/usr/share/ada/adainclude/xmlada/unicode-ces-utf16.adb is in libxmlada4.1-dev 4.1-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | -----------------------------------------------------------------------
-- XML/Ada - An XML suite for Ada95 --
-- --
-- Copyright (C) 2001-2010, AdaCore --
-- --
-- This library is free software; you can redistribute it and/or --
-- modify it under the terms of the GNU General Public --
-- License as published by the Free Software Foundation; either --
-- version 2 of the License, or (at your option) any later version. --
-- --
-- This library is distributed in the hope that it will be useful, --
-- but WITHOUT ANY WARRANTY; without even the implied warranty of --
-- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU --
-- General Public License for more details. --
-- --
-- You should have received a copy of the GNU General Public --
-- License along with this library; if not, write to the --
-- Free Software Foundation, Inc., 59 Temple Place - Suite 330, --
-- Boston, MA 02111-1307, USA. --
-- --
-----------------------------------------------------------------------
with Unicode.CES.Utf32; use Unicode.CES.Utf32;
with Unicode.CCS; use Unicode.CCS;
package body Unicode.CES.Utf16 is
------------
-- Encode --
------------
procedure Encode
(Char : Unicode_Char;
Output : in out Byte_Sequence;
Index : in out Natural)
is
C, D : Unicode_Char;
begin
if Char < 16#10000# then
C := Char and 16#00FF#;
D := (Char and 16#FF00#) / (2 ** 8);
Output (Index + 1) := Character'Val (C);
Output (Index + 2) := Character'Val (D);
Index := Index + 2;
else
C := 16#D800#
+ ((Char - 16#10000#) and 2#11111111110000000000#) / (2 ** 10);
D := 16#DC00#
+ ((Char - 16#10000#) and 2#1111111111#);
Output (Index + 1) := Character'Val (C and 16#00FF#);
Output (Index + 2) := Character'Val ((C and 16#FF00#) / (2 ** 8));
Output (Index + 3) := Character'Val (D and 16#00FF#);
Output (Index + 4) := Character'Val ((D and 16#FF00#) / (2 ** 8));
Index := Index + 4;
end if;
end Encode;
---------------
-- Encode_BE --
---------------
procedure Encode_BE
(Char : Unicode_Char;
Output : in out Byte_Sequence;
Index : in out Natural)
is
C, D : Unicode_Char;
begin
if Char < 16#10000# then
C := Char and 16#00FF#;
D := (Char and 16#FF00#) / (2 ** 8);
Output (Index + 1) := Character'Val (D);
Output (Index + 2) := Character'Val (C);
Index := Index + 2;
else
C := 16#D800#
+ ((Char - 16#10000#) and 2#11111111110000000000#) / (2 ** 10);
D := 16#DC00#
+ ((Char - 16#10000#) and 2#1111111111#);
Output (Index + 1) := Character'Val ((C and 16#FF00#) / (2 ** 8));
Output (Index + 2) := Character'Val (C and 16#00FF#);
Output (Index + 3) := Character'Val ((D and 16#FF00#) / (2 ** 8));
Output (Index + 4) := Character'Val (D and 16#00FF#);
Index := Index + 4;
end if;
end Encode_BE;
----------
-- Read --
----------
procedure Read
(Str : Utf16_LE_String;
Index : in out Positive;
Char : out Unicode_Char)
is
C, D : Unicode_Char;
begin
if Index + 1 > Str'Last then
raise Incomplete_Encoding;
end if;
C := Character'Pos (Str (Index + 1)) * 256 + Character'Pos (Str (Index));
-- High surrogate value
if C in 16#D800# .. 16#DBFF# then
if Index + 3 > Str'Last then
raise Incomplete_Encoding;
end if;
D := Character'Pos (Str (Index + 3)) * 256
+ Character'Pos (Str (Index + 2));
-- Not a low surrogate ?
if not (D in 16#DC00# .. 16#DFFF#) then
raise Invalid_Encoding;
end if;
C := C and 2#1111111111#;
D := D and 2#1111111111#;
Char := C * 2#10000000000# + D + 16#10000#;
Index := Index + 4;
else
Char := C;
Index := Index + 2;
end if;
end Read;
-------------
-- Read_BE --
-------------
procedure Read_BE
(Str : Utf16_BE_String;
Index : in out Positive;
Char : out Unicode_Char)
is
C, D : Unicode_Char;
begin
if Index + 1 > Str'Last then
raise Incomplete_Encoding;
end if;
C := Character'Pos (Str (Index)) * 256 + Character'Pos (Str (Index + 1));
-- High surrogate value
if C in 16#D800# .. 16#DBFF# then
if Index + 3 > Str'Last then
raise Incomplete_Encoding;
end if;
D := Character'Pos (Str (Index + 2)) * 256
+ Character'Pos (Str (Index + 3));
-- Not a low surrogate ?
if not (D in 16#DC00# .. 16#DFFF#) then
raise Invalid_Encoding;
end if;
C := C and 2#1111111111#;
D := D and 2#1111111111#;
Char := C * 2#10000000000# + D + 16#10000#;
Index := Index + 4;
else
Char := C;
Index := Index + 2;
end if;
end Read_BE;
-----------
-- Width --
-----------
function Width (Char : Unicode_Char) return Natural is
begin
if Char >= 16#10000# then
return 4;
else
return 2;
end if;
end Width;
------------
-- Length --
------------
function Length (Str : Utf16_String) return Natural is
Pos : Natural := Str'First;
Len : Natural := 0;
C : Unicode_Char;
begin
while Pos <= Str'Last loop
Read (Str, Pos, C);
Len := Len + 1;
end loop;
return Len;
end Length;
----------------
-- From_Utf32 --
----------------
function From_Utf32
(Str : Unicode.CES.Utf32.Utf32_LE_String)
return Utf16_LE_String
is
Result : Utf16_LE_String (1 .. (Str'Length / Utf32_Char_Width) * 4);
J : Positive := Str'First;
R_Index : Natural := Result'First - 1;
C : Unicode_Char;
begin
while J <= Str'Last loop
Unicode.CES.Utf32.Read (Str, J, C);
Encode (C, Result, R_Index);
end loop;
return Result (1 .. R_Index);
end From_Utf32;
--------------
-- To_Utf32 --
--------------
function To_Utf32
(Str : Utf16_LE_String)
return Unicode.CES.Utf32.Utf32_LE_String
is
Result : Utf32_LE_String (1 .. (Str'Length / 2) * Utf32_Char_Width);
J : Natural := Str'First;
R_Index : Natural := Result'First - 1;
C : Unicode_Char;
begin
while J <= Str'Last loop
Read (Str, J, C);
Unicode.CES.Utf32.Encode (C, Result, R_Index);
end loop;
return Result (1 .. R_Index);
end To_Utf32;
-------------------
-- To_Unicode_LE --
-------------------
-- ??? Note: this assumes that the original character and its
-- conversion are encoded on the same length, which is always
-- right so far with Unicode.
function To_Unicode_LE
(Str : Utf16_String;
Cs : Unicode.CCS.Character_Set := Unicode.CCS.Unicode_Character_Set;
Order : Byte_Order := Default_Byte_Order) return Utf16_LE_String
is
BOM : Bom_Type;
Offset : Natural := 0;
O : Byte_Order := Order;
J : Natural := Str'First;
S : Utf16_LE_String (1 .. Str'Length);
C : Unicode_Char;
begin
Read_Bom (Str, Offset, BOM);
case BOM is
when Utf16_LE => O := Low_Byte_First;
when Utf16_BE => O := High_Byte_First;
when Unknown => null;
when others => raise Invalid_Encoding;
end case;
if O = Low_Byte_First then
if Cs.To_Unicode = Identity'Access then
return Str (Str'First + Offset .. Str'Last);
else
J := J + Offset - 1;
while J <= Str'Last loop
Read (Str, J, C);
Encode (Cs.To_Unicode (C), S, J);
end loop;
return S (S'First + Offset .. S'Last);
end if;
else
J := J + Offset;
if Cs.To_Unicode = Identity'Access then
while J <= Str'Last loop
S (J + 1) := Str (J);
S (J) := Str (J + 1);
J := J + 2;
end loop;
else
J := J - 1;
while J <= Str'Last loop
Read_BE (Str, J, C);
Encode (Cs.To_Unicode (C), S, J);
end loop;
return S (S'First + Offset .. S'Last);
end if;
return S (S'First + Offset .. S'Last);
end if;
end To_Unicode_LE;
-----------
-- To_CS --
-----------
function To_CS
(Str : Utf16_LE_String;
Cs : Unicode.CCS.Character_Set := Unicode.CCS.Unicode_Character_Set;
Order : Byte_Order := Default_Byte_Order) return Utf16_String
is
pragma Warnings (Off, Order);
Offset : constant Natural := 0;
J : Natural := Str'First;
S : Utf16_LE_String (1 .. Str'Length);
C : Unicode_Char;
begin
if Order = Low_Byte_First then
if Cs.To_CS = Identity'Access then
return Str (Str'First + Offset .. Str'Last);
else
J := J + Offset - 1;
while J <= Str'Last loop
Read (Str, J, C);
Encode (Cs.To_CS (C), S, J);
end loop;
return S (S'First + Offset .. S'Last);
end if;
else
J := J + Offset;
if Cs.To_CS = Identity'Access then
while J <= Str'Last loop
S (J + 1) := Str (J);
S (J) := Str (J + 1);
J := J + 2;
end loop;
else
J := J - 1;
while J <= Str'Last loop
Read (Str, J, C);
Encode_BE (Cs.To_CS (C), S, J);
end loop;
return S (S'First + Offset .. S'Last);
end if;
return S (S'First + Offset .. S'Last);
end if;
end To_CS;
end Unicode.CES.Utf16;
|