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) 2005-2020, 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_Wide_Character
33
34with System.UTF_32;
35
36package Ada.Wide_Wide_Characters.Unicode is
37   pragma Pure;
38
39   --  The following type defines the categories from the unicode definitions.
40   --  The one addition we make is Fe, which represents the characters FFFE
41   --  and FFFF in any of the planes.
42
43   type Category is new System.UTF_32.Category;
44   --  Cc   Other, Control
45   --  Cf   Other, Format
46   --  Cn   Other, Not Assigned
47   --  Co   Other, Private Use
48   --  Cs   Other, Surrogate
49   --  Ll   Letter, Lowercase
50   --  Lm   Letter, Modifier
51   --  Lo   Letter, Other
52   --  Lt   Letter, Titlecase
53   --  Lu   Letter, Uppercase
54   --  Mc   Mark, Spacing Combining
55   --  Me   Mark, Enclosing
56   --  Mn   Mark, Nonspacing
57   --  Nd   Number, Decimal Digit
58   --  Nl   Number, Letter
59   --  No   Number, Other
60   --  Pc   Punctuation, Connector
61   --  Pd   Punctuation, Dash
62   --  Pe   Punctuation, Close
63   --  Pf   Punctuation, Final quote
64   --  Pi   Punctuation, Initial quote
65   --  Po   Punctuation, Other
66   --  Ps   Punctuation, Open
67   --  Sc   Symbol, Currency
68   --  Sk   Symbol, Modifier
69   --  Sm   Symbol, Math
70   --  So   Symbol, Other
71   --  Zl   Separator, Line
72   --  Zp   Separator, Paragraph
73   --  Zs   Separator, Space
74   --  Fe   relative position FFFE/FFFF in plane
75
76   function Get_Category (U : Wide_Wide_Character) return Category;
77   pragma Inline (Get_Category);
78   --  Given a Wide_Wide_Character, returns corresponding Category, or Cn if
79   --  the code does not have an assigned unicode category.
80
81   --  The following functions perform category tests corresponding to lexical
82   --  classes defined in the Ada standard. There are two interfaces for each
83   --  function. The second takes a Category (e.g. returned by Get_Category).
84   --  The first takes a Wide_Wide_Character. The form taking the
85   --  Wide_Wide_Character is typically more efficient than calling
86   --  Get_Category, but if several different tests are to be performed on the
87   --  same code, it is more efficient to use Get_Category to get the category,
88   --  then test the resulting category.
89
90   function Is_Letter (U : Wide_Wide_Character) return Boolean;
91   function Is_Letter (C : Category)            return Boolean;
92   pragma Inline (Is_Letter);
93   --  Returns true iff U is a letter that can be used to start an identifier,
94   --  or if C is one of the corresponding categories, which are the following:
95   --    Letter, Uppercase (Lu)
96   --    Letter, Lowercase (Ll)
97   --    Letter, Titlecase (Lt)
98   --    Letter, Modifier  (Lm)
99   --    Letter, Other     (Lo)
100   --    Number, Letter    (Nl)
101
102   function Is_Digit (U : Wide_Wide_Character) return Boolean;
103   function Is_Digit (C : Category)            return Boolean;
104   pragma Inline (Is_Digit);
105   --  Returns true iff U is a digit that can be used to extend an identifer,
106   --  or if C is one of the corresponding categories, which are the following:
107   --    Number, Decimal_Digit (Nd)
108
109   function Is_Line_Terminator (U : Wide_Wide_Character) return Boolean;
110   pragma Inline (Is_Line_Terminator);
111   --  Returns true iff U is an allowed line terminator for source programs,
112   --  if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
113   --  Line), or if U is a conventional line terminator (CR, LF, VT, FF).
114   --  There is no category version for this function, since the set of
115   --  characters does not correspond to a set of Unicode categories.
116
117   function Is_Mark (U : Wide_Wide_Character) return Boolean;
118   function Is_Mark (C : Category)            return Boolean;
119   pragma Inline (Is_Mark);
120   --  Returns true iff U is a mark character which can be used to extend an
121   --  identifier, or if C is one of the corresponding categories, which are
122   --  the following:
123   --    Mark, Non-Spacing (Mn)
124   --    Mark, Spacing Combining (Mc)
125
126   function Is_Other (U : Wide_Wide_Character) return Boolean;
127   function Is_Other (C : Category)            return Boolean;
128   pragma Inline (Is_Other);
129   --  Returns true iff U is an other format character, which means that it
130   --  can be used to extend an identifier, but is ignored for the purposes of
131   --  matching of identiers, or if C is one of the corresponding categories,
132   --  which are the following:
133   --    Other, Format (Cf)
134
135   function Is_Punctuation (U : Wide_Wide_Character) return Boolean;
136   function Is_Punctuation (C : Category)            return Boolean;
137   pragma Inline (Is_Punctuation);
138   --  Returns true iff U is a punctuation character that can be used to
139   --  separate pices of an identifier, or if C is one of the corresponding
140   --  categories, which are the following:
141   --    Punctuation, Connector (Pc)
142
143   function Is_Space (U : Wide_Wide_Character) return Boolean;
144   function Is_Space (C : Category)            return Boolean;
145   pragma Inline (Is_Space);
146   --  Returns true iff U is considered a space to be ignored, or if C is one
147   --  of the corresponding categories, which are the following:
148   --    Separator, Space (Zs)
149
150   function Is_NFKC (U : Wide_Wide_Character) return Boolean;
151   pragma Inline (Is_NFKC);
152   --  Returns True if the Wide_Wide_Character designated by U could be present
153   --  in a string normalized to Normalization Form KC (as defined by Clause
154   --  21 of ISO/IEC 10646:2017), otherwise returns False.
155
156   function Is_Non_Graphic (U : Wide_Wide_Character) return Boolean;
157   function Is_Non_Graphic (C : Category)            return Boolean;
158   pragma Inline (Is_Non_Graphic);
159   --  Returns true iff U is considered to be a non-graphic character, or if C
160   --  is one of the corresponding categories, which are the following:
161   --    Other, Control (Cc)
162   --    Other, Private Use (Co)
163   --    Other, Surrogate (Cs)
164   --    Separator, Line (Zl)
165   --    Separator, Paragraph (Zp)
166   --    FFFE or FFFF positions in any plane (Fe)
167   --
168   --  Note that the Ada category format effector is subsumed by the above
169   --  list of Unicode categories.
170   --
171   --  Note that Other, Unassiged (Cn) is quite deliberately not included
172   --  in the list of categories above. This means that should any of these
173   --  code positions be defined in future with graphic characters they will
174   --  be allowed without a need to change implementations or the standard.
175   --
176   --  Note that Other, Format (Cf) is also quite deliberately not included
177   --  in the list of categories above. This means that these characters can
178   --  be included in character and string literals.
179
180   --  The following function is used to fold to upper case, as required by
181   --  the Ada 2005 standard rules for identifier case folding. Two
182   --  identifiers are equivalent if they are identical after folding all
183   --  letters to upper case using this routine. A fold to lower routine is
184   --  also provided.
185
186   function To_Lower_Case
187     (U : Wide_Wide_Character) return Wide_Wide_Character;
188   pragma Inline (To_Lower_Case);
189   --  If U represents an upper case letter, returns the corresponding lower
190   --  case letter, otherwise U is returned unchanged. The folding is locale
191   --  independent as defined by documents referenced in the note in section
192   --  1 of ISO/IEC 10646:2003
193
194   function To_Upper_Case
195     (U : Wide_Wide_Character) return Wide_Wide_Character;
196   pragma Inline (To_Upper_Case);
197   --  If U represents a lower case letter, returns the corresponding upper
198   --  case letter, otherwise U is returned unchanged. The folding is locale
199   --  independent as defined by documents referenced in the note in section
200   --  1 of ISO/IEC 10646:2003
201
202end Ada.Wide_Wide_Characters.Unicode;
203