1 ------------------------------------------------------------------------------
3 -- GNAT COMPILER COMPONENTS --
5 -- S Y S T E M . W C H _ C O N --
9 -- $Revision: 1.10 $ --
11 -- Copyright (C) 1992-1998 Free Software Foundation, Inc. --
13 -- GNAT is free software; you can redistribute it and/or modify it under --
14 -- terms of the GNU General Public License as published by the Free Soft- --
15 -- ware Foundation; either version 2, or (at your option) any later ver- --
16 -- sion. GNAT is distributed in the hope that it will be useful, but WITH- --
17 -- OUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY --
18 -- or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License --
19 -- for more details. You should have received a copy of the GNU General --
20 -- Public License distributed with GNAT; see file COPYING. If not, write --
21 -- to the Free Software Foundation, 59 Temple Place - Suite 330, Boston, --
22 -- MA 02111-1307, USA. --
24 -- As a special exception, if other files instantiate generics from this --
25 -- unit, or you link this unit with other files to produce an executable, --
26 -- this unit does not by itself cause the resulting executable to be --
27 -- covered by the GNU General Public License. This exception does not --
28 -- however invalidate any other reasons why the executable file might be --
29 -- covered by the GNU Public License. --
31 -- GNAT was originally developed by the GNAT team at New York University. --
32 -- It is now maintained by Ada Core Technologies Inc (http://www.gnat.com). --
34 ------------------------------------------------------------------------------
36 -- This package defines the codes used to identify the encoding method for
37 -- wide characters in string and character constants. This is needed both
38 -- at compile time and at runtime (for the wide character runtime routines)
40 package System.WCh_Con is
41 pragma Pure (WCh_Con);
43 -------------------------------------
44 -- Wide_Character Encoding Methods --
45 -------------------------------------
47 -- A wide character encoding method is a method for uniquely representing
48 -- a Wide_Character value using a one or more Character values. Three
49 -- types of encoding method are supported by GNAT:
51 -- An escape encoding method uses ESC as the first character of the
52 -- sequence, and subsequent characters determine the wide character
53 -- value that is represented. Any character other than ESC stands
54 -- for itself as a single byte (i.e. any character in Latin-1, other
55 -- than ESC itself, is represented as a single character: itself).
57 -- An upper half encoding method uses a character in the upper half
58 -- range (i.e. in the range 16#80# .. 16#FF#) as the first byte of
59 -- a wide character encoding sequence. Subsequent characters are
60 -- used to determine the wide character value that is represented.
61 -- Any character in the lower half (16#00# .. 16#7F#) represents
62 -- itself as a single character.
64 -- The brackets notation, where a wide character is represented
65 -- by the sequence ["xx"] or ["xxxx"] where xx are hexadecimal
68 -- Note that GNAT does not currently support escape-in, escape-out
69 -- encoding methods, where an escape sequence is used to set a mode
70 -- used to recognize subsequent characters. All encoding methods use
71 -- individual character-by-character encodings, so that a sequence of
72 -- wide characters is represented by a sequence of encodings.
74 -- To add new encoding methods, the following steps are required:
76 -- 1. Define a code for a new value of type WC_Encoding_Method
77 -- 2. Adjust the definition of WC_Encoding_Method accordingly
78 -- 3. Provide appropriate conversion routines in System.Wch_Cnv
79 -- 4. Adjust definition of WC_Longest_Sequence if necessary
80 -- 5. Add an entry in WC_Encoding_Letters for the new method
81 -- 6. Add proper code to s-wchstw.adb, s-wchwts.adb, s-widwch.adb
83 -- Note that the WC_Encoding_Method values must be kept ordered so that
84 -- the definitions of the subtypes WC_Upper_Half_Encoding_Method and
85 -- WC_ESC_Encoding_Method are still correct.
87 ---------------------------------
88 -- Encoding Method Definitions --
89 ---------------------------------
91 type WC_Encoding_Method is range 1 .. 6;
92 -- Type covering the range of values used to represent wide character
93 -- encoding methods. An enumeration type might be a little neater, but
94 -- more trouble than it's worth, given the need to pass these values
95 -- from the compiler to the backend, and to record them in the ALI file.
97 WCEM_Hex : constant WC_Encoding_Method := 1;
98 -- The wide character with code 16#abcd# is represented by the escape
99 -- sequence ESC a b c d (five characters, where abcd are ASCII hex
100 -- characters, using upper case for letters). This method is easy
101 -- to deal with in external environments that do not support wide
102 -- characters, and covers the whole BMP. This is the default encoding
105 WCEM_Upper : constant WC_Encoding_Method := 2;
106 -- The wide character with encoding 16#abcd#, where the upper bit is on
107 -- (i.e. a is in the range 8-F) is represented as two bytes 16#ab# and
108 -- 16#cd#. The second byte may never be a format control character, but
109 -- is not required to be in the upper half. This method can be also used
110 -- for shift-JIS or EUC where the internal coding matches the external
113 WCEM_Shift_JIS : constant WC_Encoding_Method := 3;
114 -- A wide character is represented by a two character sequence 16#ab#
115 -- and 16#cd#, with the restrictions described for upper half encoding
116 -- as described above. The internal character code is the corresponding
117 -- JIS character according to the standard algorithm for Shift-JIS
118 -- conversion. See the body of package System.JIS_Conversions for
121 WCEM_EUC : constant WC_Encoding_Method := 4;
122 -- A wide character is represented by a two character sequence 16#ab# and
123 -- 16#cd#, with both characters being in the upper half set. The internal
124 -- character code is the corresponding JIS character according to the EUC
125 -- encoding algorithm. See the body of package System.JIS_Conversions for
128 WCEM_UTF8 : constant WC_Encoding_Method := 5;
129 -- An ISO 10646-1 BMP/Unicode wide character is represented in
130 -- UCS Transformation Format 8 (UTF-8) as defined in Annex R of ISO
131 -- 10646-1/Am.2. Depending on the character value, a Unicode character
132 -- is represented as the one, two, or three byte sequence
134 -- 16#0000#-16#007f#: 2#0xxxxxxx#
135 -- 16#0080#-16#07ff#: 2#110xxxxx# 2#10xxxxxx#
136 -- 16#0800#-16#ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
138 -- where the xxx bits correspond to the left-padded bits of the the
139 -- 16-bit character value. Note that all lower half ASCII characters
140 -- are represented as ASCII bytes and all upper half characters and
141 -- other wide characters are represented as sequences of upper-half
142 -- (The full UTF-8 scheme allows for encoding 31-bit characters as
143 -- 6-byte sequences, but in this implementation, all UTF-8 sequences
144 -- of four or more bytes length will raise a Constraint_Error, as
145 -- will all illegal UTF-8 sequences.)
147 WCEM_Brackets : constant WC_Encoding_Method := 6;
148 -- A wide character is represented as the sequence ["abcd"] where abcd
149 -- are four hexadecimal characters. In this mode, the sequence ["ab"]
150 -- is also recognized for the case of character codes in the range 0-255.
152 WC_Encoding_Letters : constant array (WC_Encoding_Method) of Character :=
155 WCEM_Shift_JIS => 's',
158 WCEM_Brackets => 'b');
159 -- Letters used for selection of wide character encoding method in the
160 -- compiler options (-gnatW? switch) and for Wide_Text_IO (WCEM parameter
161 -- in the form string).
163 subtype WC_ESC_Encoding_Method is
164 WC_Encoding_Method range WCEM_Hex .. WCEM_Hex;
165 -- Encoding methods using an ESC character at the start of the sequence.
167 subtype WC_Upper_Half_Encoding_Method is
168 WC_Encoding_Method range WCEM_Upper .. WCEM_UTF8;
169 -- Encoding methods using an upper half character (16#80#..16#FF) at
170 -- the start of the sequence.
172 WC_Longest_Sequence : constant := 8;
173 -- The longest number of characters that can be used for a wide
174 -- character sequence for any of the active encoding methods.