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
|
/* Test of c32width() function.
Copyright (C) 2007-2024 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT 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
along with this program. If not, see <https://www.gnu.org/licenses/>. */
/* Written by Bruno Haible <bruno@clisp.org>, 2007. */
#include <config.h>
#include <uchar.h>
#include "signature.h"
SIGNATURE_CHECK (c32width, int, (char32_t));
#include <locale.h>
#include <string.h>
#include "c-ctype.h"
#include "localcharset.h"
#include "macros.h"
int
main ()
{
char32_t wc;
#if !GNULIB_WCHAR_SINGLE_LOCALE
# ifdef C_CTYPE_ASCII
/* Test width of ASCII characters. */
for (wc = 0x20; wc < 0x7F; wc++)
ASSERT (c32width (wc) == 1);
# endif
#endif
/* Switch to an UTF-8 locale. */
if (setlocale (LC_ALL, "fr_FR.UTF-8") != NULL
/* Check whether it's really an UTF-8 locale.
On OpenBSD 4.0, the setlocale call succeeds only for the LC_CTYPE
category and therefore returns "C/fr_FR.UTF-8/C/C/C/C", but the
LC_CTYPE category is effectively set to an ASCII LC_CTYPE category;
in particular, locale_charset() returns "ASCII". */
&& strcmp (locale_charset (), "UTF-8") == 0)
{
/* Test width of ASCII characters. */
for (wc = 0x20; wc < 0x7F; wc++)
ASSERT (c32width (wc) == 1);
/* Test width of some non-spacing characters. */
ASSERT (c32width (0x0301) == 0);
ASSERT (c32width (0x05B0) == 0);
/* Test width of some format control characters. */
ASSERT (c32width (0x200E) <= 0);
ASSERT (c32width (0x2060) <= 0);
ASSERT (c32width (0xE0001) <= 0);
ASSERT (c32width (0xE0044) <= 0);
/* Test width of some zero width characters. */
/* While it is desirable that U+200B, U+200C, U+200D have width 0,
because this makes wcswidth work better on strings that contain these
characters, it is acceptable if an implementation treats these
characters like control characters. */
ASSERT (c32width (0x200B) <= 0);
ASSERT (c32width (0xFEFF) <= 0);
/* Test width of some math symbols.
U+2202 is marked as having ambiguous width (A) in EastAsianWidth.txt
(see <https://www.unicode.org/Public/12.0.0/ucd/EastAsianWidth.txt>).
The Unicode Standard Annex 11
<https://www.unicode.org/reports/tr11/tr11-36.html>
says
"Ambiguous characters behave like wide or narrow characters
depending on the context (language tag, script identification,
associated font, source of data, or explicit markup; all can
provide the context). If the context cannot be established
reliably, they should be treated as narrow characters by default."
For c32width(), the only available context information is the locale.
"fr_FR.UTF-8" is a Western locale, not an East Asian locale, therefore
U+2202 should be treated like a narrow character. */
ASSERT (c32width (0x2202) == 1);
/* Test width of some CJK characters. */
ASSERT (c32width (0x3000) == 2);
ASSERT (c32width (0xB250) == 2);
ASSERT (c32width (0xFF1A) == 2);
#if !((defined __FreeBSD__ && __FreeBSD__ < 13 && !defined __GLIBC__) || defined __sun)
ASSERT (c32width (0x20369) == 2);
ASSERT (c32width (0x2F876) == 2);
#endif
}
return test_exit_status;
}
|
