresponding categories, which are the following:
 106    --    Number, Decimal_Digit (Nd)
 107
 108    function Is_Line_Terminator (U : Wide_Wide_Character) return Boolean;
 109    pragma Inline (Is_Line_Terminator);
 110    --  Returns true iff U is an allowed line terminator for source programs,
 111    --  if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
 112    --  Line), or if U is a conventional line terminator (CR, LF, VT, FF).
 113    --  There is no category version for this function, since the set of
 114    --  characters does not correspond to a set of Unicode categories.
 115
 116    function Is_Mark (U : Wide_Wide_Character) return Boolean;
 117    function Is_Mark (C : Category)            return Boolean;
 118    pragma Inline (Is_Mark);
 119    --  Returns true iff U is a mark character which can be used to extend an
 120    --  identifier, or if C is one of the corresponding categories, which are
 121    --  the following:
 122    --    Mark, Non-Spacing (Mn)
 123    --    Mark, Spacing Combining (Mc)
 124
 125    function Is_Other (U : Wide_Wide_Character) return Boolean;
 126    function Is_Other (C : Category)            return Boolean;
 127    pragma Inline (Is_Other);
 128    --  Returns true iff U is an other format character, which means that it
 129    --  can be used to extend an identifier, but is ignored for the purposes of
 130    --  matching of identiers, or if C is one of the corresponding categories,
 131    --  which are the following:
 132    --    Other, Format (Cf)
 133
 134    function Is_Punctuation (U : Wide_Wide_Character) return Boolean;
 135    function Is_Punctuation (C : Category)            return Boolean;
 136    pragma Inline (Is_Punctuation);
 137    --  Returns true iff U is a punctuation character that can be used to
 138    --  separate pices of an identifier, or if C is one of the corresponding
 139    --  categories, which are the following:
 140    --    Punctuation, Connector (Pc)
 141
 142    function Is_Space (U : Wide_Wide_Character) return Boolean;
 143    function Is_Space (C : Category)            return Boolean;
 144    pragma Inline (Is_Space);
 145    --  Returns true iff U is considered a space to be ignored, or if C is one
 146    --  of the corresponding categories, which are the following:
 147    --    Separator, Space (Zs)
 148
 149    function Is_Non_Graphic (U : Wide_Wide_Character) return Boolean;
 150    function Is_Non_Graphic (C : Category)            return Boolean;
 151    pragma Inline (Is_Non_Graphic);
 152    --  Returns true iff U is considered to be a non-graphic character, or if C
 153    --  is one of the corresponding categories, which are the following:
 154    --    Other, Control (Cc)
 155    --    Other, Private Use (Co)
 156    --    Other, Surrogate (Cs)
 157    --    Separator, Line (Zl)
 158    --    Separator, Paragraph (Zp)
 159    --    FFFE or FFFF positions in any plane (Fe)
 160    --
 161    --  Note that the Ada category format effector is subsumed by the above
 162    --  list of Unicode categories.
 163    --
 164    --  Note that Other, Unassiged (Cn) is quite deliberately not included
 165    --  in the list of categories above. This means that should any of these
 166    --  code positions be defined in future with graphic characters they will
 167    --  be allowed without a need to change implementations or the standard.
 168    --
 169    --  Note that Other, Format (Cf) is also quite deliberately not included
 170    --  in the list of categories above. This means that these characters can
 171    --  be included in character and string literals.
 172
 173    --  The following function is used to fold to upper case, as required by
 174    --  the Ada 2005 standard rules for identifier case folding. Two
 175    --  identifiers are equivalent if they are identical after folding all
 176    --  letters to upper case using this routine.
 177
 178    function To_Upper_Case
 179      (U : Wide_Wide_Character) return Wide_Wide_Character;
 180    pragma Inline (To_Upper_Case);
 181    --  If U represents a lower case letter, returns the corresponding upper
 182    --  case letter, otherwise U is returned unchanged. The folding is locale
 183    --  independent as defined by documents referenced in the note in section
 184    --  1 of ISO/IEC 10646:2003
 185
 186 end Ada.Wide_Wide_Characters.Unicode;