1 /* Test of conversion of wide character to multibyte character.
2 Copyright (C) 2008-2023 Free Software Foundation, Inc.
3
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation, either version 3 of the License, or
7 (at your option) any later version.
8
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
13
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <https://www.gnu.org/licenses/>. */
16
17 /* Written by Bruno Haible <bruno@clisp.org>, 2008. */
18
19 #include <config.h>
20
21 #include <uchar.h>
22
23 #include "signature.h"
24 SIGNATURE_CHECK (c32rtomb, size_t, (char *, char32_t, mbstate_t *));
25
26 #include <locale.h>
27 #include <stdlib.h>
28 #include <string.h>
29
30 #include "macros.h"
31
32 /* Check the multibyte character s[0..n-1]. */
33 static void
34 check_character (const char *s, size_t n)
35 {
36 mbstate_t state;
37 char32_t wc;
38 char buf[64];
39 int iret;
40 size_t ret;
41
42 memset (&state, '\0', sizeof (mbstate_t));
43 wc = (char32_t) 0xBADFACE;
44 iret = mbrtoc32 (&wc, s, n, &state);
45 ASSERT (iret == n);
46
47 ret = c32rtomb (buf, wc, NULL);
48 ASSERT (ret == n);
49 ASSERT (memcmp (buf, s, n) == 0);
50
51 /* Test special calling convention, passing a NULL pointer. */
52 ret = c32rtomb (NULL, wc, NULL);
53 ASSERT (ret == 1);
54 }
55
56 int
57 main (int argc, char *argv[])
58 {
59 char buf[64];
60 size_t ret;
61
62 /* configure should already have checked that the locale is supported. */
63 if (setlocale (LC_ALL, "") == NULL)
64 return 1;
65
66 /* Test NUL character. */
67 {
68 buf[0] = 'x';
69 ret = c32rtomb (buf, 0, NULL);
70 ASSERT (ret == 1);
71 ASSERT (buf[0] == '\0');
72 }
73
74 /* Test single bytes. */
75 {
76 int c;
77
78 for (c = 0; c < 0x100; c++)
79 switch (c)
80 {
81 case '\t': case '\v': case '\f':
82 case ' ': case '!': case '"': case '#': case '%':
83 case '&': case '\'': case '(': case ')': case '*':
84 case '+': case ',': case '-': case '.': case '/':
85 case '0': case '1': case '2': case '3': case '4':
86 case '5': case '6': case '7': case '8': case '9':
87 case ':': case ';': case '<': case '=': case '>':
88 case '?':
89 case 'A': case 'B': case 'C': case 'D': case 'E':
90 case 'F': case 'G': case 'H': case 'I': case 'J':
91 case 'K': case 'L': case 'M': case 'N': case 'O':
92 case 'P': case 'Q': case 'R': case 'S': case 'T':
93 case 'U': case 'V': case 'W': case 'X': case 'Y':
94 case 'Z':
95 case '[': case '\\': case ']': case '^': case '_':
96 case 'a': case 'b': case 'c': case 'd': case 'e':
97 case 'f': case 'g': case 'h': case 'i': case 'j':
98 case 'k': case 'l': case 'm': case 'n': case 'o':
99 case 'p': case 'q': case 'r': case 's': case 't':
100 case 'u': case 'v': case 'w': case 'x': case 'y':
101 case 'z': case '{': case '|': case '}': case '~':
102 /* c is in the ISO C "basic character set". */
103 ret = c32rtomb (buf, btoc32 (c), NULL);
104 ASSERT (ret == 1);
105 ASSERT (buf[0] == (char) c);
106 break;
107 }
108 }
109
110 /* Test special calling convention, passing a NULL pointer. */
111 {
112 ret = c32rtomb (NULL, '\0', NULL);
113 ASSERT (ret == 1);
114 ret = c32rtomb (NULL, btoc32 ('x'), NULL);
115 ASSERT (ret == 1);
116 }
117
118 if (argc > 1)
119 switch (argv[1][0])
120 {
121 case '1':
122 /* C locale; tested above. */
123 return 0;
124
125 case '2':
126 /* Locale encoding is ISO-8859-1 or ISO-8859-15. */
127 {
128 const char input[] = "B\374\337er"; /* "Büßer" */
129
130 check_character (input + 1, 1);
131 check_character (input + 2, 1);
132 }
133 return 0;
134
135 case '3':
136 /* Locale encoding is UTF-8. */
137 {
138 const char input[] = "s\303\274\303\237\360\237\230\213!"; /* "süß😋!" */
139
140 check_character (input + 1, 2);
141 check_character (input + 3, 2);
142 check_character (input + 5, 4);
143 }
144 return 0;
145
146 case '4':
147 /* Locale encoding is EUC-JP. */
148 {
149 const char input[] = "<\306\374\313\334\270\354>"; /* "<日本語>" */
150
151 check_character (input + 1, 2);
152 check_character (input + 3, 2);
153 check_character (input + 5, 2);
154 }
155 return 0;
156
157 case '5':
158 /* Locale encoding is GB18030. */
159 #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __NetBSD__ || defined __sun))
160 fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
161 return 77;
162 #endif
163 {
164 const char input[] = "s\250\271\201\060\211\070\224\071\375\067!"; /* "süß😋!" */
165
166 check_character (input + 1, 2);
167 check_character (input + 3, 4);
168 check_character (input + 7, 4);
169 }
170 return 0;
171 }
172
173 return 1;
174 }