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 --                                                                          --
  10 --          Copyright (C) 1992-1998 Free Software Foundation, Inc.          --
  11 --                                                                          --
  12 -- GNAT is free software;  you can  redistribute it  and/or modify it under --
  13 -- terms of the  GNU General Public License as published  by the Free Soft- --
  14 -- ware  Foundation;  either version 2,  or (at your option) any later ver- --
  15 -- sion.  GNAT is distributed in the hope that it will be useful, but WITH- --
  16 -- OUT ANY WARRANTY;  without even the  implied warranty of MERCHANTABILITY --
  17 -- or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License --
  18 -- for  more details.  You should have  received  a copy of the GNU General --
  19 -- Public License  distributed with GNAT;  see file COPYING.  If not, write --
  20 -- to  the Free Software Foundation,  59 Temple Place - Suite 330,  Boston, --
  21 -- MA 02111-1307, USA.                                                      --
  22 --                                                                          --
  23 -- As a special exception,  if other files  instantiate  generics from this --
  24 -- unit, or you link  this unit with other files  to produce an executable, --
  25 -- this  unit  does not  by itself cause  the resulting  executable  to  be --
  26 -- covered  by the  GNU  General  Public  License.  This exception does not --
  27 -- however invalidate  any other reasons why  the executable file  might be --
  28 -- covered by the  GNU Public License.                                      --
  29 --                                                                          --
  30 -- GNAT was originally developed  by the GNAT team at  New York University. --
  31 -- Extensive contributions were provided by Ada Core Technologies Inc.      --
  32 --                                                                          --
  33 ------------------------------------------------------------------------------
  34
  35 --  This package defines the codes used to identify the encoding method for
  36 --  wide characters in string and character constants. This is needed both
  37 --  at compile time and at runtime (for the wide character runtime routines)
  38
  39 package System.WCh_Con is
  40 pragma Pure (WCh_Con);
  41
  42    -------------------------------------
  43    -- Wide_Character Encoding Methods --
  44    -------------------------------------
  45
  46    --  A wide character encoding method is a method for uniquely representing
  47    --  a Wide_Character value using a one or more Character values. Three
  48    --  types of encoding method are supported by GNAT:
  49
  50    --    An escape encoding method uses ESC as the first character of the
  51    --    sequence, and subsequent characters determine the wide character
  52    --    value that is represented. Any character other than ESC stands
  53    --    for itself as a single byte (i.e. any character in Latin-1, other
  54    --    than ESC itself, is represented as a single character: itself).
  55
  56    --    An upper half encoding method uses a character in the upper half
  57    --    range (i.e. in the range 16#80# .. 16#FF#) as the first byte of
  58    --    a wide character encoding sequence. Subsequent characters are
  59    --    used to determine the wide character value that is represented.
  60    --    Any character in the lower half (16#00# .. 16#7F#) represents
  61    --    itself as a single character.
  62
  63    --    The brackets notation, where a wide character is represented
  64    --    by the sequence ["xx"] or ["xxxx"] where xx are hexadecimal
  65    --    characters.
  66
  67    --  Note that GNAT does not currently support escape-in, escape-out
  68    --  encoding methods, where an escape sequence is used to set a mode
  69    --  used to recognize subsequent characters. All encoding methods use
  70    --  individual character-by-character encodings, so that a sequence of
  71    --  wide characters is represented by a sequence of encodings.
  72
  73    --  To add new encoding methods, the following steps are required:
  74
  75    --     1.  Define a code for a new value of type WC_Encoding_Method
  76    --     2.  Adjust the definition of WC_Encoding_Method accordingly
  77    --     3.  Provide appropriate conversion routines in System.Wch_Cnv
  78    --     4.  Adjust definition of WC_Longest_Sequence if necessary
  79    --     5.  Add an entry in WC_Encoding_Letters for the new method
  80    --     6.  Add proper code to s-wchstw.adb, s-wchwts.adb, s-widwch.adb
  81
  82    --  Note that the WC_Encoding_Method values must be kept ordered so that
  83    --  the definitions of the subtypes WC_Upper_Half_Encoding_Method and
  84    --  WC_ESC_Encoding_Method are still correct.
  85
  86    ---------------------------------
  87    -- Encoding Method Definitions --
  88    ---------------------------------
  89
  90    type WC_Encoding_Method is range 1 .. 6;
  91    --  Type covering the range of values used to represent wide character
  92    --  encoding methods. An enumeration type might be a little neater, but
  93    --  more trouble than it's worth, given the need to pass these values
  94    --  from the compiler to the backend, and to record them in the ALI file.
  95
  96    WCEM_Hex : constant WC_Encoding_Method := 1;
  97    --  The wide character with code 16#abcd# is represented by the escape
  98    --  sequence ESC a b c d (five characters, where abcd are ASCII hex
  99    --  characters, using upper case for letters). This method is easy
 100    --  to deal with in external environments that do not support wide
 101    --  characters, and covers the whole BMP. This is the default encoding
 102    --  method.
 103
 104    WCEM_Upper : constant WC_Encoding_Method := 2;
 105    --  The wide character with encoding 16#abcd#, where the upper bit is on
 106    --  (i.e. a is in the range 8-F) is represented as two bytes 16#ab# and
 107    --  16#cd#. The second byte may never be a format control character, but
 108    --  is not required to be in the upper half. This method can be also used
 109    --  for shift-JIS or EUC where the internal coding matches the external
 110    --  coding.
 111
 112    WCEM_Shift_JIS : constant WC_Encoding_Method := 3;
 113    --  A wide character is represented by a two character sequence 16#ab#
 114    --  and 16#cd#, with the restrictions described for upper half encoding
 115    --  as described above. The internal character code is the corresponding
 116    --  JIS character according to the standard algorithm for Shift-JIS
 117    --  conversion. See the body of package System.JIS_Conversions for
 118    --  further details.
 119
 120    WCEM_EUC : constant WC_Encoding_Method := 4;
 121    --  A wide character is represented by a two character sequence 16#ab# and
 122    --  16#cd#, with both characters being in the upper half set. The internal
 123    --  character code is the corresponding JIS character according to the EUC
 124    --  encoding algorithm. See the body of package System.JIS_Conversions for
 125    --  further details.
 126
 127    WCEM_UTF8 : constant WC_Encoding_Method := 5;
 128    --  An ISO 10646-1 BMP/Unicode wide character is represented in
 129    --  UCS Transformation Format 8 (UTF-8) as defined in Annex R of ISO
 130    --  10646-1/Am.2.  Depending on the character value, a Unicode character
 131    --  is represented as the one, two, or three byte sequence
 132    --
 133    --    16#0000#-16#007f#: 2#0xxxxxxx#
 134    --    16#0080#-16#07ff#: 2#110xxxxx# 2#10xxxxxx#
 135    --    16#0800#-16#ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
 136    --
 137    --  where the xxx bits correspond to the left-padded bits of the the
 138    --  16-bit character value. Note that all lower half ASCII characters
 139    --  are represented as ASCII bytes and all upper half characters and
 140    --  other wide characters are represented as sequences of upper-half
 141    --  (The full UTF-8 scheme allows for encoding 31-bit characters as
 142    --  6-byte sequences, but in this implementation, all UTF-8 sequences
 143    --  of four or more bytes length will raise a Constraint_Error, as
 144    --  will all illegal UTF-8 sequences.)
 145
 146    WCEM_Brackets : constant WC_Encoding_Method := 6;
 147    --  A wide character is represented as the sequence ["abcd"] where abcd
 148    --  are four hexadecimal characters. In this mode, the sequence ["ab"]
 149    --  is also recognized for the case of character codes in the range 0-255.
 150
 151    WC_Encoding_Letters : constant array (WC_Encoding_Method) of Character :=
 152      (WCEM_Hex       => 'h',
 153       WCEM_Upper     => 'u',
 154       WCEM_Shift_JIS => 's',
 155       WCEM_EUC       => 'e',
 156       WCEM_UTF8      => '8',
 157       WCEM_Brackets  => 'b');
 158    --  Letters used for selection of wide character encoding method in the
 159    --  compiler options (-gnatW? switch) and for Wide_Text_IO (WCEM parameter
 160    --  in the form string).
 161
 162    subtype WC_ESC_Encoding_Method is
 163      WC_Encoding_Method range WCEM_Hex .. WCEM_Hex;
 164    --  Encoding methods using an ESC character at the start of the sequence.
 165
 166    subtype WC_Upper_Half_Encoding_Method is
 167      WC_Encoding_Method range WCEM_Upper .. WCEM_UTF8;
 168    --  Encoding methods using an upper half character (16#80#..16#FF) at
 169    --  the start of the sequence.
 170
 171    WC_Longest_Sequence : constant := 8;
 172    --  The longest number of characters that can be used for a wide
 173    --  character sequence for any of the active encoding methods.
 174
 175 end System.WCh_Con;