home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Geek Gadgets 1
/
ADE-1.bin
/
ade-dist
/
gnat-2.06-src.tgz
/
tar.out
/
fsf
/
gnat
/
ada
/
s-wchcon.ads
< prev
next >
Wrap
Text File
|
1996-09-28
|
8KB
|
155 lines
------------------------------------------------------------------------------
-- --
-- GNAT COMPILER COMPONENTS --
-- --
-- S Y S T E M . W C H _ C O N --
-- --
-- S p e c --
-- --
-- $Revision: 1.5 $ --
-- --
-- Copyright (c) 1992,1993,1994 NYU, All Rights Reserved --
-- --
-- The GNAT library is free software; you can redistribute it and/or modify --
-- it under terms of the GNU Library General Public License as published by --
-- the Free Software Foundation; either version 2, or (at your option) any --
-- later version. The GNAT library is distributed in the hope that it will --
-- be useful, but WITHOUT ANY WARRANTY; without even the implied warranty --
-- of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU --
-- Library General Public License for more details. You should have --
-- received a copy of the GNU Library General Public License along with --
-- the GNAT library; see the file COPYING.LIB. If not, write to the Free --
-- Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. --
-- --
------------------------------------------------------------------------------
-- This package defines the codes used to identify the encoding method for
-- wide characters in string and character constants. This is needed both
-- at compile time and at runtime (for the wide character runtime routines)
package System.WCh_Con is
pragma Pure (WCh_Con);
-------------------------------------
-- Wide_Character Encoding Methods --
-------------------------------------
-- A wide character encoding method is a method for uniquely representing
-- a Wide_Character value using a one or more Character values. Two types
-- of encoding method are supported by GNAT:
-- An escape encoding method uses ESC as the first character of the
-- sequence, and subsequent characters determine the wide character
-- value that is represented. Any character other than ESC stands
-- for itself as a single byte (i.e. any character in Latin-1, other
-- than ESC itself, is represented as a single character: itself).
-- An upper half encoding method uses a character in the upper half
-- range (i.e. in the range 16#80# .. 16#FF#) as the first byte of
-- a wide character encoding sequence. Subsequent characters are
-- used to determine the wide character value that is represented.
-- Any character in the lower half (16#00# .. 16#7F#) represents
-- itself as a single character.
-- Note that GNAT does not currently support escape-in, escape-out
-- encoding methods, where an escape sequence is used to set a mode
-- used to recognize subsequent characters. All encoding methods use
-- individual character-by-character encodings, so that a sequence of
-- wide characters is represented by a sequence of encodings.
-- To add new encoding methods, the following steps are required:
-- 1. Define a code for a new value of type WC_Encoding_Method
-- 2. Adjust the definition of WC_Encoding_Method accordingly
-- 3. Provide appropriate conversion routines in System.Wch_Cnv
-- 4. Adjust definition of WC_Longest_Sequence if necessary
-- 5. Add an entry in WC_Encoding_Letters for the new method
-- Note that the WC_Encoding_Method values must be kept ordered so that
-- the definitions of the subtypes WC_Upper_Half_Encoding_Method and
-- WC_ESC_Encoding_Method are still correct.
--------------------------------
-- Compatibility Requirements --
--------------------------------
-- When a unit is compiled with a particular option, any units that it
-- with's are compiled with the same setting. Basically this means that
-- all units in a program which contain wide character encodings must
-- use a consistent encoding method. At bind time, the binder checks
-- that all units in the program are either compiled in WCEM_None mode,
-- meaning that they have no wide character encodings, or that they are
-- compiled in a consistent mode. It is not permitted to mix two modes
-- (other than WCEM_None) in a single program.
---------------------------------
-- Encoding Method Definitions --
---------------------------------
type WC_Encoding_Method is range 0 .. 4;
-- Type covering the range of values used to represent wide character
-- encoding methods. An enumeration type might be a little neater, but
-- more trouble than it's worth, given the need to pass these values
-- from the compiler to the backend, and to record them in the ALI file.
WCEM_None : constant WC_Encoding_Method := 0;
-- No wide character encoding is permitted in the source program.
-- This is the default. A unit compiled with this option can be
-- used with units compiled with any other option.
WCEM_Hex : constant WC_Encoding_Method := 1;
-- The wide character with code 16#abcd# is represented by the
-- escape sequence ESC a b c d (five characters, where abcd are
-- ASCII hex characters, using upper case for letters). This
-- method is easy to deal with in external environments that do
-- not support wide characters, and covers the whole BMP. This
-- is the default encoding method.
WCEM_Upper : constant WC_Encoding_Method := 2;
-- The wide character with encoding 16#abcd#, where the upper bit
-- is on (i.e. a is in the range 8-F) is represented as two bytes
-- 16#ab# and 16#cd#. The second byte may never be a format control
-- character, but is not required to be in the upper half. This
-- method can be also used for shift-JIS or EUC where the internal
-- coding matches the external coding.
WCEM_Shift_JIS : constant WC_Encoding_Method := 3;
-- A wide character is represented by a two character sequence
-- 16#ab# and 16#cd#, with the restrictions described for upper
-- half encoding as described above. The internal character code
-- is the corresponding JIS character according to the standard
-- algorithm for Shift-JIS conversion. See the body of package
-- System.JIS_Conversions for further details.
WCEM_EUC : constant WC_Encoding_Method := 4;
-- A wide character is represented by a two character sequence
-- 16#ab# and 16#cd#, with both characters being in the upper half.
-- The internal character code is the corresponding JIS character
-- according to the EUC encoding algorithm. See the body of package
-- System.JIS_Conversions for further details.
WC_Encoding_Letters : constant array (WC_Encoding_Method) of Character :=
(WCEM_None => 'n',
WCEM_Hex => 'h',
WCEM_Upper => 'u',
WCEM_Shift_JIS => 's',
WCEM_EUC => 'e');
-- Letters used for selection of wide character encoding method in the
-- compiler options (-gnatj? switch) and for Wide_Text_IO (wcem parameter
-- in the form string).
subtype WC_ESC_Encoding_Method is
WC_Encoding_Method range WCEM_Hex .. WCEM_Hex;
-- Encoding methods using an ESC character at the start of the sequence.
subtype WC_Upper_Half_Encoding_Method is
WC_Encoding_Method range WCEM_Upper .. WCEM_EUC;
-- Encoding methods using an upper half character (16#80#..16#FF) at
-- the start of the sequence.
WC_Longest_Sequence : constant := 5;
-- The longest number of characters that can be used for a wide
-- character sequence for any of the active encoding methods.
end System.WCh_Con;