File : g-byorma.ads
1 ------------------------------------------------------------------------------
2 -- --
3 -- GNAT COMPILER COMPONENTS --
4 -- --
5 -- G N A T . B Y T E _ O R D E R _ M A R K --
6 -- --
7 -- S p e c --
8 -- --
9 -- Copyright (C) 2006-2013, 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 -- --
19 -- --
20 -- --
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 ------------------------------------------------------------------------------
31
32 -- This package provides a procedure for reading and interpreting the BOM
33 -- (byte order mark) used to publish the encoding method for a string (for
34 -- example, a UTF-8 encoded file in windows will start with the appropriate
35 -- BOM sequence to signal UTF-8 encoding.
36
37 -- There are two cases
38
39 -- Case 1. UTF encodings for Unicode files
40
41 -- Here the convention is to have the first character of the file be a
42 -- non-breaking zero width space character (16#0000_FEFF#). For the UTF
43 -- encodings, the representation of this character can be used to uniquely
44 -- determine the encoding. Furthermore, the possibility of any confusion
45 -- with unencoded files is minimal, since for example the UTF-8 encoding
46 -- of this character looks like the sequence:
47
48 -- LC_I_Diaeresis
49 -- Right_Angle_Quotation
50 -- Fraction_One_Half
51
52 -- which is so unlikely to occur legitimately in normal use that it can
53 -- safely be ignored in most cases (for example, no legitimate Ada source
54 -- file could start with this sequence of characters).
55
56 -- Case 2. Specialized XML encodings
57
58 -- The XML standard defines a number of other possible encodings and also
59 -- defines standardized sequences for marking these encodings. This package
60 -- can also optionally handle these XML defined BOM sequences. These XML
61 -- cases depend on the first character of the XML file being < so that the
62 -- encoding of this character can be recognized.
63
64 pragma Compiler_Unit_Warning;
65
66 package GNAT.Byte_Order_Mark is
67
68 type BOM_Kind is
69 (UTF8_All, -- UTF8-encoding
70 UTF16_LE, -- UTF16 little-endian encoding
71 UTF16_BE, -- UTF16 big-endian encoding
72 UTF32_LE, -- UTF32 little-endian encoding
73 UTF32_BE, -- UTF32 big-endian encoding
74
75 -- The following cases are for XML only
76
77 UCS4_BE, -- UCS-4, big endian machine (1234 order)
78 UCS4_LE, -- UCS-4, little endian machine (4321 order)
79 UCS4_2143, -- UCS-4, unusual byte order (2143 order)
80 UCS4_3412, -- UCS-4, unusual byte order (3412 order)
81
82 -- Value returned if no BOM recognized
83
84 Unknown); -- Unknown, assumed to be ASCII compatible
85
86 procedure Read_BOM
87 (Str : String;
88 Len : out Natural;
89 BOM : out BOM_Kind;
90 XML_Support : Boolean := False);
91 -- This is the routine to read the BOM from the start of the given string
92 -- Str. On return BOM is set to the appropriate BOM_Kind and Len is set to
93 -- its length. The caller will typically skip the first Len characters in
94 -- the string to ignore the BOM sequence. The special XML possibilities are
95 -- recognized only if flag XML_Support is set to True. Note that for the
96 -- XML cases, Len is always set to zero on return (not to the length of the
97 -- relevant sequence) since in the XML cases, the sequence recognized is
98 -- for the first real character in the file (<) which is not to be skipped.
99
100 end GNAT.Byte_Order_Mark;