gcc/ada/a-zchuni.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT RUN-TIME COMPONENTS                         --
   4 --                                                                          --
   5 --    A D A . W I D E _ W I D E _ C H A R A C T E R T S . U N I C O D E    --
   6 --                                                                          --
   7 --                                 S p e c                                  --
   8 --                                                                          --
   9 --            Copyright (C) 2005, 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,  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 --  Unicode categorization routines for Wide_Wide_Character
  35
  36 with GNAT.UTF_32;
  37
  38 package Ada.Wide_Wide_Characters.Unicode is
  39
  40    --  The following type defines the categories from the unicode definitions.
  41    --  The one addition we make is Fe, which represents the characters FFFE
  42    --  and FFFF in any of the planes.
  43
  44    type Category is new GNAT.UTF_32.Category;
  45    --  Cc   Other, Control
  46    --  Cf   Other, Format
  47    --  Cn   Other, Not Assigned
  48    --  Co   Other, Private Use
  49    --  Cs   Other, Surrogate
  50    --  Ll   Letter, Lowercase
  51    --  Lm   Letter, Modifier
  52    --  Lo   Letter, Other
  53    --  Lt   Letter, Titlecase
  54    --  Lu   Letter, Uppercase
  55    --  Mc   Mark, Spacing Combining
  56    --  Me   Mark, Enclosing
  57    --  Mn   Mark, Nonspacing
  58    --  Nd   Number, Decimal Digit
  59    --  Nl   Number, Letter
  60    --  No   Number, Other
  61    --  Pc   Punctuation, Connector
  62    --  Pd   Punctuation, Dash
  63    --  Pe   Punctuation, Close
  64    --  Pf   Punctuation, Final quote
  65    --  Pi   Punctuation, Initial quote
  66    --  Po   Punctuation, Other
  67    --  Ps   Punctuation, Open
  68    --  Sc   Symbol, Currency
  69    --  Sk   Symbol, Modifier
  70    --  Sm   Symbol, Math
  71    --  So   Symbol, Other
  72    --  Zl   Separator, Line
  73    --  Zp   Separator, Paragraph
  74    --  Zs   Separator, Space
  75    --  Fe   relative position FFFE/FFFF in plane
  76
  77    function Get_Category (U : Wide_Wide_Character) return Category;
  78    pragma Inline (Get_Category);
  79    --  Given a Wide_Wide_Character, returns corresponding Category, or Cn if
  80    --  the code does not have an assigned unicode category.
  81
  82    --  The following functions perform category tests corresponding to lexical
  83    --  classes defined in the Ada standard. There are two interfaces for each
  84    --  function. The second takes a Category (e.g. returned by Get_Category).
  85    --  The first takes a Wide_Wide_Character. The form taking the
  86    --  Wide_Wide_Character is typically more efficient than calling
  87    --  Get_Category, but if several different tests are to be performed on the
  88    --  same code, it is more efficient to use Get_Category to get the category,
  89    --  then test the resulting category.
  90
  91    function Is_Letter (U : Wide_Wide_Character) return Boolean;
  92    function Is_Letter (C : Category)            return Boolean;
  93    pragma Inline (Is_Letter);
  94    --  Returns true iff U is a letter that can be used to start an identifier,
  95    --  or if C is one of the corresponding categories, which are the following:
  96    --    Letter, Uppercase (Lu)
  97    --    Letter, Lowercase (Ll)
  98    --    Letter, Titlecase (Lt)
  99    --    Letter, Modifier  (Lm)
 100    --    Letter, Other     (Lo)
 101    --    Number, Letter    (Nl)
 102
 103    function Is_Digit (U : Wide_Wide_Character) return Boolean;
 104    function Is_Digit (C : Category)            return Boolean;
 105    pragma Inline (Is_Digit);
 106    --  Returns true iff U is a digit that can be used to extend an identifer,
 107    --  or if C is one of the corresponding categories, which are the following:
 108    --    Number, Decimal_Digit (Nd)
 109
 110    function Is_Line_Terminator (U : Wide_Wide_Character) return Boolean;
 111    pragma Inline (Is_Line_Terminator);
 112    --  Returns true iff U is an allowed line terminator for source programs,
 113    --  if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
 114    --  Line), or if U is a conventional line terminator (CR, LF, VT, FF).
 115    --  There is no category version for this function, since the set of
 116    --  characters does not correspond to a set of Unicode categories.
 117
 118    function Is_Mark (U : Wide_Wide_Character) return Boolean;
 119    function Is_Mark (C : Category)            return Boolean;
 120    pragma Inline (Is_Mark);
 121    --  Returns true iff U is a mark character which can be used to extend an
 122    --  identifier, or if C is one of the corresponding categories, which are
 123    --  the following:
 124    --    Mark, Non-Spacing (Mn)
 125    --    Mark, Spacing Combining (Mc)
 126
 127    function Is_Other (U : Wide_Wide_Character) return Boolean;
 128    function Is_Other (C : Category)            return Boolean;
 129    pragma Inline (Is_Other);
 130    --  Returns true iff U is an other format character, which means that it
 131    --  can be used to extend an identifier, but is ignored for the purposes of
 132    --  matching of identiers, or if C is one of the corresponding categories,
 133    --  which are the following:
 134    --    Other, Format (Cf)
 135
 136    function Is_Punctuation (U : Wide_Wide_Character) return Boolean;
 137    function Is_Punctuation (C : Category)            return Boolean;
 138    pragma Inline (Is_Punctuation);
 139    --  Returns true iff U is a punctuation character that can be used to
 140    --  separate pices of an identifier, or if C is one of the corresponding
 141    --  categories, which are the following:
 142    --    Punctuation, Connector (Pc)
 143
 144    function Is_Space (U : Wide_Wide_Character) return Boolean;
 145    function Is_Space (C : Category)            return Boolean;
 146    pragma Inline (Is_Space);
 147    --  Returns true iff U is considered a space to be ignored, or if C is one
 148    --  of the corresponding categories, which are the following:
 149    --    Separator, Space (Zs)
 150
 151    function Is_Non_Graphic (U : Wide_Wide_Character) return Boolean;
 152    function Is_Non_Graphic (C : Category)            return Boolean;
 153    pragma Inline (Is_Non_Graphic);
 154    --  Returns true iff U is considered to be a non-graphic character, or if C
 155    --  is one of the corresponding categories, which are the following:
 156    --    Other, Control (Cc)
 157    --    Other, Private Use (Co)
 158    --    Other, Surrogate (Cs)
 159    --    Separator, Line (Zl)
 160    --    Separator, Paragraph (Zp)
 161    --    FFFE or FFFF positions in any plane (Fe)
 162    --
 163    --  Note that the Ada category format effector is subsumed by the above
 164    --  list of Unicode categories.
 165    --
 166    --  Note that Other, Unassiged (Cn) is quite deliberately not included
 167    --  in the list of categories above. This means that should any of these
 168    --  code positions be defined in future with graphic characters they will
 169    --  be allowed without a need to change implementations or the standard.
 170    --
 171    --  Note that Other, Format (Cf) is also quite deliberately not included
 172    --  in the list of categories above. This means that these characters can
 173    --  be included in character and string literals.
 174
 175    --  The following function is used to fold to upper case, as required by
 176    --  the Ada 2005 standard rules for identifier case folding. Two
 177    --  identifiers are equivalent if they are identical after folding all
 178    --  letters to upper case using this routine.
 179
 180    function To_Upper_Case
 181      (U : Wide_Wide_Character) return Wide_Wide_Character;
 182    pragma Inline (To_Upper_Case);
 183    --  If U represents a lower case letter, returns the corresponding upper
 184    --  case letter, otherwise U is returned unchanged. The folding is locale
 185    --  independent as defined by documents referenced in the note in section
 186    --  1 of ISO/IEC 10646:2003
 187
 188 end Ada.Wide_Wide_Characters.Unicode;