Merge -r 127928:132243 from trunk
[official-gcc.git] / gcc / ada / s-wchcnv.ads
blob3679b881a567d6497f70d985ab035fe94ad583a9
1 ------------------------------------------------------------------------------
2 -- --
3 -- GNAT RUN-TIME COMPONENTS --
4 -- --
5 -- S Y S T E M . W C H _ C N V --
6 -- --
7 -- S p e c --
8 -- --
9 -- Copyright (C) 1992-2007, 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, 51 Franklin Street, Fifth Floor, --
20 -- Boston, MA 02110-1301, 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 ------------------------------------------------------------------------------
34 -- This package contains generic subprograms used for converting between
35 -- sequences of Character and Wide_Character. Wide_Wide_Character values
36 -- are also handled, but represented using integer range types defined in
37 -- this package, so that this package can be used from applications that
38 -- are restricted to Ada 95 compatibility (such as the compiler itself).
40 -- All the algorithms for encoding and decoding are isolated in this package
41 -- and in System.WCh_JIS and should not be duplicated elsewhere. The only
42 -- exception to this is that GNAT.Decode_String and GNAT.Encode_String have
43 -- their own circuits for UTF-8 conversions, for improved efficiency.
45 -- This unit may be used directly from an application program by providing
46 -- an appropriate WITH, and the interface can be expected to remain stable.
48 pragma Warnings (Off);
49 pragma Compiler_Unit;
50 pragma Warnings (On);
52 with System.WCh_Con;
54 package System.WCh_Cnv is
55 pragma Pure;
57 type UTF_32_Code is range 0 .. 16#7FFF_FFFF#;
58 for UTF_32_Code'Size use 32;
59 -- Range of allowed UTF-32 encoding values
61 type UTF_32_String is array (Positive range <>) of UTF_32_Code;
63 generic
64 with function In_Char return Character;
65 function Char_Sequence_To_Wide_Char
66 (C : Character;
67 EM : System.WCh_Con.WC_Encoding_Method) return Wide_Character;
68 -- C is the first character of a sequence of one or more characters which
69 -- represent a wide character sequence. Calling the function In_Char for
70 -- additional characters as required, Char_To_Wide_Char returns the
71 -- corresponding wide character value. Constraint_Error is raised if the
72 -- sequence of characters encountered is not a valid wide character
73 -- sequence for the given encoding method.
75 -- Note on the use of brackets encoding (WCEM_Brackets). The brackets
76 -- encoding method is ambiguous in the context of this function, since
77 -- there is no way to tell if ["1234"] is eight unencoded characters or
78 -- one encoded character. In the context of Ada sources, any sequence
79 -- starting [" must be the start of an encoding (since that sequence is
80 -- not valid in Ada source otherwise). The routines in this package use
81 -- the same approach. If the input string contains the sequence [" then
82 -- this is assumed to be the start of a brackets encoding sequence, and
83 -- if it does not match the syntax, an error is raised.
85 generic
86 with function In_Char return Character;
87 function Char_Sequence_To_UTF_32
88 (C : Character;
89 EM : System.WCh_Con.WC_Encoding_Method) return UTF_32_Code;
90 -- This is similar to the above, but the function returns a code from
91 -- the full UTF_32 code set, which covers the full range of possible
92 -- values in Wide_Wide_Character. The result can be converted to
93 -- Wide_Wide_Character form using Wide_Wide_Character'Val.
95 generic
96 with procedure Out_Char (C : Character);
97 procedure Wide_Char_To_Char_Sequence
98 (WC : Wide_Character;
99 EM : System.WCh_Con.WC_Encoding_Method);
100 -- Given a wide character, converts it into a sequence of one or
101 -- more characters, calling the given Out_Char procedure for each.
102 -- Constraint_Error is raised if the given wide character value is
103 -- not a valid value for the given encoding method.
105 -- Note on brackets encoding (WCEM_Brackets). For the input routines above,
106 -- upper half characters can be represented as ["hh"] but this procedure
107 -- will only use brackets encodings for codes higher than 16#FF#, so upper
108 -- half characters will be output as single Character values.
110 generic
111 with procedure Out_Char (C : Character);
112 procedure UTF_32_To_Char_Sequence
113 (Val : UTF_32_Code;
114 EM : System.WCh_Con.WC_Encoding_Method);
115 -- This is similar to the above, but the input value is a code from the
116 -- full UTF_32 code set, which covers the full range of possible values
117 -- in Wide_Wide_Character. To convert a Wide_Wide_Character value, the
118 -- caller can use Wide_Wide_Character'Pos in the call.
120 end System.WCh_Cnv;