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
|
/* Test of conversion of wide character to multibyte character.
Copyright (C) 2008-2024 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>, 2008. */
#include <config.h>
#include <uchar.h>
#include "signature.h"
SIGNATURE_CHECK (c32rtomb, size_t, (char *, char32_t, mbstate_t *));
#include <locale.h>
#include <stdlib.h>
#include <string.h>
#include "macros.h"
/* Check the multibyte character s[0..n-1]. */
static void
check_character (const char *s, size_t n)
{
mbstate_t state;
char32_t wc;
char buf[64];
int iret;
size_t ret;
memset (&state, '\0', sizeof (mbstate_t));
wc = (char32_t) 0xBADFACE;
iret = mbrtoc32 (&wc, s, n, &state);
ASSERT (iret == n);
ret = c32rtomb (buf, wc, NULL);
ASSERT (ret == n);
ASSERT (memcmp (buf, s, n) == 0);
/* Test special calling convention, passing a NULL pointer. */
ret = c32rtomb (NULL, wc, NULL);
ASSERT (ret == 1);
}
int
main (int argc, char *argv[])
{
char buf[64];
size_t ret;
/* configure should already have checked that the locale is supported. */
if (setlocale (LC_ALL, "") == NULL)
return 1;
/* Test NUL character. */
{
buf[0] = 'x';
ret = c32rtomb (buf, 0, NULL);
ASSERT (ret == 1);
ASSERT (buf[0] == '\0');
}
/* Test single bytes. */
{
int c;
for (c = 0; c < 0x100; c++)
switch (c)
{
case '\t': case '\v': case '\f':
case ' ': case '!': case '"': case '#': case '%':
case '&': case '\'': case '(': case ')': case '*':
case '+': case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>':
case '?':
case 'A': case 'B': case 'C': case 'D': case 'E':
case 'F': case 'G': case 'H': case 'I': case 'J':
case 'K': case 'L': case 'M': case 'N': case 'O':
case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y':
case 'Z':
case '[': case '\\': case ']': case '^': case '_':
case 'a': case 'b': case 'c': case 'd': case 'e':
case 'f': case 'g': case 'h': case 'i': case 'j':
case 'k': case 'l': case 'm': case 'n': case 'o':
case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y':
case 'z': case '{': case '|': case '}': case '~':
/* c is in the ISO C "basic character set". */
ret = c32rtomb (buf, btoc32 (c), NULL);
ASSERT (ret == 1);
ASSERT (buf[0] == (char) c);
break;
}
}
/* Test special calling convention, passing a NULL pointer. */
{
ret = c32rtomb (NULL, '\0', NULL);
ASSERT (ret == 1);
ret = c32rtomb (NULL, btoc32 ('x'), NULL);
ASSERT (ret == 1);
}
if (argc > 1)
switch (argv[1][0])
{
case '1':
/* C locale; tested above. */
return test_exit_status;
case '2':
/* Locale encoding is ISO-8859-1 or ISO-8859-15. */
{
const char input[] = "B\374\337er"; /* "Büßer" */
check_character (input + 1, 1);
check_character (input + 2, 1);
}
return test_exit_status;
case '3':
/* Locale encoding is UTF-8. */
{
const char input[] = "s\303\274\303\237\360\237\230\213!"; /* "süß😋!" */
check_character (input + 1, 2);
check_character (input + 3, 2);
check_character (input + 5, 4);
}
return test_exit_status;
case '4':
/* Locale encoding is EUC-JP. */
{
const char input[] = "<\306\374\313\334\270\354>"; /* "<日本語>" */
check_character (input + 1, 2);
check_character (input + 3, 2);
check_character (input + 5, 2);
}
return test_exit_status;
case '5':
/* Locale encoding is GB18030. */
#if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __FreeBSD__ || defined __NetBSD__ || defined __sun))
if (test_exit_status != EXIT_SUCCESS)
return test_exit_status;
fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
return 77;
#endif
{
const char input[] = "s\250\271\201\060\211\070\224\071\375\067!"; /* "süß😋!" */
check_character (input + 1, 2);
check_character (input + 3, 4);
check_character (input + 7, 4);
}
return test_exit_status;
}
return 1;
}
|