File : 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) 1992-2013, 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 -- --
19 -- --
20 -- --
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 package Csets is
33 pragma Elaborate_Body;
34
35 -- This package contains character tables for the various character
36 -- sets that are supported for source representation. Character and
37 -- string literals are not affected, only identifiers. For each set,
38 -- the table in this package gives the mapping of letters to their
39 -- upper case equivalent. Each table thus provides the information
40 -- for building the table used to fold lower case to upper case, and
41 -- also the table of flags showing which characters are allowed in
42 -- identifiers.
43
44 type Translate_Table is array (Character) of Character;
45 -- Type used to describe translate tables
46
47 type Char_Array_Flags is array (Character) of Boolean;
48 -- Type used for character attribute arrays. Note that we deliberately
49 -- do NOT pack this table, since we don't want the extra overhead of
50 -- accessing a packed bit string.
51
52 ----------------------------------------------
53 -- Character Tables For Current Compilation --
54 ----------------------------------------------
55
56 procedure Initialize;
57 -- Routine to initialize following character tables, whose content depends
58 -- on the character code being used to represent the source program. In
59 -- particular, the use of the upper half of the 8-bit code set varies.
60 -- The character set in use is specified by the value stored in
61 -- Opt.Identifier_Character_Set, which has the following settings:
62
63 -- '1' Latin-1 (ISO-8859-1)
64 -- '2' Latin-2 (ISO-8859-2)
65 -- '3' Latin-3 (ISO-8859-3)
66 -- '4' Latin-4 (ISO-8859-4)
67 -- '5' Cyrillic (ISO-8859-5)
68 -- 'p' IBM PC (code page 437)
69 -- '8' IBM PC (code page 850)
70 -- '9' Latin-9 (ISO-8859-15)
71 -- 'f' Full upper set (all distinct)
72 -- 'n' No upper characters (Ada/83 rules)
73 -- 'w' Latin-1 plus wide characters also allowed
74
75 function Is_Upper_Case_Letter (C : Character) return Boolean;
76 pragma Inline (Is_Upper_Case_Letter);
77 -- Determine if character is upper case letter
78
79 function Is_Lower_Case_Letter (C : Character) return Boolean;
80 pragma Inline (Is_Lower_Case_Letter);
81 -- Determine if character is lower case letter
82
83 Fold_Upper : Translate_Table;
84 -- Table to fold lower case identifier letters to upper case
85
86 Fold_Lower : Translate_Table;
87 -- Table to fold upper case identifier letters to lower case
88
89 Identifier_Char : Char_Array_Flags;
90 -- This table has True entries for all characters that can legally appear
91 -- in identifiers, including digits, the underline character, all letters
92 -- including upper and lower case and extended letters (as controlled by
93 -- the setting of Opt.Identifier_Character_Set), left bracket for brackets
94 -- notation wide characters and also ESC if wide characters are permitted
95 -- in identifiers using escape sequences starting with ESC.
96
97 end Csets;