1 ------------------------------------------------------------------------------
3 -- GNAT RUNTIME COMPONENTS --
5 -- S Y S T E M . W C H _ C N V --
9 -- Copyright (C) 1992-2001 Free Software Foundation, Inc. --
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, 59 Temple Place - Suite 330, Boston, --
20 -- MA 02111-1307, USA. --
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. --
29 -- GNAT was originally developed by the GNAT team at New York University. --
30 -- Extensive contributions were provided by Ada Core Technologies Inc. --
32 ------------------------------------------------------------------------------
34 -- This package contains generic subprograms used for converting between
35 -- sequences of Character and Wide_Character. All access to wide character
36 -- sequences is isolated in this unit.
38 with Interfaces
; use Interfaces
;
39 with System
.WCh_Con
; use System
.WCh_Con
;
40 with System
.WCh_JIS
; use System
.WCh_JIS
;
42 package body System
.WCh_Cnv
is
44 --------------------------------
45 -- Char_Sequence_To_Wide_Char --
46 --------------------------------
48 function Char_Sequence_To_Wide_Char
50 EM
: WC_Encoding_Method
)
58 procedure Get_Hex
(N
: Character);
59 -- If N is a hex character, then set B1 to 16 * B1 + character N.
60 -- Raise Constraint_Error if character N is not a hex character.
66 procedure Get_Hex
(N
: Character) is
67 B2
: constant Integer := Character'Pos (N
);
70 if B2
in Character'Pos ('0') .. Character'Pos ('9') then
71 B1
:= B1
* 16 + B2
- Character'Pos ('0');
73 elsif B2
in Character'Pos ('A') .. Character'Pos ('F') then
74 B1
:= B1
* 16 + B2
- (Character'Pos ('A') - 10);
76 elsif B2
in Character'Pos ('a') .. Character'Pos ('f') then
77 B1
:= B1
* 16 + B2
- (Character'Pos ('a') - 10);
80 raise Constraint_Error
;
84 -- Start of processing for Char_Sequence_To_Wide_Char
90 if C
/= ASCII
.ESC
then
91 return Wide_Character'Val (Character'Pos (C
));
100 return Wide_Character'Val (B1
);
104 if C
> ASCII
.DEL
then
107 (Integer (256 * Character'Pos (C
)) +
108 Character'Pos (In_Char
));
110 return Wide_Character'Val (Character'Pos (C
));
113 when WCEM_Shift_JIS
=>
114 if C
> ASCII
.DEL
then
115 return Shift_JIS_To_JIS
(C
, In_Char
);
117 return Wide_Character'Val (Character'Pos (C
));
121 if C
> ASCII
.DEL
then
122 return EUC_To_JIS
(C
, In_Char
);
124 return Wide_Character'Val (Character'Pos (C
));
128 if C
> ASCII
.DEL
then
130 -- 16#0080#-16#07ff#: 2#110xxxxx# 2#10xxxxxx#
131 -- 16#0800#-16#ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
133 U
:= Unsigned_16
(Character'Pos (C
));
135 if (U
and 2#
11100000#
) = 2#
11000000#
then
136 W
:= Shift_Left
(U
and 2#
00011111#
, 6);
137 U
:= Unsigned_16
(Character'Pos (In_Char
));
139 if (U
and 2#
11000000#
) /= 2#
10000000#
then
140 raise Constraint_Error
;
143 W
:= W
or (U
and 2#
00111111#
);
145 elsif (U
and 2#
11110000#
) = 2#
11100000#
then
146 W
:= Shift_Left
(U
and 2#
00001111#
, 12);
147 U
:= Unsigned_16
(Character'Pos (In_Char
));
149 if (U
and 2#
11000000#
) /= 2#
10000000#
then
150 raise Constraint_Error
;
153 W
:= W
or Shift_Left
(U
and 2#
00111111#
, 6);
154 U
:= Unsigned_16
(Character'Pos (In_Char
));
156 if (U
and 2#
11000000#
) /= 2#
10000000#
then
157 raise Constraint_Error
;
160 W
:= W
or (U
and 2#
00111111#
);
163 raise Constraint_Error
;
166 return Wide_Character'Val (W
);
169 return Wide_Character'Val (Character'Pos (C
));
172 when WCEM_Brackets
=>
175 return Wide_Character'Val (Character'Pos (C
));
178 if In_Char
/= '"' then
179 raise Constraint_Error
;
193 raise Constraint_Error
;
197 if In_Char
/= ']' then
198 raise Constraint_Error
;
201 return Wide_Character'Val (B1
);
204 end Char_Sequence_To_Wide_Char
;
206 --------------------------------
207 -- Wide_Char_To_Char_Sequence --
208 --------------------------------
210 procedure Wide_Char_To_Char_Sequence
211 (WC
: Wide_Character;
212 EM
: WC_Encoding_Method
)
214 Val
: constant Natural := Wide_Character'Pos (WC
);
215 Hexc
: constant array (0 .. 15) of Character := "0123456789ABCDEF";
224 Out_Char
(Character'Val (Val
));
227 Out_Char
(ASCII
.ESC
);
228 Out_Char
(Hexc
(Val
/ (16**3)));
229 Out_Char
(Hexc
((Val
/ (16**2)) mod 16));
230 Out_Char
(Hexc
((Val
/ 16) mod 16));
231 Out_Char
(Hexc
(Val
mod 16));
236 Out_Char
(Character'Val (Val
));
238 elsif Val
< 16#
8000#
then
239 raise Constraint_Error
;
242 Out_Char
(Character'Val (Val
/ 256));
243 Out_Char
(Character'Val (Val
mod 256));
246 when WCEM_Shift_JIS
=>
248 Out_Char
(Character'Val (Val
));
250 JIS_To_Shift_JIS
(WC
, C1
, C2
);
257 Out_Char
(Character'Val (Val
));
259 JIS_To_EUC
(WC
, C1
, C2
);
265 U
:= Unsigned_16
(Val
);
267 -- 16#0000#-16#007f#: 2#0xxxxxxx#
268 -- 16#0080#-16#07ff#: 2#110xxxxx# 2#10xxxxxx#
269 -- 16#0800#-16#ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
272 Out_Char
(Character'Val (U
));
274 elsif U
< 16#
0800#
then
275 Out_Char
(Character'Val (2#
11000000#
or Shift_Right
(U
, 6)));
276 Out_Char
(Character'Val (2#
10000000#
or (U
and 2#
00111111#
)));
279 Out_Char
(Character'Val (2#
11100000#
or Shift_Right
(U
, 12)));
280 Out_Char
(Character'Val (2#
10000000#
or (Shift_Right
(U
, 6)
282 Out_Char
(Character'Val (2#
10000000#
or (U
and 2#
00111111#
)));
285 when WCEM_Brackets
=>
288 Out_Char
(Character'Val (Val
));
293 Out_Char
(Hexc
(Val
/ (16**3)));
294 Out_Char
(Hexc
((Val
/ (16**2)) mod 16));
295 Out_Char
(Hexc
((Val
/ 16) mod 16));
296 Out_Char
(Hexc
(Val
mod 16));
301 end Wide_Char_To_Char_Sequence
;