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) 2005-2009, 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 --  Unicode categorization routines for Wide_Character. Note that this
  33 --  package is strictly speaking Ada 2005 (since it is a child of an
  34 --  Ada 2005 unit), but we make it available in Ada 95 mode, since it
  35 --  only deals with wide characters.
  36
  37 with System.UTF_32;
  38
  39 package Ada.Wide_Characters.Unicode is
  40
  41    --  The following type defines the categories from the unicode definitions.
  42    --  The one addition we make is Fe, which represents the characters FFFE
  43    --  and FFFF in any of the planes.
  44
  45    type Category is new System.UTF_32.Category;
  46    --  Cc   Other, Control
  47    --  Cf   Other, Format
  48    --  Cn   Other, Not Assigned
  49    --  Co   Other, Private Use
  50    --  Cs   Other, Surrogate
  51    --  Ll   Letter, Lowercase
  52    --  Lm   Letter, Modifier
  53    --  Lo   Letter, Other
  54    --  Lt   Letter, Titlecase
  55    --  Lu   Letter, Uppercase
  56    --  Mc   Mark, Spacing Combining
  57    --  Me   Mark, Enclosing
  58    --  Mn   Mark, Nonspacing
  59    --  Nd   Number, Decimal Digit
  60    --  Nl   Number, Letter
  61    --  No   Number, Other
  62    --  Pc   Punctuation, Connector
  63    --  Pd   Punctuation, Dash
  64    --  Pe   Punctuation, Close
  65    --  Pf   Punctuation, Final quote
  66    --  Pi   Punctuation, Initial quote
  67    --  Po   Punctuation, Other
  68    --  Ps   Punctuation, Open
  69    --  Sc   Symbol, Currency
  70    --  Sk   Symbol, Modifier
  71    --  Sm   Symbol, Math
  72    --  So   Symbol, Other
  73    --  Zl   Separator, Line
  74    --  Zp   Separator, Paragraph
  75    --  Zs   Separator, Space
  76    --  Fe   relative position FFFE/FFFF in plane
  77
  78    function Get_Category (U : Wide_Character) return Category;
  79    pragma Inline (Get_Category);
  80    --  Given a Wide_Character, returns corresponding Category, or Cn if the
  81    --  code does not have an assigned unicode category.
  82
  83    --  The following functions perform category tests corresponding to lexical
  84    --  classes defined in the Ada standard. There are two interfaces for each
  85    --  function. The second takes a Category (e.g. returned by Get_Category).
  86    --  The first takes a Wide_Character. The form taking the Wide_Character is
  87    --  typically more efficient than calling Get_Category, but if several
  88    --  different tests are to be performed on the same code, it is more
  89    --  efficient to use Get_Category to get the category, then test the
  90    --  resulting category.
  91
  92    function Is_Letter (U : Wide_Character) return Boolean;
  93    function Is_Letter (C : Category)       return Boolean;
  94    pragma Inline (Is_Letter);
  95    --  Returns true iff U is a letter that can be used to start an identifier,
  96    --  or if C is one of the corresponding categories, which are the following:
  97    --    Letter, Uppercase (Lu)
  98    --    Letter, Lowercase (Ll)
  99    --    Letter, Titlecase (Lt)
 100    --    Letter, Modifier  (Lm)
 101    --    Letter, Other     (Lo)
 102    --    Number, Letter    (Nl)
 103
 104    function Is_Digit (U : Wide_Character) return Boolean;
 105    function Is_Digit (C : Category)       return Boolean;
 106    pragma Inline (Is_Digit);
 107    --  Returns true iff U is a digit that can be used to extend an identifer,
 108    --  or if C is one of the corresponding categories, which are the following:
 109    --    Number, Decimal_Digit (Nd)
 110
 111    function Is_Line_Terminator (U : Wide_Character) return Boolean;
 112    pragma Inline (Is_Line_Terminator);
 113    --  Returns true iff U is an allowed line terminator for source programs,
 114    --  if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
 115    --  Line), or if U is a conventional line terminator (CR, LF, VT, FF).
 116    --  There is no category version for this function, since the set of
 117    --  characters does not correspond to a set of Unicode categories.
 118
 119    function Is_Mark (U : Wide_Character) return Boolean;
 120    function Is_Mark (C : Category)       return Boolean;
 121    pragma Inline (Is_Mark);
 122    --  Returns true iff U is a mark character which can be used to extend an
 123    --  identifier, or if C is one of the corresponding categories, which are
 124    --  the following:
 125    --    Mark, Non-Spacing (Mn)
 126    --    Mark, Spacing Combining (Mc)
 127
 128    function Is_Other (U : Wide_Character) return Boolean;
 129    function Is_Other (C : Category)       return Boolean;
 130    pragma Inline (Is_Other);
 131    --  Returns true iff U is an other format character, which means that it
 132    --  can be used to extend an identifier, but is ignored for the purposes of
 133    --  matching of identiers, or if C is one of the corresponding categories,
 134    --  which are the following:
 135    --    Other, Format (Cf)
 136
 137    function Is_Punctuation (U : Wide_Character) return Boolean;
 138    function Is_Punctuation (C : Category)       return Boolean;
 139    pragma Inline (Is_Punctuation);
 140    --  Returns true iff U is a punctuation character that can be used to
 141    --  separate pices of an identifier, or if C is one of the corresponding
 142    --  categories, which are the following:
 143    --    Punctuation, Connector (Pc)
 144
 145    function Is_Space (U : Wide_Character) return Boolean;
 146    function Is_Space (C : Category)       return Boolean;
 147    pragma Inline (Is_Space);
 148    --  Returns true iff U is considered a space to be ignored, or if C is one
 149    --  of the corresponding categories, which are the following:
 150    --    Separator, Space (Zs)
 151
 152    function Is_Non_Graphic (U : Wide_Character) return Boolean;
 153    function Is_Non_Graphic (C : Category)       return Boolean;
 154    pragma Inline (Is_Non_Graphic);
 155    --  Returns true iff U is considered to be a non-graphic character, or if C
 156    --  is one of the corresponding categories, which are the following:
 157    --    Other, Control (Cc)
 158    --    Other, Private Use (Co)
 159    --    Other, Surrogate (Cs)
 160    --    Separator, Line (Zl)
 161    --    Separator, Paragraph (Zp)
 162    --    FFFE or FFFF positions in any plane (Fe)
 163    --
 164    --  Note that the Ada category format effector is subsumed by the above
 165    --  list of Unicode categories.
 166    --
 167    --  Note that Other, Unassiged (Cn) is quite deliberately not included
 168    --  in the list of categories above. This means that should any of these
 169    --  code positions be defined in future with graphic characters they will
 170    --  be allowed without a need to change implementations or the standard.
 171    --
 172    --  Note that Other, Format (Cf) is also quite deliberately not included
 173    --  in the list of categories above. This means that these characters can
 174    --  be included in character and string literals.
 175
 176    --  The following function is used to fold to upper case, as required by
 177    --  the Ada 2005 standard rules for identifier case folding. Two
 178    --  identifiers are equivalent if they are identical after folding all
 179    --  letters to upper case using this routine.
 180
 181    function To_Upper_Case (U : Wide_Character) return 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_Characters.Unicode;