gcc/ada/g-utf_32.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT RUNTIME COMPONENTS                          --
   4 --                                                                          --
   5 --                          G N A T . U T F _ 3 2                           --
   6 --                                                                          --
   7 --                                 S p e c                                  --
   8 --                                                                          --
   9 --             Copyright (C) 2005 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 2,  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.  See the GNU General Public License --
  17 -- for  more details.  You should have  received  a copy of the GNU General --
  18 -- Public License  distributed with GNAT;  see file COPYING.  If not, write --
  19 -- to  the Free Software Foundation,  59 Temple Place - Suite 330,  Boston, --
  20 -- MA 02111-1307, USA.                                                      --
  21 --                                                                          --
  22 -- As a special exception,  if other files  instantiate  generics from this --
  23 -- unit, or you link  this unit with other files  to produce an executable, --
  24 -- this  unit  does not  by itself cause  the resulting  executable  to  be --
  25 -- covered  by the  GNU  General  Public  License.  This exception does not --
  26 -- however invalidate  any other reasons why  the executable file  might be --
  27 -- covered by the  GNU Public License.                                      --
  28 --                                                                          --
  29 -- GNAT was originally developed  by the GNAT team at  New York University. --
  30 -- Extensive contributions were provided by Ada Core Technologies Inc.      --
  31 --                                                                          --
  32 ------------------------------------------------------------------------------
  33
  34 --  This package is an internal package that provides basic character
  35 --  classification capabilities needed by the compiler for handling full
  36 --  32-bit wide wide characters. We avoid the use of the actual type
  37 --  Wide_Wide_Character, since we want to use these routines in the compiler
  38 --  itself, and we want to be able to compile the compiler with old versions
  39 --  of GNAT that did not implement Wide_Wide_Character.
  40
  41 --  This package is not available directly for use in application programs,
  42 --  but it serves as the basis for GNAT.Wide_Case_Utilities and
  43 --  GNAT.Wide_Wide_Case_Utilities, which can be used directly.
  44
  45 package GNAT.UTF_32 is
  46
  47    type UTF_32 is mod 2 ** 32;
  48    --  The actual allowed range is 16#00_0000# .. 16#01_FFFF#
  49
  50    function Is_UTF_32_Letter (U : UTF_32) return Boolean;
  51    pragma Inline (Is_UTF_32_Letter);
  52    --  Returns true iff U is a letter that can be used to start an identifier.
  53    --  This means that it is in one of the following categories:
  54    --    Letter, Uppercase (Lu)
  55    --    Letter, Lowercase (Ll)
  56    --    Letter, Titlecase (Lt)
  57    --    Letter, Modifier  (Lm)
  58    --    Letter, Other     (Lo)
  59    --    Number, Letter    (Nl)
  60
  61    function Is_UTF_32_Digit (U : UTF_32) return Boolean;
  62    pragma Inline (Is_UTF_32_Digit);
  63    --  Returns true iff U is a digit that can be used to extend an identifer,
  64    --  which means it is in one of the following categories:
  65    --    Number, Decimal_Digit (Nd)
  66
  67    function Is_UTF_32_Line_Terminator (U : UTF_32) return Boolean;
  68    pragma Inline (Is_UTF_32_Line_Terminator);
  69    --  Returns true iff U is an allowed line terminator for source programs,
  70    --  which means it is in one of the following categories:
  71    --    Separator, Line (Zl)
  72    --    Separator, Paragraph (Zp)
  73    --  or that it is a conventional line terminator (CR, LF, VT, FF)
  74
  75    function Is_UTF_32_Mark (U : UTF_32) return Boolean;
  76    pragma Inline (Is_UTF_32_Mark);
  77    --  Returns true iff U is a mark character which can be used to extend
  78    --  an identifier. This means it is in one of the following categories:
  79    --    Mark, Non-Spacing (Mn)
  80    --    Mark, Spacing Combining (Mc)
  81
  82    function Is_UTF_32_Other (U : UTF_32) return Boolean;
  83    pragma Inline (Is_UTF_32_Other);
  84    --  Returns true iff U is an other format character, which means that it
  85    --  can be used to extend an identifier, but is ignored for the purposes of
  86    --  matching of identiers. This means that it is in one of the following
  87    --  categories:
  88    --    Other, Format (Cf)
  89
  90    function Is_UTF_32_Punctuation (U : UTF_32) return Boolean;
  91    pragma Inline (Is_UTF_32_Punctuation);
  92    --  Returns true iff U is a punctuation character that can be used to
  93    --  separate pices of an identifier. This means that it is in one of the
  94    --  following categories:
  95    --    Punctuation, Connector (Pc)
  96
  97    function Is_UTF_32_Space (U : UTF_32) return Boolean;
  98    pragma Inline (Is_UTF_32_Space);
  99    --  Returns true iff U is considered a space to be ignored, which means
 100    --  that it is in one of the following categories:
 101    --    Separator, Space (Zs)
 102
 103    function Is_UTF_32_Non_Graphic (U : UTF_32) return Boolean;
 104    pragma Inline (Is_UTF_32_Non_Graphic);
 105    --  Returns true iff U is considered to be a non-graphic character,
 106    --  which means that it is in one of the following categories:
 107    --    Other, Control (Cc)
 108    --    Other, Private Use (Co)
 109    --    Other, Surrogate (Cs)
 110    --    Other, Format (Cf)
 111    --    Separator, Line (Zl)
 112    --    Separator, Paragraph (Zp)
 113    --
 114    --  Note that the Ada category format effector is subsumed by the above
 115    --  list of Unicode categories.
 116
 117    function UTF_32_To_Upper_Case (U : UTF_32) return UTF_32;
 118    pragma Inline (UTF_32_To_Upper_Case);
 119    --  If U represents a lower case letter, returns the corresponding upper
 120    --  case letter, otherwise U is returned unchanged. The folding is locale
 121    --  independent as defined by documents referenced in the note in section
 122    --  1 of ISO/IEC 10646:2003
 123
 124 end GNAT.UTF_32;