gcc/ada/s-wchcon.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT COMPILER COMPONENTS                         --
   4 --                                                                          --
   5 --                       S Y S T E M . W C H _ C O N                        --
   6 --                                                                          --
   7 --                                 S p e c                                  --
   8 --                                                                          --
   9 --          Copyright (C) 1992-1998 Free Software Foundation, Inc.          --
  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,  59 Temple Place - Suite 330,  Boston, --
  20 -- MA 02111-1307, 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 --  This package defines the codes used to identify the encoding method for
  35 --  wide characters in string and character constants. This is needed both
  36 --  at compile time and at runtime (for the wide character runtime routines)
  37
  38 package System.WCh_Con is
  39 pragma Pure (WCh_Con);
  40
  41    -------------------------------------
  42    -- Wide_Character Encoding Methods --
  43    -------------------------------------
  44
  45    --  A wide character encoding method is a method for uniquely representing
  46    --  a Wide_Character value using a one or more Character values. Three
  47    --  types of encoding method are supported by GNAT:
  48
  49    --    An escape encoding method uses ESC as the first character of the
  50    --    sequence, and subsequent characters determine the wide character
  51    --    value that is represented. Any character other than ESC stands
  52    --    for itself as a single byte (i.e. any character in Latin-1, other
  53    --    than ESC itself, is represented as a single character: itself).
  54
  55    --    An upper half encoding method uses a character in the upper half
  56    --    range (i.e. in the range 16#80# .. 16#FF#) as the first byte of
  57    --    a wide character encoding sequence. Subsequent characters are
  58    --    used to determine the wide character value that is represented.
  59    --    Any character in the lower half (16#00# .. 16#7F#) represents
  60    --    itself as a single character.
  61
  62    --    The brackets notation, where a wide character is represented
  63    --    by the sequence ["xx"] or ["xxxx"] where xx are hexadecimal
  64    --    characters.
  65
  66    --  Note that GNAT does not currently support escape-in, escape-out
  67    --  encoding methods, where an escape sequence is used to set a mode
  68    --  used to recognize subsequent characters. All encoding methods use
  69    --  individual character-by-character encodings, so that a sequence of
  70    --  wide characters is represented by a sequence of encodings.
  71
  72    --  To add new encoding methods, the following steps are required:
  73
  74    --     1.  Define a code for a new value of type WC_Encoding_Method
  75    --     2.  Adjust the definition of WC_Encoding_Method accordingly
  76    --     3.  Provide appropriate conversion routines in System.Wch_Cnv
  77    --     4.  Adjust definition of WC_Longest_Sequence if necessary
  78    --     5.  Add an entry in WC_Encoding_Letters for the new method
  79    --     6.  Add proper code to s-wchstw.adb, s-wchwts.adb, s-widwch.adb
  80
  81    --  Note that the WC_Encoding_Method values must be kept ordered so that
  82    --  the definitions of the subtypes WC_Upper_Half_Encoding_Method and
  83    --  WC_ESC_Encoding_Method are still correct.
  84
  85    ---------------------------------
  86    -- Encoding Method Definitions --
  87    ---------------------------------
  88
  89    type WC_Encoding_Method is range 1 .. 6;
  90    --  Type covering the range of values used to represent wide character
  91    --  encoding methods. An enumeration type might be a little neater, but
  92    --  more trouble than it's worth, given the need to pass these values
  93    --  from the compiler to the backend, and to record them in the ALI file.
  94
  95    WCEM_Hex : constant WC_Encoding_Method := 1;
  96    --  The wide character with code 16#abcd# is represented by the escape
  97    --  sequence ESC a b c d (five characters, where abcd are ASCII hex
  98    --  characters, using upper case for letters). This method is easy
  99    --  to deal with in external environments that do not support wide
 100    --  characters, and covers the whole BMP. This is the default encoding
 101    --  method.
 102
 103    WCEM_Upper : constant WC_Encoding_Method := 2;
 104    --  The wide character with encoding 16#abcd#, where the upper bit is on
 105    --  (i.e. a is in the range 8-F) is represented as two bytes 16#ab# and
 106    --  16#cd#. The second byte may never be a format control character, but
 107    --  is not required to be in the upper half. This method can be also used
 108    --  for shift-JIS or EUC where the internal coding matches the external
 109    --  coding.
 110
 111    WCEM_Shift_JIS : constant WC_Encoding_Method := 3;
 112    --  A wide character is represented by a two character sequence 16#ab#
 113    --  and 16#cd#, with the restrictions described for upper half encoding
 114    --  as described above. The internal character code is the corresponding
 115    --  JIS character according to the standard algorithm for Shift-JIS
 116    --  conversion. See the body of package System.JIS_Conversions for
 117    --  further details.
 118
 119    WCEM_EUC : constant WC_Encoding_Method := 4;
 120    --  A wide character is represented by a two character sequence 16#ab# and
 121    --  16#cd#, with both characters being in the upper half set. The internal
 122    --  character code is the corresponding JIS character according to the EUC
 123    --  encoding algorithm. See the body of package System.JIS_Conversions for
 124    --  further details.
 125
 126    WCEM_UTF8 : constant WC_Encoding_Method := 5;
 127    --  An ISO 10646-1 BMP/Unicode wide character is represented in
 128    --  UCS Transformation Format 8 (UTF-8) as defined in Annex R of ISO
 129    --  10646-1/Am.2.  Depending on the character value, a Unicode character
 130    --  is represented as the one, two, or three byte sequence
 131    --
 132    --    16#0000#-16#007f#: 2#0xxxxxxx#
 133    --    16#0080#-16#07ff#: 2#110xxxxx# 2#10xxxxxx#
 134    --    16#0800#-16#ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
 135    --
 136    --  where the xxx bits correspond to the left-padded bits of the the
 137    --  16-bit character value. Note that all lower half ASCII characters
 138    --  are represented as ASCII bytes and all upper half characters and
 139    --  other wide characters are represented as sequences of upper-half
 140    --  (The full UTF-8 scheme allows for encoding 31-bit characters as
 141    --  6-byte sequences, but in this implementation, all UTF-8 sequences
 142    --  of four or more bytes length will raise a Constraint_Error, as
 143    --  will all illegal UTF-8 sequences.)
 144
 145    WCEM_Brackets : constant WC_Encoding_Method := 6;
 146    --  A wide character is represented as the sequence ["abcd"] where abcd
 147    --  are four hexadecimal characters. In this mode, the sequence ["ab"]
 148    --  is also recognized for the case of character codes in the range 0-255.
 149
 150    WC_Encoding_Letters : constant array (WC_Encoding_Method) of Character :=
 151      (WCEM_Hex       => 'h',
 152       WCEM_Upper     => 'u',
 153       WCEM_Shift_JIS => 's',
 154       WCEM_EUC       => 'e',
 155       WCEM_UTF8      => '8',
 156       WCEM_Brackets  => 'b');
 157    --  Letters used for selection of wide character encoding method in the
 158    --  compiler options (-gnatW? switch) and for Wide_Text_IO (WCEM parameter
 159    --  in the form string).
 160
 161    subtype WC_ESC_Encoding_Method is
 162      WC_Encoding_Method range WCEM_Hex .. WCEM_Hex;
 163    --  Encoding methods using an ESC character at the start of the sequence.
 164
 165    subtype WC_Upper_Half_Encoding_Method is
 166      WC_Encoding_Method range WCEM_Upper .. WCEM_UTF8;
 167    --  Encoding methods using an upper half character (16#80#..16#FF) at
 168    --  the start of the sequence.
 169
 170    WC_Longest_Sequence : constant := 8;
 171    --  The longest number of characters that can be used for a wide
 172    --  character sequence for any of the active encoding methods.
 173
 174 end System.WCh_Con;