1 |
281 |
jeremybenn |
------------------------------------------------------------------------------
|
2 |
|
|
-- --
|
3 |
|
|
-- GNAT RUN-TIME COMPONENTS --
|
4 |
|
|
-- --
|
5 |
|
|
-- S Y S T E M . U T F _ 3 2 --
|
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 |
|
|
-- This package is an internal package that provides basic character
|
33 |
|
|
-- classification capabilities needed by the compiler for handling full
|
34 |
|
|
-- 32-bit wide wide characters. We avoid the use of the actual type
|
35 |
|
|
-- Wide_Wide_Character, since we want to use these routines in the compiler
|
36 |
|
|
-- itself, and we want to be able to compile the compiler with old versions
|
37 |
|
|
-- of GNAT that did not implement Wide_Wide_Character.
|
38 |
|
|
|
39 |
|
|
-- System.UTF_32 should not be directly used from an application program, but
|
40 |
|
|
-- an equivalent package GNAT.UTF_32 can be used directly and provides exactly
|
41 |
|
|
-- the same services. The reason this package is in System is so that it can
|
42 |
|
|
-- with'ed by other packages in the Ada and System hierarchies.
|
43 |
|
|
|
44 |
|
|
pragma Compiler_Unit;
|
45 |
|
|
|
46 |
|
|
package System.UTF_32 is
|
47 |
|
|
|
48 |
|
|
type UTF_32 is range 0 .. 16#7FFF_FFFF#;
|
49 |
|
|
-- So far, the only defined character codes are in 0 .. 16#01_FFFF#
|
50 |
|
|
|
51 |
|
|
-- The following type defines the categories from the unicode definitions.
|
52 |
|
|
-- The one addition we make is Fe, which represents the characters FFFE
|
53 |
|
|
-- and FFFF in any of the planes.
|
54 |
|
|
|
55 |
|
|
type Category is (
|
56 |
|
|
Cc, -- Other, Control
|
57 |
|
|
Cf, -- Other, Format
|
58 |
|
|
Cn, -- Other, Not Assigned
|
59 |
|
|
Co, -- Other, Private Use
|
60 |
|
|
Cs, -- Other, Surrogate
|
61 |
|
|
Ll, -- Letter, Lowercase
|
62 |
|
|
Lm, -- Letter, Modifier
|
63 |
|
|
Lo, -- Letter, Other
|
64 |
|
|
Lt, -- Letter, Titlecase
|
65 |
|
|
Lu, -- Letter, Uppercase
|
66 |
|
|
Mc, -- Mark, Spacing Combining
|
67 |
|
|
Me, -- Mark, Enclosing
|
68 |
|
|
Mn, -- Mark, Nonspacing
|
69 |
|
|
Nd, -- Number, Decimal Digit
|
70 |
|
|
Nl, -- Number, Letter
|
71 |
|
|
No, -- Number, Other
|
72 |
|
|
Pc, -- Punctuation, Connector
|
73 |
|
|
Pd, -- Punctuation, Dash
|
74 |
|
|
Pe, -- Punctuation, Close
|
75 |
|
|
Pf, -- Punctuation, Final quote
|
76 |
|
|
Pi, -- Punctuation, Initial quote
|
77 |
|
|
Po, -- Punctuation, Other
|
78 |
|
|
Ps, -- Punctuation, Open
|
79 |
|
|
Sc, -- Symbol, Currency
|
80 |
|
|
Sk, -- Symbol, Modifier
|
81 |
|
|
Sm, -- Symbol, Math
|
82 |
|
|
So, -- Symbol, Other
|
83 |
|
|
Zl, -- Separator, Line
|
84 |
|
|
Zp, -- Separator, Paragraph
|
85 |
|
|
Zs, -- Separator, Space
|
86 |
|
|
Fe); -- relative position FFFE/FFFF in any plane
|
87 |
|
|
|
88 |
|
|
function Get_Category (U : UTF_32) return Category;
|
89 |
|
|
-- Given a UTF32 code, returns corresponding Category, or Cn if
|
90 |
|
|
-- the code does not have an assigned unicode category.
|
91 |
|
|
|
92 |
|
|
-- The following functions perform category tests corresponding to lexical
|
93 |
|
|
-- classes defined in the Ada standard. There are two interfaces for each
|
94 |
|
|
-- function. The second takes a Category (e.g. returned by Get_Category).
|
95 |
|
|
-- The first takes a UTF_32 code. The form taking the UTF_32 code is
|
96 |
|
|
-- typically more efficient than calling Get_Category, but if several
|
97 |
|
|
-- different tests are to be performed on the same code, it is more
|
98 |
|
|
-- efficient to use Get_Category to get the category, then test the
|
99 |
|
|
-- resulting category.
|
100 |
|
|
|
101 |
|
|
function Is_UTF_32_Letter (U : UTF_32) return Boolean;
|
102 |
|
|
function Is_UTF_32_Letter (C : Category) return Boolean;
|
103 |
|
|
pragma Inline (Is_UTF_32_Letter);
|
104 |
|
|
-- Returns true iff U is a letter that can be used to start an identifier,
|
105 |
|
|
-- or if C is one of the corresponding categories, which are the following:
|
106 |
|
|
-- Letter, Uppercase (Lu)
|
107 |
|
|
-- Letter, Lowercase (Ll)
|
108 |
|
|
-- Letter, Titlecase (Lt)
|
109 |
|
|
-- Letter, Modifier (Lm)
|
110 |
|
|
-- Letter, Other (Lo)
|
111 |
|
|
-- Number, Letter (Nl)
|
112 |
|
|
|
113 |
|
|
function Is_UTF_32_Digit (U : UTF_32) return Boolean;
|
114 |
|
|
function Is_UTF_32_Digit (C : Category) return Boolean;
|
115 |
|
|
pragma Inline (Is_UTF_32_Digit);
|
116 |
|
|
-- Returns true iff U is a digit that can be used to extend an identifier,
|
117 |
|
|
-- or if C is one of the corresponding categories, which are the following:
|
118 |
|
|
-- Number, Decimal_Digit (Nd)
|
119 |
|
|
|
120 |
|
|
function Is_UTF_32_Line_Terminator (U : UTF_32) return Boolean;
|
121 |
|
|
pragma Inline (Is_UTF_32_Line_Terminator);
|
122 |
|
|
-- Returns true iff U is an allowed line terminator for source programs,
|
123 |
|
|
-- if U is in the category Zp (Separator, Paragraph), or Zs (Separator,
|
124 |
|
|
-- Line), or if U is a conventional line terminator (CR, LF, VT, FF).
|
125 |
|
|
-- There is no category version for this function, since the set of
|
126 |
|
|
-- characters does not correspond to a set of Unicode categories.
|
127 |
|
|
|
128 |
|
|
function Is_UTF_32_Mark (U : UTF_32) return Boolean;
|
129 |
|
|
function Is_UTF_32_Mark (C : Category) return Boolean;
|
130 |
|
|
pragma Inline (Is_UTF_32_Mark);
|
131 |
|
|
-- Returns true iff U is a mark character which can be used to extend an
|
132 |
|
|
-- identifier, or if C is one of the corresponding categories, which are
|
133 |
|
|
-- the following:
|
134 |
|
|
-- Mark, Non-Spacing (Mn)
|
135 |
|
|
-- Mark, Spacing Combining (Mc)
|
136 |
|
|
|
137 |
|
|
function Is_UTF_32_Other (U : UTF_32) return Boolean;
|
138 |
|
|
function Is_UTF_32_Other (C : Category) return Boolean;
|
139 |
|
|
pragma Inline (Is_UTF_32_Other);
|
140 |
|
|
-- Returns true iff U is an other format character, which means that it
|
141 |
|
|
-- can be used to extend an identifier, but is ignored for the purposes of
|
142 |
|
|
-- matching of identifiers, or if C is one of the corresponding categories,
|
143 |
|
|
-- which are the following:
|
144 |
|
|
-- Other, Format (Cf)
|
145 |
|
|
|
146 |
|
|
function Is_UTF_32_Punctuation (U : UTF_32) return Boolean;
|
147 |
|
|
function Is_UTF_32_Punctuation (C : Category) return Boolean;
|
148 |
|
|
pragma Inline (Is_UTF_32_Punctuation);
|
149 |
|
|
-- Returns true iff U is a punctuation character that can be used to
|
150 |
|
|
-- separate pieces of an identifier, or if C is one of the corresponding
|
151 |
|
|
-- categories, which are the following:
|
152 |
|
|
-- Punctuation, Connector (Pc)
|
153 |
|
|
|
154 |
|
|
function Is_UTF_32_Space (U : UTF_32) return Boolean;
|
155 |
|
|
function Is_UTF_32_Space (C : Category) return Boolean;
|
156 |
|
|
pragma Inline (Is_UTF_32_Space);
|
157 |
|
|
-- Returns true iff U is considered a space to be ignored, or if C is one
|
158 |
|
|
-- of the corresponding categories, which are the following:
|
159 |
|
|
-- Separator, Space (Zs)
|
160 |
|
|
|
161 |
|
|
function Is_UTF_32_Non_Graphic (U : UTF_32) return Boolean;
|
162 |
|
|
function Is_UTF_32_Non_Graphic (C : Category) return Boolean;
|
163 |
|
|
pragma Inline (Is_UTF_32_Non_Graphic);
|
164 |
|
|
-- Returns true iff U is considered to be a non-graphic character, or if C
|
165 |
|
|
-- is one of the corresponding categories, which are the following:
|
166 |
|
|
-- Other, Control (Cc)
|
167 |
|
|
-- Other, Private Use (Co)
|
168 |
|
|
-- Other, Surrogate (Cs)
|
169 |
|
|
-- Separator, Line (Zl)
|
170 |
|
|
-- Separator, Paragraph (Zp)
|
171 |
|
|
-- FFFE or FFFF positions in any plane (Fe)
|
172 |
|
|
--
|
173 |
|
|
-- Note that the Ada category format effector is subsumed by the above
|
174 |
|
|
-- list of Unicode categories.
|
175 |
|
|
--
|
176 |
|
|
-- Note that Other, Unassigned (Cn) is quite deliberately not included
|
177 |
|
|
-- in the list of categories above. This means that should any of these
|
178 |
|
|
-- code positions be defined in future with graphic characters they will
|
179 |
|
|
-- be allowed without a need to change implementations or the standard.
|
180 |
|
|
--
|
181 |
|
|
-- Note that Other, Format (Cf) is also quite deliberately not included
|
182 |
|
|
-- in the list of categories above. This means that these characters can
|
183 |
|
|
-- be included in character and string literals.
|
184 |
|
|
|
185 |
|
|
-- The following function is used to fold to upper case, as required by
|
186 |
|
|
-- the Ada 2005 standard rules for identifier case folding. Two
|
187 |
|
|
-- identifiers are equivalent if they are identical after folding all
|
188 |
|
|
-- letters to upper case using this routine.
|
189 |
|
|
|
190 |
|
|
function UTF_32_To_Upper_Case (U : UTF_32) return UTF_32;
|
191 |
|
|
pragma Inline (UTF_32_To_Upper_Case);
|
192 |
|
|
-- If U represents a lower case letter, returns the corresponding upper
|
193 |
|
|
-- case letter, otherwise U is returned unchanged. The folding is locale
|
194 |
|
|
-- independent as defined by documents referenced in the note in section
|
195 |
|
|
-- 1 of ISO/IEC 10646:2003
|
196 |
|
|
|
197 |
|
|
end System.UTF_32;
|