gcc/ada/libgnat/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) 1992-2023, 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 3,  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.                                     --
  17 --                                                                          --
  18 -- As a special exception under Section 7 of GPL version 3, you are granted --
  19 -- additional permissions described in the GCC Runtime Library Exception,   --
  20 -- version 3.1, as published by the Free Software Foundation.               --
  21 --                                                                          --
  22 -- You should have received a copy of the GNU General Public License and    --
  23 -- a copy of the GCC Runtime Library Exception along with this program;     --
  24 -- see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see    --
  25 -- <http://www.gnu.org/licenses/>.                                          --
  26 --                                                                          --
  27 -- GNAT was originally developed  by the GNAT team at  New York University. --
  28 -- Extensive contributions were provided by Ada Core Technologies Inc.      --
  29 --                                                                          --
  30 ------------------------------------------------------------------------------
  31
  32 --  This package defines the codes used to identify the encoding method for
  33 --  wide characters in string and character constants. This is needed both
  34 --  at compile time and at runtime (for the wide character runtime routines)
  35
  36 --  This unit may be used directly from an application program by providing
  37 --  an appropriate WITH, and the interface can be expected to remain stable.
  38
  39 package System.WCh_Con is
  40    pragma Pure;
  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 or Wide_Wide_Character value using a one or more
  48    --  Character values. Three 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 by the
  64    --    sequence ["xx"] or ["xxxx"] or ["xxxxxx"] where xx are hexadecimal
  65    --    characters. Note that currently this is the only encoding that
  66    --    supports the full UTF-32 range.
  67
  68    --  Note that GNAT does not currently support escape-in, escape-out
  69    --  encoding methods, where an escape sequence is used to set a mode
  70    --  used to recognize subsequent characters. All encoding methods use
  71    --  individual character-by-character encodings, so that a sequence of
  72    --  wide characters is represented by a sequence of encodings.
  73
  74    --  To add new encoding methods, the following steps are required:
  75
  76    --     1.  Define a code for a new value of type WC_Encoding_Method
  77    --     2.  Adjust the definition of WC_Encoding_Method accordingly
  78    --     3.  Provide appropriate conversion routines in System.WCh_Cnv
  79    --     4.  Adjust definition of WC_Longest_Sequence if necessary
  80    --     5.  Add an entry in WC_Encoding_Letters for the new method
  81    --     6.  Add proper code to s-wchstw.adb, s-wchwts.adb, s-widwch.adb
  82    --     7.  Update documentation (remember section on form strings)
  83
  84    --  Note that the WC_Encoding_Method values must be kept ordered so that
  85    --  the definitions of the subtypes WC_Upper_Half_Encoding_Method and
  86    --  WC_ESC_Encoding_Method are still correct.
  87
  88    ---------------------------------
  89    -- Encoding Method Definitions --
  90    ---------------------------------
  91
  92    type WC_Encoding_Method is range 1 .. 6;
  93    --  Type covering the range of values used to represent wide character
  94    --  encoding methods. An enumeration type might be a little neater, but
  95    --  more trouble than it's worth, given the need to pass these values
  96    --  from the compiler to the backend, and to record them in the ALI file.
  97
  98    WCEM_Hex : constant WC_Encoding_Method := 1;
  99    --  The wide character with code 16#abcd# is represented by the escape
 100    --  sequence ESC a b c d (five characters, where abcd are ASCII hex
 101    --  characters, using upper case for letters). This method is easy
 102    --  to deal with in external environments that do not support wide
 103    --  characters, and covers the whole 16-bit BMP. Codes larger than
 104    --  16#FFFF# are not representable using this encoding method.
 105
 106    WCEM_Upper : constant WC_Encoding_Method := 2;
 107    --  The wide character with encoding 16#abcd#, where the upper bit is on
 108    --  (i.e. a is in the range 8-F) is represented as two bytes 16#ab# and
 109    --  16#cd#. The second byte may never be a format control character, but
 110    --  is not required to be in the upper half. This method can be also used
 111    --  for shift-JIS or EUC where the internal coding matches the external
 112    --  coding. Codes larger than 16#FFFF# are not representable using this
 113    --  encoding method.
 114
 115    WCEM_Shift_JIS : constant WC_Encoding_Method := 3;
 116    --  A wide character is represented by a two character sequence 16#ab#
 117    --  and 16#cd#, with the restrictions described for upper half encoding
 118    --  as described above. The internal character code is the corresponding
 119    --  JIS character according to the standard algorithm for Shift-JIS
 120    --  conversion. See the body of package System.JIS_Conversions for
 121    --  further details. Codes larger than 16#FFFF are not representable
 122    --  using this encoding method.
 123
 124    WCEM_EUC : constant WC_Encoding_Method := 4;
 125    --  A wide character is represented by a two character sequence 16#ab# and
 126    --  16#cd#, with both characters being in the upper half set. The internal
 127    --  character code is the corresponding JIS character according to the EUC
 128    --  encoding algorithm. See the body of package System.JIS_Conversions for
 129    --  further details. Codes larger than 16#FFFF# are not representable using
 130    --  this encoding method.
 131
 132    WCEM_UTF8 : constant WC_Encoding_Method := 5;
 133    --  An ISO 10646-1 BMP/Unicode wide character is represented in UCS
 134    --  Transformation Format 8 (UTF-8), as defined in Annex R of ISO
 135    --  10646-1/Am.2. Depending on the character value, a Unicode character
 136    --  is represented as the one to six byte sequence.
 137    --
 138    --    16#0000_0000#-16#0000_007f#: 2#0xxxxxxx#
 139    --    16#0000_0080#-16#0000_07ff#: 2#110xxxxx# 2#10xxxxxx#
 140    --    16#0000_0800#-16#0000_ffff#: 2#1110xxxx# 2#10xxxxxx# 2#10xxxxxx#
 141    --    16#0001_0000#-16#001F_FFFF#: 2#11110xxx# 2#10xxxxxx# 2#10xxxxxx#
 142    --                                 2#10xxxxxx#
 143    --    16#0020_0000#-16#03FF_FFFF#: 2#111110xx# 2#10xxxxxx# 2#10xxxxxx#
 144    --                                 2#10xxxxxx# 2#10xxxxxx#
 145    --    16#0400_0000#-16#7FFF_FFFF#: 2#1111110x# 2#10xxxxxx# 2#10xxxxxx#
 146    --                                 2#10xxxxxx# 2#10xxxxxx# 2#10xxxxxx#
 147    --
 148    --  where the xxx bits correspond to the left-padded bits of the
 149    --  16-bit character value. Note that all lower half ASCII characters
 150    --  are represented as ASCII bytes and all upper half characters and
 151    --  other wide characters are represented as sequences of upper-half. This
 152    --  encoding method can represent the entire range of Wide_Wide_Character.
 153
 154    WCEM_Brackets : constant WC_Encoding_Method := 6;
 155    --  A wide character is represented using one of the following sequences:
 156    --
 157    --    ["xx"]
 158    --    ["xxxx"]
 159    --    ["xxxxxx"]
 160    --    ["xxxxxxxx"]
 161    --
 162    --  where xx are hexadecimal digits representing the character code. This
 163    --  encoding method can represent the entire range of Wide_Wide_Character
 164    --  but in the general case results in ambiguous representations (there is
 165    --  no ambiguity in Ada sources, since the above sequences are illegal Ada).
 166
 167    WC_Encoding_Letters : constant array (WC_Encoding_Method) of Character :=
 168      [WCEM_Hex       => 'h',
 169       WCEM_Upper     => 'u',
 170       WCEM_Shift_JIS => 's',
 171       WCEM_EUC       => 'e',
 172       WCEM_UTF8      => '8',
 173       WCEM_Brackets  => 'b'];
 174    --  Letters used for selection of wide character encoding method in the
 175    --  compiler options (-gnatW? switch) and for Wide_Text_IO (WCEM parameter
 176    --  in the form string).
 177
 178    subtype WC_ESC_Encoding_Method is
 179      WC_Encoding_Method range WCEM_Hex .. WCEM_Hex;
 180    --  Encoding methods using an ESC character at the start of the sequence
 181
 182    subtype WC_Upper_Half_Encoding_Method is
 183      WC_Encoding_Method range WCEM_Upper .. WCEM_UTF8;
 184    --  Encoding methods using an upper half character (16#80#..16#FF) at
 185    --  the start of the sequence.
 186
 187    WC_Longest_Sequence : constant := 12;
 188    --  The longest number of characters that can be used for a wide character
 189    --  or wide wide character sequence for any of the active encoding methods.
 190
 191    WC_Longest_Sequences : constant array (WC_Encoding_Method) of Natural :=
 192      [WCEM_Hex       => 5,
 193       WCEM_Upper     => 2,
 194       WCEM_Shift_JIS => 2,
 195       WCEM_EUC       => 2,
 196       WCEM_UTF8      => 6,
 197       WCEM_Brackets  => 12];
 198    --  The longest number of characters that can be used for a wide character
 199    --  or wide wide character sequence using the given encoding method.
 200
 201    function Get_WC_Encoding_Method (C : Character) return WC_Encoding_Method;
 202    --  Given a character C, returns corresponding encoding method (see array
 203    --  WC_Encoding_Letters above). Raises Constraint_Error if not in list.
 204
 205    function Get_WC_Encoding_Method (S : String) return WC_Encoding_Method;
 206    --  Given a lower case string that is one of hex, upper, shift_jis, euc,
 207    --  utf8, brackets, return the corresponding encoding method. Raises
 208    --  Constraint_Error if not in list.
 209
 210    function Is_Start_Of_Encoding
 211      (C  : Character;
 212       EM : WC_Encoding_Method) return Boolean;
 213    pragma Inline (Is_Start_Of_Encoding);
 214    --  Returns True if the Character C is the start of a multi-character
 215    --  encoding sequence for the given encoding method EM. If EM is set to
 216    --  WCEM_Brackets, this function always returns False.
 217
 218 end System.WCh_Con;