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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
|
/** tests for strXXX
*/
#include <testfwk.h>
#include <string.h>
#include <stdlib.h>
#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199409L
#include <wchar.h>
#endif
#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
#if defined(__APPLE__) || defined(__OpenBSD__) // As of 2023, macOS and OpenBSD are still not fully C11-compliant: they lack uchar.h.
// Work around Apple's missing uchar.h
#include <stdint.h>
typedef int_least16_t char16_t;
typedef int_least32_t char32_t;
#else
#include <uchar.h> // For char16_t, char32_t
#endif
#endif
/** tests for strcmp
*/
static void
do_teststrcmp (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if !(defined (__SDCC_pdk15) && defined(__SDCC_STACK_AUTO)) // Lack of code memory
int result = strcmp ("", "");
ASSERT (result == 0);
result = strcmp ("", "a");
ASSERT (result < 0);
result = strcmp ("a", "");
ASSERT (result > 0);
result = strcmp ("ab", "ab");
ASSERT (result == 0);
result = strcmp ("aa", "ab");
ASSERT (result < 0);
#endif
#endif
}
/** tests for strcpy
*/
static void
do_teststrcpy (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if !(defined (__SDCC_pdk15) && defined(__SDCC_STACK_AUTO)) // Lack of code memory
static char empty[] = "";
static char string[] = "\1\2\0\3";
char buf[40] = "abcdefghijklmnopqrstuvwxyz";
char * result = strcpy (buf, empty);
ASSERT (strlen (buf) == 0);
ASSERT (result == buf);
result = strcpy (buf, string);
ASSERT (result == buf);
ASSERT (strlen (buf) == 2);
ASSERT (buf[0] == '\1');
ASSERT (buf[1] == '\2');
ASSERT (buf[3] == 'd');
#endif
#endif
}
/** tests for strncmp
*/
static void
do_teststrncmp (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if !(defined (__SDCC_pdk15) && defined(__SDCC_STACK_AUTO)) // Lack of code memory
ASSERT (strncmp ("", "", 0) == 0);
ASSERT (strncmp ("ab", "ab", 0) == 0);
ASSERT (strncmp ("a", "a", 2) == 0);
ASSERT (strncmp ("aa", "ab", 1) == 0);
ASSERT (strncmp ("aa", "ab", 2) < 0);
ASSERT (strncmp ("abc", "abd", 2) == 0);
ASSERT (strncmp ("abc", "abc", 3) == 0);
#endif
#endif
}
/** tests for strpbrk
* related to bug #2908537
*/
static void
do_teststrpbrk (void)
{
#if !defined(__SDCC_pdk14) && !defined(__SDCC_pdk15) // Lack of memory
const char *a = "test";
ASSERT (strpbrk (a, "e") == &a[1] );
ASSERT (strpbrk (a, "z") == NULL );
ASSERT (strpbrk (a, "et") == &a[0] );
ASSERT (strpbrk (a, "ze") == &a[1] );
ASSERT (strpbrk (a, "") == NULL );
ASSERT (strpbrk ("", "e") == NULL );
ASSERT (*strpbrk ("test2", "s") == 's' );
#endif
}
/** tests for strrchr
*/
static void
do_teststrrchr (void)
{
#if !defined(__SDCC_pdk14) && !defined(__SDCC_pdk15) // Lack of memory
const char *test = "test";
ASSERT (strrchr (test, 0) == test + 4);
ASSERT (strrchr (test, 't') == test + 3);
ASSERT (strrchr (test, 'e') == test + 1);
#endif
}
/** tests for strstr
*/
static void
do_teststrstr (void)
{
#if !defined(__SDCC_pdk14) && !defined(__SDCC_pdk15) // Lack of memory
const char *a = "aabbcd";
ASSERT (strstr (a, "\0\1") == a);
ASSERT (strstr (a, "") == a);
ASSERT (strstr (a, "ab") == &a[1]);
ASSERT (strstr (a, "abc") == NULL);
ASSERT (strstr (a, "abbc") == &a[1]);
ASSERT (strstr ("", "abbc") == NULL);
/* ASSERT (strstr ("", "") == a); should work, but it doesn't */
ASSERT (strstr (a, "cd") == &a[4]);
#endif
}
/** tests for strspn
*/
static void
do_teststrspn (void)
{
#if !defined(__SDCC_pdk14) && !defined(__SDCC_pdk15) // Lack of memory
ASSERT (strspn("aabbcd", "ab") == 4);
ASSERT (strspn("abbacd", "") == 0);
ASSERT (strspn("abbacd", "ac") == 1);
ASSERT (strspn("abbacd", "x") == 0);
ASSERT (strspn("abbacd", "c") == 0);
ASSERT (strspn("abbacd", "cba") == 5);
ASSERT (strspn("abbacd", "cdba") == 6);
#endif
}
/** tests for strtok
*/
static void
do_teststrtok (void)
{
#if !defined(__SDCC_pdk14) && !defined(__SDCC_pdk15) // Lack of memory
static char str[] = "?a???b,,,#c";
char str2[] = "axaaba";
char *token = strtok (str, "?"); // 'token' points to the token "a"
ASSERT (token == &str[1] && 0 == strcmp (token,"a"));
token = strtok (NULL, ","); // 'token' points to the token "??b"
ASSERT (token == &str[3] && 0 == strcmp (token,"??b"));
token = strtok (NULL, "#,"); // 'token' points to the token "c"
ASSERT (token == &str[10] && 0 == strcmp (token,"c"));
token = strtok (NULL, "?"); // 'token' is a null pointer
ASSERT (token == NULL);
token = strtok (str2, "ab");
ASSERT (token && 0 == strcmp (token, "x"));
token = strtok (NULL, "ab");
ASSERT (token == NULL);
#if !defined (__SUNPRO_C) && !defined (__sun__)
/* SunPro C compiler and GCC on Solaris have problem with strtok-ing after NULL */
token = strtok (NULL, "a");
ASSERT (token == NULL);
#endif
#endif
}
#if !defined (__APPLE__) // uchar.h/char16_t/char32_t are not supported on MacOS/Clang
// Test C11 UTF-8 behaviour.
static void
do_utf_8 (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if defined(__STDC_VERSION) && __STDC_VERSION >= 201112L
const char *str1 = u8"Ä ä";
const char *str2 = u8"\u00c4 ä";
const char *str3 = u8"Ä " "ä";
const char *str4 = u8"Ä " u8"ä";
const char *str5 = "Ä " u8"ä";
ASSERT (str1[0] == 0xc3);
ASSERT (str2[1] == 0x84);
ASSERT (!strcmp (str1, str2));
ASSERT (!strcmp (str1, str3));
ASSERT (!strcmp (str1, str4));
ASSERT (!strcmp (str1, str5));
#endif
#endif
}
// Test SDCC implementation-defined UTF-8 behaviour
// string literals are UTF-8 (as nearly all implementations out there)
static void
do_utf_8_sdcc (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if !(defined (__SDCC_pdk15) && defined(__SDCC_STACK_AUTO)) // Lack of code memory
#ifdef __SDCC
const char *str1 = "Ä ä";
const char *str2 = "\u00c4 ä";
const char *str3 = u8"Ä " "ä";
const char *str4 = "Ä " "ä";
const char *str5 = u8"Ä " u8"ä";
ASSERT (str1[0] == 0xc3);
ASSERT (str2[1] == 0x84);
ASSERT (!strcmp (str1, str2));
ASSERT (!strcmp (str1, str3));
ASSERT (!strcmp (str1, str4));
ASSERT (!strcmp (str1, str5));
ASSERT (!mblen(0, 0));
ASSERT (mblen(str1, 3) == 2);
ASSERT (mblen("test", 3) == 1);
ASSERT (mblen("", 3) == 0);
#endif
#endif
#endif
}
// Test C11 UTF-16 behaviour
static void
do_utf_16 (void)
{
#if defined(__STDC_UTF_16__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
const char16_t *str1 = u"Ä ä";
const char16_t *str2 = u"\u00c4 ä";
const char16_t *str3 = u"Ä " "ä";
const char16_t *str4 = "Ä " u"ä";
const char16_t *str5 = u"Ä " u"ä";
ASSERT (str1[0] == 0xc4);
ASSERT (str2[2] == 0xe4);
ASSERT (!memcmp (str1, str2, 4 * sizeof(char16_t)));
ASSERT (!memcmp (str1, str3, 4 * sizeof(char16_t)));
ASSERT (!memcmp (str1, str4, 4 * sizeof(char16_t)));
ASSERT (!memcmp (str1, str5, 4 * sizeof(char16_t)));
#endif
}
// Test C95 UTF-32 behaviour
static void
do_utf_32_c95 (void)
{
#ifndef __SDCC_pdk14 // Lack of memory
#if !(defined (__SDCC_pdk15) && defined(__SDCC_STACK_AUTO)) // Lack of code memory
#ifdef __STDC_ISO_10646__
const wchar_t *str1 = L"Ä ä";
const wchar_t *str2 = L"\u00c4 ä";
const wchar_t *str3 = L"Ä " "ä";
const wchar_t *str4 = "Ä " L"ä";
const wchar_t *str5 = L"Ä " L"ä";
ASSERT (str1[0] == 0xc4);
ASSERT (str2[2] == 0xe4);
ASSERT (wcslen (str1) == 3);
ASSERT (!memcmp (str1, str2, 4 * sizeof(wchar_t)));
ASSERT (!memcmp (str1, str3, 4 * sizeof(wchar_t)));
ASSERT (!memcmp (str1, str4, 4 * sizeof(wchar_t)));
ASSERT (!memcmp (str1, str5, 4 * sizeof(wchar_t)));
#endif
#endif
#endif
}
// Test C11 UTF-32 behaviour
static void
do_utf_32_c11 (void)
{
#if defined(__STDC_UTF_32__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
const char32_t *str1 = U"Ä ä";
const char32_t *str2 = U"\u00c4 ä";
const char32_t *str3 = U"Ä " "ä";
const char32_t *str4 = "Ä " U"ä";
const char32_t *str5 = U"Ä " U"ä";
ASSERT (str1[0] == 0xc4);
ASSERT (str2[2] == 0xe4);
ASSERT (!memcmp (str1, str2, 4 * sizeof(char32_t)));
ASSERT (!memcmp (str1, str3, 4 * sizeof(char32_t)));
ASSERT (!memcmp (str1, str4, 4 * sizeof(char32_t)));
ASSERT (!memcmp (str1, str5, 4 * sizeof(char32_t)));
#endif
}
static void
do_chinese (void)
{
#if defined(__STDC_UTF_32__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
const char32_t *p0 = U"史斌";
#endif
#ifdef __STDC_ISO_10646__
const wchar_t *p1 = L"史庭芳";
#endif
#if defined(__STDC_UTF_16__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
const char16_t *p2 = u"天津";
#endif
#if defined(__STDC_UTF_32__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
ASSERT (p0[0] == 0x53f2);
#endif
#ifdef __STDC_ISO_10646__
ASSERT (p1[2] == 0x82b3);
#endif
#if defined(__STDC_UTF_16__) && defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L
ASSERT (p2[1] == 0x6d25);
#endif
}
#endif // __APPLE__
static void
teststr (void)
{
do_teststrcmp ();
do_teststrcpy ();
do_teststrncmp ();
do_teststrpbrk ();
do_teststrrchr ();
do_teststrstr ();
do_teststrspn ();
do_teststrtok ();
#if !defined (__APPLE__)
do_utf_8 ();
do_utf_8_sdcc ();
do_utf_16 ();
do_utf_32_c95 ();
do_utf_32_c11 ();
do_chinese ();
#endif // __APPLE__
}
|
