gcc/ada/csets.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT COMPILER COMPONENTS                         --
   4 --                                                                          --
   5 --                                C S E T S                                 --
   6 --                                                                          --
   7 --                                 S p e c                                  --
   8 --                                                                          --
   9 --          Copyright (C) 1992-2024, 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.  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 COPYING3.  If not, go to --
  19 -- http://www.gnu.org/licenses for a complete copy of the license.          --
  20 --                                                                          --
  21 -- GNAT was originally developed  by the GNAT team at  New York University. --
  22 -- Extensive contributions were provided by Ada Core Technologies Inc.      --
  23 --                                                                          --
  24 ------------------------------------------------------------------------------
  25
  26 package Csets is
  27    pragma Elaborate_Body;
  28
  29    --  This package contains character tables for the various character
  30    --  sets that are supported for source representation. Character and
  31    --  string literals are not affected, only identifiers. For each set,
  32    --  the table in this package gives the mapping of letters to their
  33    --  upper case equivalent. Each table thus provides the information
  34    --  for building the table used to fold lower case to upper case, and
  35    --  also the table of flags showing which characters are allowed in
  36    --  identifiers.
  37
  38    type Translate_Table is array (Character) of Character;
  39    --  Type used to describe translate tables
  40
  41    type Char_Array_Flags is array (Character) of Boolean;
  42    --  Type used for character attribute arrays. Note that we deliberately
  43    --  do NOT pack this table, since we don't want the extra overhead of
  44    --  accessing a packed bit string.
  45
  46    ----------------------------------------------
  47    -- Character Tables For Current Compilation --
  48    ----------------------------------------------
  49
  50    procedure Initialize;
  51    --  Routine to initialize following character tables, whose content depends
  52    --  on the character code being used to represent the source program. In
  53    --  particular, the use of the upper half of the 8-bit code set varies.
  54    --  The character set in use is specified by the value stored in
  55    --  Opt.Identifier_Character_Set, which has the following settings:
  56
  57    --    '1'  Latin-1  (ISO-8859-1)
  58    --    '2'  Latin-2  (ISO-8859-2)
  59    --    '3'  Latin-3  (ISO-8859-3)
  60    --    '4'  Latin-4  (ISO-8859-4)
  61    --    '5'  Cyrillic (ISO-8859-5)
  62    --    'p'  IBM PC   (code page 437)
  63    --    '8'  IBM PC   (code page 850)
  64    --    '9'  Latin-9  (ISO-8859-15)
  65    --    'f'  Full upper set (all distinct)
  66    --    'n'  No upper characters (Ada/83 rules)
  67    --    'w'  Latin-1 plus wide characters also allowed
  68
  69    function Is_Upper_Case_Letter (C : Character) return Boolean;
  70    pragma Inline (Is_Upper_Case_Letter);
  71    --  Determine if character is upper case letter
  72
  73    function Is_Lower_Case_Letter (C : Character) return Boolean;
  74    pragma Inline (Is_Lower_Case_Letter);
  75    --  Determine if character is lower case letter
  76
  77    Fold_Upper : Translate_Table;
  78    --  Table to fold lower case identifier letters to upper case
  79
  80    Fold_Lower : Translate_Table;
  81    --  Table to fold upper case identifier letters to lower case
  82
  83    Identifier_Char : Char_Array_Flags;
  84    --  This table has True entries for all characters that can legally appear
  85    --  in identifiers, including digits, the underline character, all letters
  86    --  including upper and lower case and extended letters (as controlled by
  87    --  the setting of Opt.Identifier_Character_Set), left bracket for brackets
  88    --  notation wide characters and also ESC if wide characters are permitted
  89    --  in identifiers using escape sequences starting with ESC.
  90
  91 end Csets;