1 | /* Test of conversion of wide character to multibyte character.
|
---|
2 | Copyright (C) 2008-2021 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 | #include <config.h>
|
---|
18 |
|
---|
19 | #include <wchar.h>
|
---|
20 |
|
---|
21 | #include <locale.h>
|
---|
22 | #include <stdio.h>
|
---|
23 | #include <stdlib.h>
|
---|
24 | #include <string.h>
|
---|
25 |
|
---|
26 | #include "localcharset.h"
|
---|
27 | #include "macros.h"
|
---|
28 |
|
---|
29 | #if defined _WIN32 && !defined __CYGWIN__
|
---|
30 |
|
---|
31 | static int
|
---|
32 | test_one_locale (const char *name, int codepage)
|
---|
33 | {
|
---|
34 | char buf[64];
|
---|
35 | size_t ret;
|
---|
36 |
|
---|
37 | # if 1
|
---|
38 | /* Portable code to set the locale. */
|
---|
39 | {
|
---|
40 | char name_with_codepage[1024];
|
---|
41 |
|
---|
42 | sprintf (name_with_codepage, "%s.%d", name, codepage);
|
---|
43 |
|
---|
44 | /* Set the locale. */
|
---|
45 | if (setlocale (LC_ALL, name_with_codepage) == NULL)
|
---|
46 | return 77;
|
---|
47 | }
|
---|
48 | # else
|
---|
49 | /* Hacky way to set a locale.codepage combination that setlocale() refuses
|
---|
50 | to set. */
|
---|
51 | {
|
---|
52 | /* Codepage of the current locale, set with setlocale().
|
---|
53 | Not necessarily the same as GetACP(). */
|
---|
54 | extern __declspec(dllimport) unsigned int __lc_codepage;
|
---|
55 |
|
---|
56 | /* Set the locale. */
|
---|
57 | if (setlocale (LC_ALL, name) == NULL)
|
---|
58 | return 77;
|
---|
59 |
|
---|
60 | /* Clobber the codepage and MB_CUR_MAX, both set by setlocale(). */
|
---|
61 | __lc_codepage = codepage;
|
---|
62 | switch (codepage)
|
---|
63 | {
|
---|
64 | case 1252:
|
---|
65 | case 1256:
|
---|
66 | MB_CUR_MAX = 1;
|
---|
67 | break;
|
---|
68 | case 932:
|
---|
69 | case 950:
|
---|
70 | case 936:
|
---|
71 | MB_CUR_MAX = 2;
|
---|
72 | break;
|
---|
73 | case 54936:
|
---|
74 | case 65001:
|
---|
75 | MB_CUR_MAX = 4;
|
---|
76 | break;
|
---|
77 | }
|
---|
78 |
|
---|
79 | /* Test whether the codepage is really available. */
|
---|
80 | {
|
---|
81 | mbstate_t state;
|
---|
82 | wchar_t wc;
|
---|
83 |
|
---|
84 | memset (&state, '\0', sizeof (mbstate_t));
|
---|
85 | if (mbrtowc (&wc, " ", 1, &state) == (size_t)(-1))
|
---|
86 | return 77;
|
---|
87 | }
|
---|
88 | }
|
---|
89 | # endif
|
---|
90 |
|
---|
91 | /* Test NUL character. */
|
---|
92 | {
|
---|
93 | buf[0] = 'x';
|
---|
94 | ret = wcrtomb (buf, 0, NULL);
|
---|
95 | ASSERT (ret == 1);
|
---|
96 | ASSERT (buf[0] == '\0');
|
---|
97 | }
|
---|
98 |
|
---|
99 | /* Test single bytes. */
|
---|
100 | {
|
---|
101 | int c;
|
---|
102 |
|
---|
103 | for (c = 0; c < 0x100; c++)
|
---|
104 | switch (c)
|
---|
105 | {
|
---|
106 | case '\t': case '\v': case '\f':
|
---|
107 | case ' ': case '!': case '"': case '#': case '%':
|
---|
108 | case '&': case '\'': case '(': case ')': case '*':
|
---|
109 | case '+': case ',': case '-': case '.': case '/':
|
---|
110 | case '0': case '1': case '2': case '3': case '4':
|
---|
111 | case '5': case '6': case '7': case '8': case '9':
|
---|
112 | case ':': case ';': case '<': case '=': case '>':
|
---|
113 | case '?':
|
---|
114 | case 'A': case 'B': case 'C': case 'D': case 'E':
|
---|
115 | case 'F': case 'G': case 'H': case 'I': case 'J':
|
---|
116 | case 'K': case 'L': case 'M': case 'N': case 'O':
|
---|
117 | case 'P': case 'Q': case 'R': case 'S': case 'T':
|
---|
118 | case 'U': case 'V': case 'W': case 'X': case 'Y':
|
---|
119 | case 'Z':
|
---|
120 | case '[': case '\\': case ']': case '^': case '_':
|
---|
121 | case 'a': case 'b': case 'c': case 'd': case 'e':
|
---|
122 | case 'f': case 'g': case 'h': case 'i': case 'j':
|
---|
123 | case 'k': case 'l': case 'm': case 'n': case 'o':
|
---|
124 | case 'p': case 'q': case 'r': case 's': case 't':
|
---|
125 | case 'u': case 'v': case 'w': case 'x': case 'y':
|
---|
126 | case 'z': case '{': case '|': case '}': case '~':
|
---|
127 | /* c is in the ISO C "basic character set". */
|
---|
128 | ret = wcrtomb (buf, btowc (c), NULL);
|
---|
129 | ASSERT (ret == 1);
|
---|
130 | ASSERT (buf[0] == (char) c);
|
---|
131 | break;
|
---|
132 | }
|
---|
133 | }
|
---|
134 |
|
---|
135 | /* Test special calling convention, passing a NULL pointer. */
|
---|
136 | {
|
---|
137 | ret = wcrtomb (NULL, '\0', NULL);
|
---|
138 | ASSERT (ret == 1);
|
---|
139 | ret = wcrtomb (NULL, btowc ('x'), NULL);
|
---|
140 | ASSERT (ret == 1);
|
---|
141 | }
|
---|
142 |
|
---|
143 | switch (codepage)
|
---|
144 | {
|
---|
145 | case 1252:
|
---|
146 | /* Locale encoding is CP1252, an extension of ISO-8859-1. */
|
---|
147 | {
|
---|
148 | /* Convert "B\374\337er": "Büßer" */
|
---|
149 | memset (buf, 'x', 8);
|
---|
150 | ret = wcrtomb (buf, 0x00FC, NULL);
|
---|
151 | ASSERT (ret == 1);
|
---|
152 | ASSERT (memcmp (buf, "\374", 1) == 0);
|
---|
153 | ASSERT (buf[1] == 'x');
|
---|
154 |
|
---|
155 | memset (buf, 'x', 8);
|
---|
156 | ret = wcrtomb (buf, 0x00DF, NULL);
|
---|
157 | ASSERT (ret == 1);
|
---|
158 | ASSERT (memcmp (buf, "\337", 1) == 0);
|
---|
159 | ASSERT (buf[1] == 'x');
|
---|
160 | }
|
---|
161 | return 0;
|
---|
162 |
|
---|
163 | case 1256:
|
---|
164 | /* Locale encoding is CP1256, not the same as ISO-8859-6. */
|
---|
165 | {
|
---|
166 | /* Convert "x\302\341\346y": "xآلوy" */
|
---|
167 | memset (buf, 'x', 8);
|
---|
168 | ret = wcrtomb (buf, 0x0622, NULL);
|
---|
169 | ASSERT (ret == 1);
|
---|
170 | ASSERT (memcmp (buf, "\302", 1) == 0);
|
---|
171 | ASSERT (buf[1] == 'x');
|
---|
172 |
|
---|
173 | memset (buf, 'x', 8);
|
---|
174 | ret = wcrtomb (buf, 0x0644, NULL);
|
---|
175 | ASSERT (ret == 1);
|
---|
176 | ASSERT (memcmp (buf, "\341", 1) == 0);
|
---|
177 | ASSERT (buf[1] == 'x');
|
---|
178 |
|
---|
179 | memset (buf, 'x', 8);
|
---|
180 | ret = wcrtomb (buf, 0x0648, NULL);
|
---|
181 | ASSERT (ret == 1);
|
---|
182 | ASSERT (memcmp (buf, "\346", 1) == 0);
|
---|
183 | ASSERT (buf[1] == 'x');
|
---|
184 | }
|
---|
185 | return 0;
|
---|
186 |
|
---|
187 | case 932:
|
---|
188 | /* Locale encoding is CP932, similar to Shift_JIS. */
|
---|
189 | {
|
---|
190 | /* Convert "<\223\372\226\173\214\352>": "<日本語>" */
|
---|
191 | memset (buf, 'x', 8);
|
---|
192 | ret = wcrtomb (buf, 0x65E5, NULL);
|
---|
193 | ASSERT (ret == 2);
|
---|
194 | ASSERT (memcmp (buf, "\223\372", 2) == 0);
|
---|
195 | ASSERT (buf[2] == 'x');
|
---|
196 |
|
---|
197 | memset (buf, 'x', 8);
|
---|
198 | ret = wcrtomb (buf, 0x672C, NULL);
|
---|
199 | ASSERT (ret == 2);
|
---|
200 | ASSERT (memcmp (buf, "\226\173", 2) == 0);
|
---|
201 | ASSERT (buf[2] == 'x');
|
---|
202 |
|
---|
203 | memset (buf, 'x', 8);
|
---|
204 | ret = wcrtomb (buf, 0x8A9E, NULL);
|
---|
205 | ASSERT (ret == 2);
|
---|
206 | ASSERT (memcmp (buf, "\214\352", 2) == 0);
|
---|
207 | ASSERT (buf[2] == 'x');
|
---|
208 | }
|
---|
209 | return 0;
|
---|
210 |
|
---|
211 | case 950:
|
---|
212 | /* Locale encoding is CP950, similar to Big5. */
|
---|
213 | {
|
---|
214 | /* Convert "<\244\351\245\273\273\171>": "<日本語>" */
|
---|
215 | memset (buf, 'x', 8);
|
---|
216 | ret = wcrtomb (buf, 0x65E5, NULL);
|
---|
217 | ASSERT (ret == 2);
|
---|
218 | ASSERT (memcmp (buf, "\244\351", 2) == 0);
|
---|
219 | ASSERT (buf[2] == 'x');
|
---|
220 |
|
---|
221 | memset (buf, 'x', 8);
|
---|
222 | ret = wcrtomb (buf, 0x672C, NULL);
|
---|
223 | ASSERT (ret == 2);
|
---|
224 | ASSERT (memcmp (buf, "\245\273", 2) == 0);
|
---|
225 | ASSERT (buf[2] == 'x');
|
---|
226 |
|
---|
227 | memset (buf, 'x', 8);
|
---|
228 | ret = wcrtomb (buf, 0x8A9E, NULL);
|
---|
229 | ASSERT (ret == 2);
|
---|
230 | ASSERT (memcmp (buf, "\273\171", 2) == 0);
|
---|
231 | ASSERT (buf[2] == 'x');
|
---|
232 | }
|
---|
233 | return 0;
|
---|
234 |
|
---|
235 | case 936:
|
---|
236 | /* Locale encoding is CP936 = GBK, an extension of GB2312. */
|
---|
237 | {
|
---|
238 | /* Convert "<\310\325\261\276\325\132>": "<日本語>" */
|
---|
239 | memset (buf, 'x', 8);
|
---|
240 | ret = wcrtomb (buf, 0x65E5, NULL);
|
---|
241 | ASSERT (ret == 2);
|
---|
242 | ASSERT (memcmp (buf, "\310\325", 2) == 0);
|
---|
243 | ASSERT (buf[2] == 'x');
|
---|
244 |
|
---|
245 | memset (buf, 'x', 8);
|
---|
246 | ret = wcrtomb (buf, 0x672C, NULL);
|
---|
247 | ASSERT (ret == 2);
|
---|
248 | ASSERT (memcmp (buf, "\261\276", 2) == 0);
|
---|
249 | ASSERT (buf[2] == 'x');
|
---|
250 |
|
---|
251 | memset (buf, 'x', 8);
|
---|
252 | ret = wcrtomb (buf, 0x8A9E, NULL);
|
---|
253 | ASSERT (ret == 2);
|
---|
254 | ASSERT (memcmp (buf, "\325\132", 2) == 0);
|
---|
255 | ASSERT (buf[2] == 'x');
|
---|
256 | }
|
---|
257 | return 0;
|
---|
258 |
|
---|
259 | case 54936:
|
---|
260 | /* Locale encoding is CP54936 = GB18030. */
|
---|
261 | if (strcmp (locale_charset (), "GB18030") != 0)
|
---|
262 | return 77;
|
---|
263 | {
|
---|
264 | /* Convert "B\250\271\201\060\211\070er": "Büßer" */
|
---|
265 | memset (buf, 'x', 8);
|
---|
266 | ret = wcrtomb (buf, 0x00FC, NULL);
|
---|
267 | ASSERT (ret == 2);
|
---|
268 | ASSERT (memcmp (buf, "\250\271", 2) == 0);
|
---|
269 | ASSERT (buf[2] == 'x');
|
---|
270 |
|
---|
271 | memset (buf, 'x', 8);
|
---|
272 | ret = wcrtomb (buf, 0x00DF, NULL);
|
---|
273 | ASSERT (ret == 4);
|
---|
274 | ASSERT (memcmp (buf, "\201\060\211\070", 4) == 0);
|
---|
275 | ASSERT (buf[4] == 'x');
|
---|
276 | }
|
---|
277 | return 0;
|
---|
278 |
|
---|
279 | case 65001:
|
---|
280 | /* Locale encoding is CP65001 = UTF-8. */
|
---|
281 | if (strcmp (locale_charset (), "UTF-8") != 0)
|
---|
282 | return 77;
|
---|
283 | {
|
---|
284 | /* Convert "B\303\274\303\237er": "Büßer" */
|
---|
285 | memset (buf, 'x', 8);
|
---|
286 | ret = wcrtomb (buf, 0x00FC, NULL);
|
---|
287 | ASSERT (ret == 2);
|
---|
288 | ASSERT (memcmp (buf, "\303\274", 2) == 0);
|
---|
289 | ASSERT (buf[2] == 'x');
|
---|
290 |
|
---|
291 | memset (buf, 'x', 8);
|
---|
292 | ret = wcrtomb (buf, 0x00DF, NULL);
|
---|
293 | ASSERT (ret == 2);
|
---|
294 | ASSERT (memcmp (buf, "\303\237", 2) == 0);
|
---|
295 | ASSERT (buf[2] == 'x');
|
---|
296 | }
|
---|
297 | return 0;
|
---|
298 |
|
---|
299 | default:
|
---|
300 | return 1;
|
---|
301 | }
|
---|
302 | }
|
---|
303 |
|
---|
304 | int
|
---|
305 | main (int argc, char *argv[])
|
---|
306 | {
|
---|
307 | int codepage = atoi (argv[argc - 1]);
|
---|
308 | int result;
|
---|
309 | int i;
|
---|
310 |
|
---|
311 | result = 77;
|
---|
312 | for (i = 1; i < argc - 1; i++)
|
---|
313 | {
|
---|
314 | int ret = test_one_locale (argv[i], codepage);
|
---|
315 |
|
---|
316 | if (ret != 77)
|
---|
317 | result = ret;
|
---|
318 | }
|
---|
319 |
|
---|
320 | if (result == 77)
|
---|
321 | {
|
---|
322 | fprintf (stderr, "Skipping test: found no locale with codepage %d\n",
|
---|
323 | codepage);
|
---|
324 | }
|
---|
325 | return result;
|
---|
326 | }
|
---|
327 |
|
---|
328 | #else
|
---|
329 |
|
---|
330 | int
|
---|
331 | main (int argc, char *argv[])
|
---|
332 | {
|
---|
333 | fputs ("Skipping test: not a native Windows system\n", stderr);
|
---|
334 | return 77;
|
---|
335 | }
|
---|
336 |
|
---|
337 | #endif
|
---|