1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
|
------------------------------------------------------------------------------
-- --
-- GNAT RUN-TIME COMPONENTS --
-- --
-- G N A T . U T F _ 3 2 --
-- --
-- S p e c --
-- --
-- Copyright (C) 2005 Free Software Foundation, Inc. --
-- --
-- GNAT is free software; you can redistribute it and/or modify it under --
-- terms of the GNU General Public License as published by the Free Soft- --
-- ware Foundation; either version 2, or (at your option) any later ver- --
-- sion. GNAT is distributed in the hope that it will be useful, but WITH- --
-- OUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY --
-- or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License --
-- for more details. You should have received a copy of the GNU General --
-- Public License distributed with GNAT; see file COPYING. If not, write --
-- to the Free Software Foundation, 51 Franklin Street, Fifth Floor, --
-- Boston, MA 02110-1301, USA. --
-- --
-- As a special exception, if other files instantiate generics from this --
-- unit, or you link this unit with other files to produce an executable, --
-- this unit does not by itself cause the resulting executable to be --
-- covered by the GNU General Public License. This exception does not --
-- however invalidate any other reasons why the executable file might be --
-- covered by the GNU Public License. --
-- --
-- GNAT was originally developed by the GNAT team at New York University. --
-- Extensive contributions were provided by Ada Core Technologies Inc. --
-- --
------------------------------------------------------------------------------
-- This package is an internal package that provides basic character
-- classification capabilities needed by the compiler for handling full
-- 32-bit wide wide characters. We avoid the use of the actual type
-- Wide_Wide_Character, since we want to use these routines in the compiler
-- itself, and we want to be able to compile the compiler with old versions
-- of GNAT that did not implement Wide_Wide_Character.
-- This package is available directly for use in application programs,
-- and also serves as the basis for Ada.Wide_Wide_Characters.Unicode and
-- Ada.Wide_Characters.Unicode, which can also be used directly.
package GNAT.UTF_32 is
type UTF_32 is range 0 .. 16#7FFF_FFFF#;
-- So far, the only defined character codes are in 0 .. 16#01_FFFF#
-- The following type defines the categories from the unicode definitions.
-- The one addition we make is Fe, which represents the characters FFFE
-- and FFFF in any of the planes.
type Category is (
Cc, -- Other, Control
Cf, -- Other, Format
Cn, -- Other, Not Assigned
Co, -- Other, Private Use
Cs, -- Other, Surrogate
Ll, -- Letter, Lowercase
Lm, -- Letter, Modifier
Lo, -- Letter, Other
Lt, -- Letter, Titlecase
Lu, -- Letter, Uppercase
Mc, -- Mark, Spacing Combining
Me, -- Mark, Enclosing
Mn, -- Mark, Nonspacing
Nd, -- Number, Decimal Digit
Nl, -- Number, Letter
No, -- Number, Other
Pc, -- Punctuation, Connector
Pd, -- Punctuation, Dash
Pe, -- Punctuation, Close
Pf, -- Punctuation, Final quote
Pi, -- Punctuation, Initial quote
Po, -- Punctuation, Other
Ps, -- Punctuation, Open
Sc, -- Symbol, Currency
Sk, -- Symbol, Modifier
Sm, -- Symbol, Math
So, -- Symbol, Other
Zl, -- Separator, Line
Zp, -- Separator, Paragraph
Zs, -- Separator, Space
Fe); -- relative position FFFE/FFFF in any plane
function Get_Category (U : UTF_32) return Category;
-- Given a UTF32 code, returns corresponding Category, or Cn if
-- the code does not have an assigned unicode category.
-- The following functions perform category tests corresponding to lexical
-- classes defined in the Ada standard. There are two interfaces for each
-- function. The second takes a Category (e.g. returned by Get_Category).
-- The first takes a UTF_32 code. The form taking the UTF_32 code is
-- typically more efficient than calling Get_Category, but if several
-- different tests are to be performed on the same code, it is more
-- efficient to use Get_Category to get the category, then test the
-- resulting category.
function Is_UTF_32_Letter (U : UTF_32) return Boolean;
function Is_UTF_32_Letter (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Letter);
-- Returns true iff U is a letter that can be used to start an identifier,
-- or if C is one of the corresponding categories, which are the following:
-- Letter, Uppercase (Lu)
-- Letter, Lowercase (Ll)
-- Letter, Titlecase (Lt)
-- Letter, Modifier (Lm)
-- Letter, Other (Lo)
-- Number, Letter (Nl)
function Is_UTF_32_Digit (U : UTF_32) return Boolean;
function Is_UTF_32_Digit (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Digit);
-- Returns true iff U is a digit that can be used to extend an identifer,
-- or if C is one of the corresponding categories, which are the following:
-- Number, Decimal_Digit (Nd)
function Is_UTF_32_Line_Terminator (U : UTF_32) return Boolean;
pragma Inline (Is_UTF_32_Line_Terminator);
-- Returns true iff U is an allowed line terminator for source programs,
-- if U is in the category Zp (Separator, Paragaph), or Zs (Separator,
-- Line), or if U is a conventional line terminator (CR, LF, VT, FF).
-- There is no category version for this function, since the set of
-- characters does not correspond to a set of Unicode categories.
function Is_UTF_32_Mark (U : UTF_32) return Boolean;
function Is_UTF_32_Mark (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Mark);
-- Returns true iff U is a mark character which can be used to extend an
-- identifier, or if C is one of the corresponding categories, which are
-- the following:
-- Mark, Non-Spacing (Mn)
-- Mark, Spacing Combining (Mc)
function Is_UTF_32_Other (U : UTF_32) return Boolean;
function Is_UTF_32_Other (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Other);
-- Returns true iff U is an other format character, which means that it
-- can be used to extend an identifier, but is ignored for the purposes of
-- matching of identiers, or if C is one of the corresponding categories,
-- which are the following:
-- Other, Format (Cf)
function Is_UTF_32_Punctuation (U : UTF_32) return Boolean;
function Is_UTF_32_Punctuation (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Punctuation);
-- Returns true iff U is a punctuation character that can be used to
-- separate pices of an identifier, or if C is one of the corresponding
-- categories, which are the following:
-- Punctuation, Connector (Pc)
function Is_UTF_32_Space (U : UTF_32) return Boolean;
function Is_UTF_32_Space (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Space);
-- Returns true iff U is considered a space to be ignored, or if C is one
-- of the corresponding categories, which are the following:
-- Separator, Space (Zs)
function Is_UTF_32_Non_Graphic (U : UTF_32) return Boolean;
function Is_UTF_32_Non_Graphic (C : Category) return Boolean;
pragma Inline (Is_UTF_32_Non_Graphic);
-- Returns true iff U is considered to be a non-graphic character, or if C
-- is one of the corresponding categories, which are the following:
-- Other, Control (Cc)
-- Other, Private Use (Co)
-- Other, Surrogate (Cs)
-- Separator, Line (Zl)
-- Separator, Paragraph (Zp)
-- FFFE or FFFF positions in any plane (Fe)
--
-- Note that the Ada category format effector is subsumed by the above
-- list of Unicode categories.
--
-- Note that Other, Unassiged (Cn) is quite deliberately not included
-- in the list of categories above. This means that should any of these
-- code positions be defined in future with graphic characters they will
-- be allowed without a need to change implementations or the standard.
--
-- Note that Other, Format (Cf) is also quite deliberately not included
-- in the list of categories above. This means that these characters can
-- be included in character and string literals.
-- The following function is used to fold to upper case, as required by
-- the Ada 2005 standard rules for identifier case folding. Two
-- identifiers are equivalent if they are identical after folding all
-- letters to upper case using this routine.
function UTF_32_To_Upper_Case (U : UTF_32) return UTF_32;
pragma Inline (UTF_32_To_Upper_Case);
-- If U represents a lower case letter, returns the corresponding upper
-- case letter, otherwise U is returned unchanged. The folding is locale
-- independent as defined by documents referenced in the note in section
-- 1 of ISO/IEC 10646:2003
end GNAT.UTF_32;
|
