gcc/ada/a-wichun.ads

   1 ------------------------------------------------------------------------------
   2 --                                                                          --
   3 --                         GNAT RUN-TIME COMPONENTS                         --
   4 --                                                                          --
   5 --          A D A . W I D E _ C H A R A C T E R 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_Character. Note that this
  35 --  package is strictly speaking Ada 2005 (since it is a child of an
  36 --  Ada 2005 unit), but we make it available in Ada 95 mode, since it
  37 --  only deals with wide characters.
  38
  39 with GNAT.UTF_32;
  40
  41 package Ada.Wide_Characters.Unicode is
  42
  43    --  The following type defines the categories from the unicode definitions.
  44    --  The one addition we make is Fe, which represents the characters FFFE
  45    --  and FFFF in any of the planes.
  46
  47    type Category is new GNAT.UTF_32.Category;
  48    --  Cc   Other, Control
  49    --  Cf   Other, Format
  50    --  Cn   Other, Not Assigned
  51    --  Co   Other, Private Use
  52    --  Cs   Other, Surrogate
  53    --  Ll   Letter, Lowercase
  54    --  Lm   Letter, Modifier
  55    --  Lo   Letter, Other
  56    --  Lt   Letter, Titlecase
  57    --  Lu   Letter, Uppercase
  58    --  Mc   Mark, Spacing Combining
  59    --  Me   Mark, Enclosing
  60    --  Mn   Mark, Nonspacing
  61    --  Nd   Number, Decimal Digit
  62    --  Nl   Number, Letter
  63    --  No   Number, Other
  64    --  Pc   Punctuation, Connector
  65    --  Pd   Punctuation, Dash
  66    --  Pe   Punctuation, Close
  67    --  Pf   Punctuation, Final quote
  68    --  Pi   Punctuation, Initial quote
  69    --  Po   Punctuation, Other
  70    --  Ps   Punctuation, Open
  71    --  Sc   Symbol, Currency
  72    --  Sk   Symbol, Modifier
  73    --  Sm   Symbol, Math
  74    --  So   Symbol, Other
  75    --  Zl   Separator, Line
  76    --  Zp   Separator, Paragraph
  77    --  Zs   Separator, Space
  78    --  Fe   relative position FFFE/FFFF in plane
  79
  80    function Get_Category (U : Wide_Character) return Category;
  81    pragma Inline (Get_Category);
  82    --  Given a Wide_Character, returns corresponding Category, or Cn if the
  83    --  code does not have an assigned unicode category.
  84
  85    --  The following functions perform category tests corresponding to lexical
  86    --  classes defined in the Ada standard. There are two interfaces for each
  87    --  function. The second takes a Category (e.g. returned by Get_Category).
  88    --  The first takes a Wide_Character. The form taking the Wide_Character is
  89    --  typically more efficient than calling Get_Category, but if several
  90    --  different tests are to be performed on the same code, it is more
  91    --  efficient to use Get_Category to get the category, then test the
  92    --  resulting category.
  93
  94    function Is_Letter (U : Wide_Character) return Boolean;
  95    function Is_Letter (C : Category)       return Boolean;
  96    pragma Inline (Is_Letter);
  97    --  Returns true iff U is a letter that can be used to start an identifier,
  98    --  or if C is one of the corresponding categories, which are the following:
  99    --    Letter, Uppercase (Lu)
 100    --    Letter, Lowercase (Ll)
 101    --    Letter, Titlecase (Lt)
 102    --    Letter, Modifier  (Lm)
 103    --    Letter, Other     (Lo)
 104    --    Number, Letter    (Nl)
 105
 106    function Is_Digit (U : Wide_Character) return Boolean;
 107    function Is_Digit (C : Category)       return Boolean;
 108    pragma Inline (Is_Digit);
 109    --  Returns true iff U is a digit that can be used to extend an identifer,
 110    --  or if C is one of the corresponding categories, which are the following:
 111    --    Number, Decimal_Digit (Nd)
 112
 113    function Is_Line_Terminator (U : Wide_Character) return Boolean;
 114    pragma Inline (Is_Line_Terminator);
 115    --  Returns true iff U is an allowed line terminator for source programs,
 116    --  if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
 117    --  Line), or if U is a conventional line terminator (CR, LF, VT, FF).
 118    --  There is no category version for this function, since the set of
 119    --  characters does not correspond to a set of Unicode categories.
 120
 121    function Is_Mark (U : Wide_Character) return Boolean;
 122    function Is_Mark (C : Category)       return Boolean;
 123    pragma Inline (Is_Mark);
 124    --  Returns true iff U is a mark character which can be used to extend an
 125    --  identifier, or if C is one of the corresponding categories, which are
 126    --  the following:
 127    --    Mark, Non-Spacing (Mn)
 128    --    Mark, Spacing Combining (Mc)
 129
 130    function Is_Other (U : Wide_Character) return Boolean;
 131    function Is_Other (C : Category)       return Boolean;
 132    pragma Inline (Is_Other);
 133    --  Returns true iff U is an other format character, which means that it
 134    --  can be used to extend an identifier, but is ignored for the purposes of
 135    --  matching of identiers, or if C is one of the corresponding categories,
 136    --  which are the following:
 137    --    Other, Format (Cf)
 138
 139    function Is_Punctuation (U : Wide_Character) return Boolean;
 140    function Is_Punctuation (C : Category)       return Boolean;
 141    pragma Inline (Is_Punctuation);
 142    --  Returns true iff U is a punctuation character that can be used to
 143    --  separate pices of an identifier, or if C is one of the corresponding
 144    --  categories, which are the following:
 145    --    Punctuation, Connector (Pc)
 146
 147    function Is_Space (U : Wide_Character) return Boolean;
 148    function Is_Space (C : Category)       return Boolean;
 149    pragma Inline (Is_Space);
 150    --  Returns true iff U is considered a space to be ignored, or if C is one
 151    --  of the corresponding categories, which are the following:
 152    --    Separator, Space (Zs)
 153
 154    function Is_Non_Graphic (U : Wide_Character) return Boolean;
 155    function Is_Non_Graphic (C : Category)       return Boolean;
 156    pragma Inline (Is_Non_Graphic);
 157    --  Returns true iff U is considered to be a non-graphic character, or if C
 158    --  is one of the corresponding categories, which are the following:
 159    --    Other, Control (Cc)
 160    --    Other, Private Use (Co)
 161    --    Other, Surrogate (Cs)
 162    --    Separator, Line (Zl)
 163    --    Separator, Paragraph (Zp)
 164    --    FFFE or FFFF positions in any plane (Fe)
 165    --
 166    --  Note that the Ada category format effector is subsumed by the above
 167    --  list of Unicode categories.
 168    --
 169    --  Note that Other, Unassiged (Cn) is quite deliberately not included
 170    --  in the list of categories above. This means that should any of these
 171    --  code positions be defined in future with graphic characters they will
 172    --  be allowed without a need to change implementations or the standard.
 173    --
 174    --  Note that Other, Format (Cf) is also quite deliberately not included
 175    --  in the list of categories above. This means that these characters can
 176    --  be included in character and string literals.
 177
 178    --  The following function is used to fold to upper case, as required by
 179    --  the Ada 2005 standard rules for identifier case folding. Two
 180    --  identifiers are equivalent if they are identical after folding all
 181    --  letters to upper case using this routine.
 182
 183    function To_Upper_Case (U : Wide_Character) return Wide_Character;
 184    pragma Inline (To_Upper_Case);
 185    --  If U represents a lower case letter, returns the corresponding upper
 186    --  case letter, otherwise U is returned unchanged. The folding is locale
 187    --  independent as defined by documents referenced in the note in section
 188    --  1 of ISO/IEC 10646:2003
 189
 190 end Ada.Wide_Characters.Unicode;