2013-05-03 Richard Biener <rguenther@suse.de>
[official-gcc.git] / gcc / ada / g-decstr.ads
blobe4d7b7f16334de42a54642165dd44aba0a44af3b
1 ------------------------------------------------------------------------------
2 -- --
3 -- GNAT RUN-TIME COMPONENTS --
4 -- --
5 -- G N A T . D E C O D E _ S T R I N G --
6 -- --
7 -- S p e c --
8 -- --
9 -- Copyright (C) 2007-2010, AdaCore --
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 -- 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/>. --
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 ------------------------------------------------------------------------------
32 -- This generic package provides utility routines for converting from an
33 -- encoded string to a corresponding Wide_String or Wide_Wide_String value
34 -- using a specified encoding convention, which is supplied as the generic
35 -- parameter. UTF-8 is handled especially efficiently, and if the encoding
36 -- method is known at compile time to be WCEM_UTF8, then the instantiation
37 -- is specialized to handle only the UTF-8 case and exclude code for the
38 -- other encoding methods. The package also provides positioning routines
39 -- for skipping encoded characters in either direction, and for validating
40 -- strings for correct encodings.
42 -- Note: this package is only about decoding sequences of 8-bit characters
43 -- into corresponding 16-bit Wide_String or 32-bit Wide_Wide_String values.
44 -- It knows nothing at all about the character encodings being used for the
45 -- resulting Wide_Character and Wide_Wide_Character values. Most often this
46 -- will be Unicode/ISO-10646 as specified by the Ada RM, but this package
47 -- does not make any assumptions about the character coding. See also the
48 -- packages Ada.Wide_[Wide_]Characters.Unicode for unicode specific functions.
50 -- Note on the use of brackets encoding (WCEM_Brackets). The brackets encoding
51 -- method is ambiguous in the context of this package, since there is no way
52 -- to tell if ["1234"] is eight unencoded characters or one encoded character.
53 -- In the context of Ada sources, any sequence starting [" must be the start
54 -- of an encoding (since that sequence is not valid in Ada source otherwise).
55 -- The routines in this package use the same approach. If the input string
56 -- contains the sequence [" then this is assumed to be the start of a brackets
57 -- encoding sequence, and if it does not match the syntax, an error is raised.
58 -- In the case of the Prev functions, a sequence ending with "] is assumed to
59 -- be a valid brackets sequence, and an error is raised if it is not.
61 with System.WCh_Con;
63 generic
64 Encoding_Method : System.WCh_Con.WC_Encoding_Method;
66 package GNAT.Decode_String is
67 pragma Pure;
69 function Decode_Wide_String (S : String) return Wide_String;
70 pragma Inline (Decode_Wide_String);
71 -- Decode the given String, which is encoded using the indicated coding
72 -- method, returning the corresponding decoded Wide_String value. If S
73 -- contains a character code that cannot be represented with the given
74 -- encoding, then Constraint_Error is raised.
76 procedure Decode_Wide_String
77 (S : String;
78 Result : out Wide_String;
79 Length : out Natural);
80 -- Similar to the above function except that the result is stored in the
81 -- given Wide_String variable Result, starting at Result (Result'First). On
82 -- return, Length is set to the number of characters stored in Result. The
83 -- caller must ensure that Result is long enough (an easy choice is to set
84 -- the length equal to the S'Length, since decoding can never increase the
85 -- string length). If the length of Result is insufficient Constraint_Error
86 -- will be raised.
88 function Decode_Wide_Wide_String (S : String) return Wide_Wide_String;
89 pragma Inline (Decode_Wide_Wide_String);
90 -- Same as above function but for Wide_Wide_String output
92 procedure Decode_Wide_Wide_String
93 (S : String;
94 Result : out Wide_Wide_String;
95 Length : out Natural);
96 -- Same as above procedure, but for Wide_Wide_String output
98 function Validate_Wide_String (S : String) return Boolean;
99 -- This function inspects the string S to determine if it contains only
100 -- valid encodings corresponding to Wide_Character values using the
101 -- given encoding. If a call to Decode_Wide_String (S) would return
102 -- without raising Constraint_Error, then Validate_Wide_String will
103 -- return True. If the call would have raised Constraint_Error, then
104 -- Validate_Wide_String will return False.
106 function Validate_Wide_Wide_String (S : String) return Boolean;
107 -- Similar to Validate_Wide_String, except that it succeeds if the string
108 -- contains only encodings corresponding to Wide_Wide_Character values.
110 procedure Decode_Wide_Character
111 (Input : String;
112 Ptr : in out Natural;
113 Result : out Wide_Character);
114 pragma Inline (Decode_Wide_Character);
115 -- This is a lower level procedure that decodes a single character using
116 -- the given encoding method. The encoded character is stored in Input,
117 -- starting at Input (Ptr). The resulting output character is stored in
118 -- Result, and on return Ptr is updated past the input character or
119 -- encoding sequence. Constraint_Error will be raised if the input has
120 -- has a character that cannot be represented using the given encoding,
121 -- or if Ptr is outside the bounds of the Input string.
123 procedure Decode_Wide_Wide_Character
124 (Input : String;
125 Ptr : in out Natural;
126 Result : out Wide_Wide_Character);
127 -- Same as above procedure but with Wide_Wide_Character input
129 procedure Next_Wide_Character (Input : String; Ptr : in out Natural);
130 -- This procedure examines the input string starting at Input (Ptr), and
131 -- advances Ptr past one character in the encoded string, so that on return
132 -- Ptr points to the next encoded character. Constraint_Error is raised if
133 -- an invalid encoding is encountered, or the end of the string is reached
134 -- or if Ptr is less than String'First on entry, or if the character
135 -- skipped is not a valid Wide_Character code. This call may be more
136 -- efficient than calling Decode_Wide_Character and discarding the result.
138 procedure Prev_Wide_Character (Input : String; Ptr : in out Natural);
139 -- This procedure is similar to Next_Encoded_Character except that it moves
140 -- backwards in the string, so that on return, Ptr is set to point to the
141 -- previous encoded character. Constraint_Error is raised if the start of
142 -- the string is encountered. It is valid for Ptr to be one past the end
143 -- of the string for this call (in which case on return it will point to
144 -- the last encoded character).
146 -- Note: it is not generally possible to do this function efficiently with
147 -- all encodings, the current implementation is only efficient for the case
148 -- of UTF-8 (Encoding_Method = WCEM_UTF8) and Brackets (Encoding_Method =
149 -- WCEM_Brackets). For all other encodings, we work by starting at the
150 -- beginning of the string and moving forward till Ptr is reached, which
151 -- is correct but slow.
153 procedure Next_Wide_Wide_Character (Input : String; Ptr : in out Natural);
154 -- Similar to Next_Wide_Character except that codes skipped must be valid
155 -- Wide_Wide_Character codes.
157 procedure Prev_Wide_Wide_Character (Input : String; Ptr : in out Natural);
158 -- Similar to Prev_Wide_Character except that codes skipped must be valid
159 -- Wide_Wide_Character codes.
161 end GNAT.Decode_String;