1 /* Test of conversion of multibyte character to wide 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 <wchar.h>
22
23 #include "signature.h"
24 SIGNATURE_CHECK (mbrtowc, size_t, (wchar_t *, char const *, size_t,
25 mbstate_t *));
26
27 #include <locale.h>
28 #include <stdio.h>
29 #include <stdlib.h>
30 #include <string.h>
31
32 #include "macros.h"
33
34 int
35 main (int argc, char *argv[])
36 {
37 mbstate_t state;
38 wchar_t wc;
39 size_t ret;
40
41 /* configure should already have checked that the locale is supported. */
42 if (setlocale (LC_ALL, "") == NULL)
43 return 1;
44
45 /* Test zero-length input. */
46 {
47 memset (&state, '\0', sizeof (mbstate_t));
48 wc = (wchar_t) 0xBADFACE;
49 ret = mbrtowc (&wc, "x", 0, &state);
50 ASSERT (ret == (size_t)(-2));
51 ASSERT (mbsinit (&state));
52 }
53
54 /* Test NUL byte input. */
55 {
56 memset (&state, '\0', sizeof (mbstate_t));
57 wc = (wchar_t) 0xBADFACE;
58 ret = mbrtowc (&wc, "", 1, &state);
59 ASSERT (ret == 0);
60 ASSERT (wc == 0);
61 ASSERT (mbsinit (&state));
62 ret = mbrtowc (NULL, "", 1, &state);
63 ASSERT (ret == 0);
64 ASSERT (mbsinit (&state));
65 }
66
67 /* Test single-byte input. */
68 {
69 int c;
70 char buf[1];
71
72 memset (&state, '\0', sizeof (mbstate_t));
73 for (c = 0; c < 0x100; c++)
74 switch (c)
75 {
76 case '\t': case '\v': case '\f':
77 case ' ': case '!': case '"': case '#': case '%':
78 case '&': case '\'': case '(': case ')': case '*':
79 case '+': case ',': case '-': case '.': case '/':
80 case '0': case '1': case '2': case '3': case '4':
81 case '5': case '6': case '7': case '8': case '9':
82 case ':': case ';': case '<': case '=': case '>':
83 case '?':
84 case 'A': case 'B': case 'C': case 'D': case 'E':
85 case 'F': case 'G': case 'H': case 'I': case 'J':
86 case 'K': case 'L': case 'M': case 'N': case 'O':
87 case 'P': case 'Q': case 'R': case 'S': case 'T':
88 case 'U': case 'V': case 'W': case 'X': case 'Y':
89 case 'Z':
90 case '[': case '\\': case ']': case '^': case '_':
91 case 'a': case 'b': case 'c': case 'd': case 'e':
92 case 'f': case 'g': case 'h': case 'i': case 'j':
93 case 'k': case 'l': case 'm': case 'n': case 'o':
94 case 'p': case 'q': case 'r': case 's': case 't':
95 case 'u': case 'v': case 'w': case 'x': case 'y':
96 case 'z': case '{': case '|': case '}': case '~':
97 /* c is in the ISO C "basic character set". */
98 ASSERT (c < 0x80);
99 /* c is an ASCII character. */
100 buf[0] = c;
101
102 wc = (wchar_t) 0xBADFACE;
103 ret = mbrtowc (&wc, buf, 1, &state);
104 ASSERT (ret == 1);
105 ASSERT (wc == c);
106 ASSERT (mbsinit (&state));
107
108 ret = mbrtowc (NULL, buf, 1, &state);
109 ASSERT (ret == 1);
110 ASSERT (mbsinit (&state));
111
112 break;
113 default:
114 break;
115 }
116 }
117
118 /* Test special calling convention, passing a NULL pointer. */
119 {
120 memset (&state, '\0', sizeof (mbstate_t));
121 wc = (wchar_t) 0xBADFACE;
122 ret = mbrtowc (&wc, NULL, 5, &state);
123 ASSERT (ret == 0);
124 ASSERT (wc == (wchar_t) 0xBADFACE);
125 ASSERT (mbsinit (&state));
126 }
127
128 #ifdef __ANDROID__
129 /* On Android ≥ 5.0, the default locale is the "C.UTF-8" locale, not the
130 "C" locale. Furthermore, when you attempt to set the "C" or "POSIX"
131 locale via setlocale(), what you get is a "C" locale with UTF-8 encoding,
132 that is, effectively the "C.UTF-8" locale. */
133 if (argc > 1 && strcmp (argv[1], "1") == 0 && MB_CUR_MAX > 1)
134 argv[1] = "3";
135 #endif
136
137 if (argc > 1)
138 switch (argv[1][0])
139 {
140 case '1':
141 /* C or POSIX locale. */
142 {
143 int c;
144 char buf[1];
145
146 memset (&state, '\0', sizeof (mbstate_t));
147 for (c = 0; c < 0x100; c++)
148 if (c != 0)
149 {
150 /* We are testing all nonnull bytes. */
151 buf[0] = c;
152
153 wc = (wchar_t) 0xBADFACE;
154 ret = mbrtowc (&wc, buf, 1, &state);
155 /* POSIX:2018 says: "In the POSIX locale an [EILSEQ] error
156 cannot occur since all byte values are valid characters." */
157 ASSERT (ret == 1);
158 if (c < 0x80)
159 /* c is an ASCII character. */
160 ASSERT (wc == c);
161 else
162 /* On most platforms, the bytes 0x80..0xFF map to U+0080..U+00FF.
163 But on musl libc, the bytes 0x80..0xFF map to U+DF80..U+DFFF. */
164 ASSERT (wc == (btowc (c) == 0xDF00 + c ? btowc (c) : c));
165 ASSERT (mbsinit (&state));
166
167 ret = mbrtowc (NULL, buf, 1, &state);
168 ASSERT (ret == 1);
169 ASSERT (mbsinit (&state));
170 }
171 }
172 return 0;
173
174 case '2':
175 /* Locale encoding is ISO-8859-1 or ISO-8859-15. */
176 {
177 char input[] = "B\374\337er"; /* "Büßer" */
178 memset (&state, '\0', sizeof (mbstate_t));
179
180 wc = (wchar_t) 0xBADFACE;
181 ret = mbrtowc (&wc, input, 1, &state);
182 ASSERT (ret == 1);
183 ASSERT (wc == 'B');
184 ASSERT (mbsinit (&state));
185 input[0] = '\0';
186
187 wc = (wchar_t) 0xBADFACE;
188 ret = mbrtowc (&wc, input + 1, 1, &state);
189 ASSERT (ret == 1);
190 ASSERT (wctob (wc) == (unsigned char) '\374');
191 ASSERT (mbsinit (&state));
192 input[1] = '\0';
193
194 /* Test support of NULL first argument. */
195 ret = mbrtowc (NULL, input + 2, 3, &state);
196 ASSERT (ret == 1);
197 ASSERT (mbsinit (&state));
198
199 wc = (wchar_t) 0xBADFACE;
200 ret = mbrtowc (&wc, input + 2, 3, &state);
201 ASSERT (ret == 1);
202 ASSERT (wctob (wc) == (unsigned char) '\337');
203 ASSERT (mbsinit (&state));
204 input[2] = '\0';
205
206 wc = (wchar_t) 0xBADFACE;
207 ret = mbrtowc (&wc, input + 3, 2, &state);
208 ASSERT (ret == 1);
209 ASSERT (wc == 'e');
210 ASSERT (mbsinit (&state));
211 input[3] = '\0';
212
213 wc = (wchar_t) 0xBADFACE;
214 ret = mbrtowc (&wc, input + 4, 1, &state);
215 ASSERT (ret == 1);
216 ASSERT (wc == 'r');
217 ASSERT (mbsinit (&state));
218 }
219 return 0;
220
221 case '3':
222 /* Locale encoding is UTF-8. */
223 {
224 char input[] = "B\303\274\303\237er"; /* "Büßer" */
225 memset (&state, '\0', sizeof (mbstate_t));
226
227 wc = (wchar_t) 0xBADFACE;
228 ret = mbrtowc (&wc, input, 1, &state);
229 ASSERT (ret == 1);
230 ASSERT (wc == 'B');
231 ASSERT (mbsinit (&state));
232 input[0] = '\0';
233
234 wc = (wchar_t) 0xBADFACE;
235 ret = mbrtowc (&wc, input + 1, 1, &state);
236 ASSERT (ret == (size_t)(-2));
237 ASSERT (wc == (wchar_t) 0xBADFACE);
238 ASSERT (!mbsinit (&state));
239 input[1] = '\0';
240
241 wc = (wchar_t) 0xBADFACE;
242 ret = mbrtowc (&wc, input + 2, 5, &state);
243 ASSERT (ret == 1);
244 ASSERT (wctob (wc) == EOF);
245 ASSERT (mbsinit (&state));
246 input[2] = '\0';
247
248 /* Test support of NULL first argument. */
249 ret = mbrtowc (NULL, input + 3, 4, &state);
250 ASSERT (ret == 2);
251 ASSERT (mbsinit (&state));
252
253 wc = (wchar_t) 0xBADFACE;
254 ret = mbrtowc (&wc, input + 3, 4, &state);
255 ASSERT (ret == 2);
256 ASSERT (wctob (wc) == EOF);
257 ASSERT (mbsinit (&state));
258 input[3] = '\0';
259 input[4] = '\0';
260
261 wc = (wchar_t) 0xBADFACE;
262 ret = mbrtowc (&wc, input + 5, 2, &state);
263 ASSERT (ret == 1);
264 ASSERT (wc == 'e');
265 ASSERT (mbsinit (&state));
266 input[5] = '\0';
267
268 wc = (wchar_t) 0xBADFACE;
269 ret = mbrtowc (&wc, input + 6, 1, &state);
270 ASSERT (ret == 1);
271 ASSERT (wc == 'r');
272 ASSERT (mbsinit (&state));
273 }
274 return 0;
275
276 case '4':
277 /* Locale encoding is EUC-JP. */
278 {
279 char input[] = "<\306\374\313\334\270\354>"; /* "<日本語>" */
280 memset (&state, '\0', sizeof (mbstate_t));
281
282 wc = (wchar_t) 0xBADFACE;
283 ret = mbrtowc (&wc, input, 1, &state);
284 ASSERT (ret == 1);
285 ASSERT (wc == '<');
286 ASSERT (mbsinit (&state));
287 input[0] = '\0';
288
289 wc = (wchar_t) 0xBADFACE;
290 ret = mbrtowc (&wc, input + 1, 2, &state);
291 ASSERT (ret == 2);
292 ASSERT (wctob (wc) == EOF);
293 ASSERT (mbsinit (&state));
294 input[1] = '\0';
295 input[2] = '\0';
296
297 wc = (wchar_t) 0xBADFACE;
298 ret = mbrtowc (&wc, input + 3, 1, &state);
299 ASSERT (ret == (size_t)(-2));
300 ASSERT (wc == (wchar_t) 0xBADFACE);
301 ASSERT (!mbsinit (&state));
302 input[3] = '\0';
303
304 wc = (wchar_t) 0xBADFACE;
305 ret = mbrtowc (&wc, input + 4, 4, &state);
306 ASSERT (ret == 1);
307 ASSERT (wctob (wc) == EOF);
308 ASSERT (mbsinit (&state));
309 input[4] = '\0';
310
311 /* Test support of NULL first argument. */
312 ret = mbrtowc (NULL, input + 5, 3, &state);
313 ASSERT (ret == 2);
314 ASSERT (mbsinit (&state));
315
316 wc = (wchar_t) 0xBADFACE;
317 ret = mbrtowc (&wc, input + 5, 3, &state);
318 ASSERT (ret == 2);
319 ASSERT (wctob (wc) == EOF);
320 ASSERT (mbsinit (&state));
321 input[5] = '\0';
322 input[6] = '\0';
323
324 wc = (wchar_t) 0xBADFACE;
325 ret = mbrtowc (&wc, input + 7, 1, &state);
326 ASSERT (ret == 1);
327 ASSERT (wc == '>');
328 ASSERT (mbsinit (&state));
329 }
330 return 0;
331
332 case '5':
333 /* Locale encoding is GB18030. */
334 {
335 char input[] = "B\250\271\201\060\211\070er"; /* "Büßer" */
336 memset (&state, '\0', sizeof (mbstate_t));
337
338 wc = (wchar_t) 0xBADFACE;
339 ret = mbrtowc (&wc, input, 1, &state);
340 ASSERT (ret == 1);
341 ASSERT (wc == 'B');
342 ASSERT (mbsinit (&state));
343 input[0] = '\0';
344
345 wc = (wchar_t) 0xBADFACE;
346 ret = mbrtowc (&wc, input + 1, 1, &state);
347 ASSERT (ret == (size_t)(-2));
348 ASSERT (wc == (wchar_t) 0xBADFACE);
349 ASSERT (!mbsinit (&state));
350 input[1] = '\0';
351
352 wc = (wchar_t) 0xBADFACE;
353 ret = mbrtowc (&wc, input + 2, 7, &state);
354 ASSERT (ret == 1);
355 ASSERT (wctob (wc) == EOF);
356 ASSERT (mbsinit (&state));
357 input[2] = '\0';
358
359 /* Test support of NULL first argument. */
360 ret = mbrtowc (NULL, input + 3, 6, &state);
361 ASSERT (ret == 4);
362 ASSERT (mbsinit (&state));
363
364 wc = (wchar_t) 0xBADFACE;
365 ret = mbrtowc (&wc, input + 3, 6, &state);
366 ASSERT (ret == 4);
367 ASSERT (wctob (wc) == EOF);
368 ASSERT (mbsinit (&state));
369 input[3] = '\0';
370 input[4] = '\0';
371 input[5] = '\0';
372 input[6] = '\0';
373
374 wc = (wchar_t) 0xBADFACE;
375 ret = mbrtowc (&wc, input + 7, 2, &state);
376 ASSERT (ret == 1);
377 ASSERT (wc == 'e');
378 ASSERT (mbsinit (&state));
379 input[7] = '\0';
380
381 wc = (wchar_t) 0xBADFACE;
382 ret = mbrtowc (&wc, input + 8, 1, &state);
383 ASSERT (ret == 1);
384 ASSERT (wc == 'r');
385 ASSERT (mbsinit (&state));
386 }
387 return 0;
388 }
389
390 return 1;
391 }