[thirdparty/gcc.git] / gcc / ada / s-wchcnv.ads

------------------------------------------------------------------------------
--                                                                          --
--                         GNAT RUN-TIME COMPONENTS                         --
--                                                                          --
--                       S Y S T E M . W C H _ C N V                        --
--                                                                          --
--                                 S p e c                                  --
--                                                                          --
--          Copyright (C) 1992-2009, Free Software Foundation, Inc.         --
--                                                                          --
-- GNAT is free software;  you can  redistribute it  and/or modify it under --
-- terms of the  GNU General Public License as published  by the Free Soft- --
-- ware  Foundation;  either version 3,  or (at your option) any later ver- --
-- sion.  GNAT is distributed in the hope that it will be useful, but WITH- --
-- OUT ANY WARRANTY;  without even the  implied warranty of MERCHANTABILITY --
-- or FITNESS FOR A PARTICULAR PURPOSE.                                     --
--                                                                          --
-- As a special exception under Section 7 of GPL version 3, you are granted --
-- additional permissions described in the GCC Runtime Library Exception,   --
-- version 3.1, as published by the Free Software Foundation.               --
--                                                                          --
-- You should have received a copy of the GNU General Public License and    --
-- a copy of the GCC Runtime Library Exception along with this program;     --
-- see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see    --
-- <http://www.gnu.org/licenses/>.                                          --
--                                                                          --
-- GNAT was originally developed  by the GNAT team at  New York University. --
-- Extensive contributions were provided by Ada Core Technologies Inc.      --
--                                                                          --
------------------------------------------------------------------------------

--  This package contains generic subprograms used for converting between
--  sequences of Character and Wide_Character. Wide_Wide_Character values
--  are also handled, but represented using integer range types defined in
--  this package, so that this package can be used from applications that
--  are restricted to Ada 95 compatibility (such as the compiler itself).

--  All the algorithms for encoding and decoding are isolated in this package
--  and in System.WCh_JIS and should not be duplicated elsewhere. The only
--  exception to this is that GNAT.Decode_String and GNAT.Encode_String have
--  their own circuits for UTF-8 conversions, for improved efficiency.

--  This unit may be used directly from an application program by providing
--  an appropriate WITH, and the interface can be expected to remain stable.

pragma Warnings (Off);
pragma Compiler_Unit;
pragma Warnings (On);

with System.WCh_Con;

package System.WCh_Cnv is
   pragma Pure;

   type UTF_32_Code is range 0 .. 16#7FFF_FFFF#;
   for UTF_32_Code'Size use 32;
   --  Range of allowed UTF-32 encoding values

   type UTF_32_String is array (Positive range <>) of UTF_32_Code;

   generic
      with function In_Char return Character;
   function Char_Sequence_To_Wide_Char
     (C  : Character;
      EM : System.WCh_Con.WC_Encoding_Method) return Wide_Character;
   --  C is the first character of a sequence of one or more characters which
   --  represent a wide character sequence. Calling the function In_Char for
   --  additional characters as required, Char_To_Wide_Char returns the
   --  corresponding wide character value. Constraint_Error is raised if the
   --  sequence of characters encountered is not a valid wide character
   --  sequence for the given encoding method.
   --
   --  Note on the use of brackets encoding (WCEM_Brackets). The brackets
   --  encoding method is ambiguous in the context of this function, since
   --  there is no way to tell if ["1234"] is eight unencoded characters or
   --  one encoded character. In the context of Ada sources, any sequence
   --  starting [" must be the start of an encoding (since that sequence is
   --  not valid in Ada source otherwise). The routines in this package use
   --  the same approach. If the input string contains the sequence [" then
   --  this is assumed to be the start of a brackets encoding sequence, and
   --  if it does not match the syntax, an error is raised.

   generic
      with function In_Char return Character;
   function Char_Sequence_To_UTF_32
     (C  : Character;
      EM : System.WCh_Con.WC_Encoding_Method) return UTF_32_Code;
   --  This is similar to the above, but the function returns a code from
   --  the full UTF_32 code set, which covers the full range of possible
   --  values in Wide_Wide_Character. The result can be converted to
   --  Wide_Wide_Character form using Wide_Wide_Character'Val.

   generic
      with procedure Out_Char (C : Character);
   procedure Wide_Char_To_Char_Sequence
     (WC : Wide_Character;
      EM : System.WCh_Con.WC_Encoding_Method);
   --  Given a wide character, converts it into a sequence of one or
   --  more characters, calling the given Out_Char procedure for each.
   --  Constraint_Error is raised if the given wide character value is
   --  not a valid value for the given encoding method.
   --
   --  Note on brackets encoding (WCEM_Brackets). For the input routines above,
   --  upper half characters can be represented as ["hh"] but this procedure
   --  will only use brackets encodings for codes higher than 16#FF#, so upper
   --  half characters will be output as single Character values.

   generic
      with procedure Out_Char (C : Character);
   procedure UTF_32_To_Char_Sequence
     (Val : UTF_32_Code;
      EM  : System.WCh_Con.WC_Encoding_Method);
   --  This is similar to the above, but the input value is a code from the
   --  full UTF_32 code set, which covers the full range of possible values
   --  in Wide_Wide_Character. To convert a Wide_Wide_Character value, the
   --  caller can use Wide_Wide_Character'Pos in the call.

end System.WCh_Cnv;
Commit	Line	Data
cacbc350 RK	1	------------------------------------------------------------------------------
cacbc350 RK	2	-- --
3084fecd	3	-- GNAT RUN-TIME COMPONENTS --
cacbc350 RK	4	-- --
	5	-- S Y S T E M . W C H _ C N V --
	6	-- --
	7	-- S p e c --
	8	-- --
748086b7	9	-- Copyright (C) 1992-2009, Free Software Foundation, Inc. --
cacbc350 RK	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- --
748086b7	13	-- ware Foundation; either version 3, or (at your option) any later ver- --
cacbc350 RK	14	-- sion. GNAT is distributed in the hope that it will be useful, but WITH- --
cacbc350 RK	15	-- OUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY --
748086b7 JJ	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/>. --
cacbc350 RK	26	-- --
cacbc350 RK	27	-- GNAT was originally developed by the GNAT team at New York University. --
71ff80dc	28	-- Extensive contributions were provided by Ada Core Technologies Inc. --
cacbc350 RK	29	-- --
	30	------------------------------------------------------------------------------
	31
2d9ea47f	32	-- This package contains generic subprograms used for converting between
c80d4855 RD	33	-- sequences of Character and Wide_Character. Wide_Wide_Character values
	34	-- are also handled, but represented using integer range types defined in
	35	-- this package, so that this package can be used from applications that
	36	-- are restricted to Ada 95 compatibility (such as the compiler itself).
	37
	38	-- All the algorithms for encoding and decoding are isolated in this package
	39	-- and in System.WCh_JIS and should not be duplicated elsewhere. The only
	40	-- exception to this is that GNAT.Decode_String and GNAT.Encode_String have
	41	-- their own circuits for UTF-8 conversions, for improved efficiency.
2d9ea47f	42
fbf5a39b AC	43	-- This unit may be used directly from an application program by providing
	44	-- an appropriate WITH, and the interface can be expected to remain stable.
	45
2d9ea47f RD	46	pragma Warnings (Off);
	47	pragma Compiler_Unit;
	48	pragma Warnings (On);
	49
cacbc350 RK	50	with System.WCh_Con;
	51
	52	package System.WCh_Cnv is
009186e0	53	pragma Pure;
82c80734 RD	54
	55	type UTF_32_Code is range 0 .. 16#7FFF_FFFF#;
	56	for UTF_32_Code'Size use 32;
	57	-- Range of allowed UTF-32 encoding values
cacbc350	58
c80d4855 RD	59	type UTF_32_String is array (Positive range <>) of UTF_32_Code;
c80d4855 RD	60
cacbc350 RK	61	generic
	62	with function In_Char return Character;
	63	function Char_Sequence_To_Wide_Char
82c80734 RD	64	(C : Character;
82c80734 RD	65	EM : System.WCh_Con.WC_Encoding_Method) return Wide_Character;
cacbc350 RK	66	-- C is the first character of a sequence of one or more characters which
	67	-- represent a wide character sequence. Calling the function In_Char for
	68	-- additional characters as required, Char_To_Wide_Char returns the
	69	-- corresponding wide character value. Constraint_Error is raised if the
	70	-- sequence of characters encountered is not a valid wide character
	71	-- sequence for the given encoding method.
c80d4855 RD	72	--
	73	-- Note on the use of brackets encoding (WCEM_Brackets). The brackets
	74	-- encoding method is ambiguous in the context of this function, since
	75	-- there is no way to tell if ["1234"] is eight unencoded characters or
	76	-- one encoded character. In the context of Ada sources, any sequence
	77	-- starting [" must be the start of an encoding (since that sequence is
	78	-- not valid in Ada source otherwise). The routines in this package use
	79	-- the same approach. If the input string contains the sequence [" then
	80	-- this is assumed to be the start of a brackets encoding sequence, and
	81	-- if it does not match the syntax, an error is raised.
cacbc350	82
82c80734 RD	83	generic
	84	with function In_Char return Character;
	85	function Char_Sequence_To_UTF_32
	86	(C : Character;
	87	EM : System.WCh_Con.WC_Encoding_Method) return UTF_32_Code;
	88	-- This is similar to the above, but the function returns a code from
	89	-- the full UTF_32 code set, which covers the full range of possible
	90	-- values in Wide_Wide_Character. The result can be converted to
	91	-- Wide_Wide_Character form using Wide_Wide_Character'Val.
	92
cacbc350 RK	93	generic
	94	with procedure Out_Char (C : Character);
	95	procedure Wide_Char_To_Char_Sequence
	96	(WC : Wide_Character;
	97	EM : System.WCh_Con.WC_Encoding_Method);
	98	-- Given a wide character, converts it into a sequence of one or
	99	-- more characters, calling the given Out_Char procedure for each.
	100	-- Constraint_Error is raised if the given wide character value is
	101	-- not a valid value for the given encoding method.
c80d4855 RD	102	--
	103	-- Note on brackets encoding (WCEM_Brackets). For the input routines above,
	104	-- upper half characters can be represented as ["hh"] but this procedure
	105	-- will only use brackets encodings for codes higher than 16#FF#, so upper
	106	-- half characters will be output as single Character values.
cacbc350	107
82c80734 RD	108	generic
	109	with procedure Out_Char (C : Character);
	110	procedure UTF_32_To_Char_Sequence
	111	(Val : UTF_32_Code;
	112	EM : System.WCh_Con.WC_Encoding_Method);
	113	-- This is similar to the above, but the input value is a code from the
	114	-- full UTF_32 code set, which covers the full range of possible values
	115	-- in Wide_Wide_Character. To convert a Wide_Wide_Character value, the
	116	-- caller can use Wide_Wide_Character'Pos in the call.
	117
cacbc350	118	end System.WCh_Cnv;