1 |
281 |
jeremybenn |
------------------------------------------------------------------------------
|
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, 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 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 |
|
|
------------------------------------------------------------------------------
|
33 |
|
|
|
34 |
|
|
-- This generic package provides utility routines for converting from an
|
35 |
|
|
-- encoded string to a corresponding Wide_String or Wide_Wide_String value
|
36 |
|
|
-- using a specified encoding convention, which is supplied as the generic
|
37 |
|
|
-- parameter. UTF-8 is handled especially efficiently, and if the encoding
|
38 |
|
|
-- method is known at compile time to be WCEM_UTF8, then the instantiation
|
39 |
|
|
-- is specialized to handle only the UTF-8 case and exclude code for the
|
40 |
|
|
-- other encoding methods. The package also provides positioning routines
|
41 |
|
|
-- for skipping encoded characters in either direction, and for validating
|
42 |
|
|
-- strings for correct encodings.
|
43 |
|
|
|
44 |
|
|
-- Note: this package is only about decoding sequences of 8-bit characters
|
45 |
|
|
-- into corresponding 16-bit Wide_String or 32-bit Wide_Wide_String values.
|
46 |
|
|
-- It knows nothing at all about the character encodings being used for the
|
47 |
|
|
-- resulting Wide_Character and Wide_Wide_Character values. Most often this
|
48 |
|
|
-- will be Unicode/ISO-10646 as specified by the Ada RM, but this package
|
49 |
|
|
-- does not make any assumptions about the character coding. See also the
|
50 |
|
|
-- packages Ada.Wide_[Wide_]Characters.Unicode for unicode specific functions.
|
51 |
|
|
|
52 |
|
|
-- Note on the use of brackets encoding (WCEM_Brackets). The brackets encoding
|
53 |
|
|
-- method is ambiguous in the context of this package, since there is no way
|
54 |
|
|
-- to tell if ["1234"] is eight unencoded characters or one encoded character.
|
55 |
|
|
-- In the context of Ada sources, any sequence starting [" must be the start
|
56 |
|
|
-- of an encoding (since that sequence is not valid in Ada source otherwise).
|
57 |
|
|
-- The routines in this package use the same approach. If the input string
|
58 |
|
|
-- contains the sequence [" then this is assumed to be the start of a brackets
|
59 |
|
|
-- encoding sequence, and if it does not match the syntax, an error is raised.
|
60 |
|
|
-- In the case of the Prev functions, a sequence ending with "] is assumed to
|
61 |
|
|
-- be a valid brackets sequence, and an error is raised if it is not.
|
62 |
|
|
|
63 |
|
|
with System.WCh_Con;
|
64 |
|
|
|
65 |
|
|
generic
|
66 |
|
|
Encoding_Method : System.WCh_Con.WC_Encoding_Method;
|
67 |
|
|
|
68 |
|
|
package GNAT.Decode_String is
|
69 |
|
|
pragma Pure;
|
70 |
|
|
|
71 |
|
|
function Decode_Wide_String (S : String) return Wide_String;
|
72 |
|
|
pragma Inline (Decode_Wide_String);
|
73 |
|
|
-- Decode the given String, which is encoded using the indicated coding
|
74 |
|
|
-- method, returning the corresponding decoded Wide_String value. If S
|
75 |
|
|
-- contains a character code that cannot be represented with the given
|
76 |
|
|
-- encoding, then Constraint_Error is raised.
|
77 |
|
|
|
78 |
|
|
procedure Decode_Wide_String
|
79 |
|
|
(S : String;
|
80 |
|
|
Result : out Wide_String;
|
81 |
|
|
Length : out Natural);
|
82 |
|
|
-- Similar to the above function except that the result is stored in the
|
83 |
|
|
-- given Wide_String variable Result, starting at Result (Result'First). On
|
84 |
|
|
-- return, Length is set to the number of characters stored in Result. The
|
85 |
|
|
-- caller must ensure that Result is long enough (an easy choice is to set
|
86 |
|
|
-- the length equal to the S'Length, since decoding can never increase the
|
87 |
|
|
-- string length). If the length of Result is insufficient Constraint_Error
|
88 |
|
|
-- will be raised.
|
89 |
|
|
|
90 |
|
|
function Decode_Wide_Wide_String (S : String) return Wide_Wide_String;
|
91 |
|
|
pragma Inline (Decode_Wide_Wide_String);
|
92 |
|
|
-- Same as above function but for Wide_Wide_String output
|
93 |
|
|
|
94 |
|
|
procedure Decode_Wide_Wide_String
|
95 |
|
|
(S : String;
|
96 |
|
|
Result : out Wide_Wide_String;
|
97 |
|
|
Length : out Natural);
|
98 |
|
|
-- Same as above procedure, but for Wide_Wide_String output
|
99 |
|
|
|
100 |
|
|
function Validate_Wide_String (S : String) return Boolean;
|
101 |
|
|
-- This function inspects the string S to determine if it contains only
|
102 |
|
|
-- valid encodings corresponding to Wide_Character values using the
|
103 |
|
|
-- given encoding. If a call to Decode_Wide_String (S) would return
|
104 |
|
|
-- without raising Constraint_Error, then Validate_Wide_String will
|
105 |
|
|
-- return True. If the call would have raised Constraint_Error, then
|
106 |
|
|
-- Validate_Wide_String will return False.
|
107 |
|
|
|
108 |
|
|
function Validate_Wide_Wide_String (S : String) return Boolean;
|
109 |
|
|
-- Similar to Validate_Wide_String, except that it succeeds if the string
|
110 |
|
|
-- contains only encodings corresponding to Wide_Wide_Character values.
|
111 |
|
|
|
112 |
|
|
procedure Decode_Wide_Character
|
113 |
|
|
(Input : String;
|
114 |
|
|
Ptr : in out Natural;
|
115 |
|
|
Result : out Wide_Character);
|
116 |
|
|
pragma Inline (Decode_Wide_Character);
|
117 |
|
|
-- This is a lower level procedure that decodes a single character using
|
118 |
|
|
-- the given encoding method. The encoded character is stored in Input,
|
119 |
|
|
-- starting at Input (Ptr). The resulting output character is stored in
|
120 |
|
|
-- Result, and on return Ptr is updated past the input character or
|
121 |
|
|
-- encoding sequence. Constraint_Error will be raised if the input has
|
122 |
|
|
-- has a character that cannot be represented using the given encoding,
|
123 |
|
|
-- or if Ptr is outside the bounds of the Input string.
|
124 |
|
|
|
125 |
|
|
procedure Decode_Wide_Wide_Character
|
126 |
|
|
(Input : String;
|
127 |
|
|
Ptr : in out Natural;
|
128 |
|
|
Result : out Wide_Wide_Character);
|
129 |
|
|
-- Same as above procedure but with Wide_Wide_Character input
|
130 |
|
|
|
131 |
|
|
procedure Next_Wide_Character (Input : String; Ptr : in out Natural);
|
132 |
|
|
-- This procedure examines the input string starting at Input (Ptr), and
|
133 |
|
|
-- advances Ptr past one character in the encoded string, so that on return
|
134 |
|
|
-- Ptr points to the next encoded character. Constraint_Error is raised if
|
135 |
|
|
-- an invalid encoding is encountered, or the end of the string is reached
|
136 |
|
|
-- or if Ptr is less than String'First on entry, or if the character
|
137 |
|
|
-- skipped is not a valid Wide_Character code. This call may be more
|
138 |
|
|
-- efficient than calling Decode_Wide_Character and discarding the result.
|
139 |
|
|
|
140 |
|
|
procedure Prev_Wide_Character (Input : String; Ptr : in out Natural);
|
141 |
|
|
-- This procedure is similar to Next_Encoded_Character except that it moves
|
142 |
|
|
-- backwards in the string, so that on return, Ptr is set to point to the
|
143 |
|
|
-- previous encoded character. Constraint_Error is raised if the start of
|
144 |
|
|
-- the string is encountered. It is valid for Ptr to be one past the end
|
145 |
|
|
-- of the string for this call (in which case on return it will point to
|
146 |
|
|
-- the last encoded character).
|
147 |
|
|
--
|
148 |
|
|
-- Note: it is not generally possible to do this function efficiently with
|
149 |
|
|
-- all encodings, the current implementation is only efficient for the case
|
150 |
|
|
-- of UTF-8 (Encoding_Method = WCEM_UTF8) and Brackets (Encoding_Method =
|
151 |
|
|
-- WCEM_Brackets). For all other encodings, we work by starting at the
|
152 |
|
|
-- beginning of the string and moving forward till Ptr is reached, which
|
153 |
|
|
-- is correct but slow.
|
154 |
|
|
|
155 |
|
|
procedure Next_Wide_Wide_Character (Input : String; Ptr : in out Natural);
|
156 |
|
|
-- Similar to Next_Wide_Character except that codes skipped must be valid
|
157 |
|
|
-- Wide_Wide_Character codes.
|
158 |
|
|
|
159 |
|
|
procedure Prev_Wide_Wide_Character (Input : String; Ptr : in out Natural);
|
160 |
|
|
-- Similar to Prev_Wide_Character except that codes skipped must be valid
|
161 |
|
|
-- Wide_Wide_Character codes.
|
162 |
|
|
|
163 |
|
|
end GNAT.Decode_String;
|