gcc/ada/g-byorma.adb

   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 --                                 B o d y                                  --
   8 --                                                                          --
   9 --                     Copyright (C) 2006-2008, 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 pragma Compiler_Unit;
  35
  36 package body GNAT.Byte_Order_Mark is
  37
  38    --------------
  39    -- Read_BOM --
  40    --------------
  41
  42    procedure Read_BOM
  43      (Str         : String;
  44       Len         : out Natural;
  45       BOM         : out BOM_Kind;
  46       XML_Support : Boolean := False)
  47    is
  48    begin
  49       --  Note: the order of these tests is important, because in some cases
  50       --  one sequence is a prefix of a longer sequence, and we must test for
  51       --  the longer sequence first
  52
  53       --  UTF-32 (big-endian)
  54
  55       if Str'Length >= 4
  56         and then Str (Str'First)     = Character'Val (16#00#)
  57         and then Str (Str'First + 1) = Character'Val (16#00#)
  58         and then Str (Str'First + 2) = Character'Val (16#FE#)
  59         and then Str (Str'First + 3) = Character'Val (16#FF#)
  60       then
  61          Len := 4;
  62          BOM := UTF32_BE;
  63
  64       --  UTF-32 (little-endian)
  65
  66       elsif Str'Length >= 4
  67         and then Str (Str'First)     = Character'Val (16#FF#)
  68         and then Str (Str'First + 1) = Character'Val (16#FE#)
  69         and then Str (Str'First + 2) = Character'Val (16#00#)
  70         and then Str (Str'First + 3) = Character'Val (16#00#)
  71       then
  72          Len := 4;
  73          BOM := UTF32_LE;
  74
  75       --  UTF-16 (big-endian)
  76
  77       elsif Str'Length >= 2
  78         and then Str (Str'First) = Character'Val (16#FE#)
  79         and then Str (Str'First + 1) = Character'Val (16#FF#)
  80       then
  81          Len := 2;
  82          BOM := UTF16_BE;
  83
  84       --  UTF-16 (little-endian)
  85
  86       elsif Str'Length >= 2
  87         and then Str (Str'First) = Character'Val (16#FF#)
  88         and then Str (Str'First + 1) = Character'Val (16#FE#)
  89       then
  90          Len := 2;
  91          BOM := UTF16_LE;
  92
  93       --  UTF-8 (endian-independent)
  94
  95       elsif Str'Length >= 3
  96         and then Str (Str'First)     = Character'Val (16#EF#)
  97         and then Str (Str'First + 1) = Character'Val (16#BB#)
  98         and then Str (Str'First + 2) = Character'Val (16#BF#)
  99       then
 100          Len := 3;
 101          BOM := UTF8_All;
 102
 103       --  UCS-4 (big-endian) XML only
 104
 105       elsif XML_Support
 106         and then Str'Length >= 4
 107         and then Str (Str'First)     = Character'Val (16#00#)
 108         and then Str (Str'First + 1) = Character'Val (16#00#)
 109         and then Str (Str'First + 2) = Character'Val (16#00#)
 110         and then Str (Str'First + 3) = Character'Val (16#3C#)
 111       then
 112          Len := 0;
 113          BOM := UCS4_BE;
 114
 115       --  UCS-4 (little-endian) XML case
 116
 117       elsif XML_Support
 118         and then Str'Length >= 4
 119         and then Str (Str'First)     = Character'Val (16#3C#)
 120         and then Str (Str'First + 1) = Character'Val (16#00#)
 121         and then Str (Str'First + 2) = Character'Val (16#00#)
 122         and then Str (Str'First + 3) = Character'Val (16#00#)
 123       then
 124          Len := 0;
 125          BOM := UCS4_LE;
 126
 127       --  UCS-4 (unusual byte order 2143) XML case
 128
 129       elsif XML_Support
 130         and then Str'Length >= 4
 131         and then Str (Str'First)     = Character'Val (16#00#)
 132         and then Str (Str'First + 1) = Character'Val (16#00#)
 133         and then Str (Str'First + 2) = Character'Val (16#3C#)
 134         and then Str (Str'First + 3) = Character'Val (16#00#)
 135       then
 136          Len := 0;
 137          BOM := UCS4_2143;
 138
 139       --  UCS-4 (unusual byte order 3412) XML case
 140
 141       elsif XML_Support
 142         and then Str'Length >= 4
 143         and then Str (Str'First)     = Character'Val (16#00#)
 144         and then Str (Str'First + 1) = Character'Val (16#3C#)
 145         and then Str (Str'First + 2) = Character'Val (16#00#)
 146         and then Str (Str'First + 3) = Character'Val (16#00#)
 147       then
 148          Len := 0;
 149          BOM := UCS4_3412;
 150
 151       --  UTF-16 (big-endian) XML case
 152
 153       elsif XML_Support
 154         and then Str'Length >= 4
 155         and then Str (Str'First)     = Character'Val (16#00#)
 156         and then Str (Str'First + 1) = Character'Val (16#3C#)
 157         and then Str (Str'First + 2) = Character'Val (16#00#)
 158         and then Str (Str'First + 3) = Character'Val (16#3F#)
 159       then
 160          Len := 0;
 161          BOM := UTF16_BE;
 162
 163       --  UTF-32 (little-endian) XML case
 164
 165       elsif XML_Support
 166         and then Str'Length >= 4
 167         and then Str (Str'First)     = Character'Val (16#3C#)
 168         and then Str (Str'First + 1) = Character'Val (16#00#)
 169         and then Str (Str'First + 2) = Character'Val (16#3F#)
 170         and then Str (Str'First + 3) = Character'Val (16#00#)
 171       then
 172          Len := 0;
 173          BOM := UTF16_LE;
 174
 175       --  Unrecognized special encodings XML only
 176
 177       elsif XML_Support
 178         and then Str'Length >= 4
 179         and then Str (Str'First)     = Character'Val (16#3C#)
 180         and then Str (Str'First + 1) = Character'Val (16#3F#)
 181         and then Str (Str'First + 2) = Character'Val (16#78#)
 182         and then Str (Str'First + 3) = Character'Val (16#6D#)
 183       then
 184          --  UTF-8, ASCII, some part of ISO8859, Shift-JIS, EUC,...
 185
 186          Len := 0;
 187          BOM := Unknown;
 188
 189       --  No BOM recognized
 190
 191       else
 192          Len := 0;
 193          BOM := Unknown;
 194       end if;
 195    end Read_BOM;
 196
 197 end GNAT.Byte_Order_Mark;