summary refs log tree commit diff
path: root/string/test-strcmp.c
blob: 7b546d26e883bf9f572d56d91ac95cee21200e02 (plain) (blame)
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
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
/* Test and measure strcmp and wcscmp functions.
   Copyright (C) 1999-2017 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Written by Jakub Jelinek <jakub@redhat.com>, 1999.
   Added wcscmp support by Liubov Dmitrieva <liubov.dmitrieva@gmail.com>, 2011.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library 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
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

#define TEST_MAIN
#ifdef WIDE
# define TEST_NAME "wcscmp"
#else
# define TEST_NAME "strcmp"
#endif
#include "test-string.h"

#ifdef WIDE
# include <wchar.h>

# define L(str) L##str
# define STRCMP wcscmp
# define STRCPY wcscpy
# define STRLEN wcslen
# define MEMCPY wmemcpy
# define SIMPLE_STRCMP simple_wcscmp
# define STUPID_STRCMP stupid_wcscmp
# define CHAR wchar_t
# define UCHAR wchar_t
# define CHARBYTES 4
# define CHARBYTESLOG 2
# define CHARALIGN __alignof__ (CHAR)
# define MIDCHAR 0x7fffffff
# define LARGECHAR 0xfffffffe
# define CHAR__MAX WCHAR_MAX
# define CHAR__MIN WCHAR_MIN

/* Wcscmp uses signed semantics for comparison, not unsigned */
/* Avoid using substraction since possible overflow */

int
simple_wcscmp (const wchar_t *s1, const wchar_t *s2)
{
  wchar_t c1, c2;
  do
    {
      c1 = *s1++;
      c2 = *s2++;
      if (c2 == L'\0')
      return c1 - c2;
    }
  while (c1 == c2);

  return c1 < c2 ? -1 : 1;
}

int
stupid_wcscmp (const wchar_t *s1, const wchar_t *s2)
{
  size_t ns1 = wcslen (s1) + 1;
  size_t ns2 = wcslen (s2) + 1;
  size_t n = ns1 < ns2 ? ns1 : ns2;
  int ret = 0;

  wchar_t c1, c2;

  while (n--) {
    c1 = *s1++;
    c2 = *s2++;
    if ((ret = c1 < c2 ? -1 : c1 == c2 ? 0 : 1) != 0)
      break;
  }
  return ret;
}

#else
# include <limits.h>

# define L(str) str
# define STRCMP strcmp
# define STRCPY strcpy
# define STRLEN strlen
# define MEMCPY memcpy
# define SIMPLE_STRCMP simple_strcmp
# define STUPID_STRCMP stupid_strcmp
# define CHAR char
# define UCHAR unsigned char
# define CHARBYTES 1
# define CHARBYTESLOG 0
# define CHARALIGN 1
# define MIDCHAR 0x7f
# define LARGECHAR 0xfe
# define CHAR__MAX CHAR_MAX
# define CHAR__MIN CHAR_MIN

/* Strcmp uses unsigned semantics for comparison. */
int
simple_strcmp (const char *s1, const char *s2)
{
  int ret;

  while ((ret = *(unsigned char *) s1 - *(unsigned char*) s2++) == 0 && *s1++);
  return ret;
}

int
stupid_strcmp (const char *s1, const char *s2)
{
  size_t ns1 = strlen (s1) + 1;
  size_t ns2 = strlen (s2) + 1;
  size_t n = ns1 < ns2 ? ns1 : ns2;
  int ret = 0;

  while (n--)
    if ((ret = *(unsigned char *) s1++ - *(unsigned char *) s2++) != 0)
      break;
  return ret;
}
#endif

typedef int (*proto_t) (const CHAR *, const CHAR *);

IMPL (STUPID_STRCMP, 1)
IMPL (SIMPLE_STRCMP, 1)
IMPL (STRCMP, 1)

static int
check_result (impl_t *impl,
	     const CHAR *s1, const CHAR *s2,
	     int exp_result)
{
  int result = CALL (impl, s1, s2);
  if ((exp_result == 0 && result != 0)
      || (exp_result < 0 && result >= 0)
      || (exp_result > 0 && result <= 0))
    {
      error (0, 0, "Wrong result in function %s %d %d", impl->name,
	     result, exp_result);
      ret = 1;
      return -1;
    }

  return 0;
}

static void
do_one_test (impl_t *impl,
	     const CHAR *s1, const CHAR *s2,
	     int exp_result)
{
  if (check_result (impl, s1, s2, exp_result) < 0)
    return;
}

static void
do_test (size_t align1, size_t align2, size_t len, int max_char,
	 int exp_result)
{
  size_t i;

  CHAR *s1, *s2;

  if (len == 0)
    return;

  align1 &= 63;
  if (align1 + (len + 1) * CHARBYTES >= page_size)
    return;

  align2 &= 63;
  if (align2 + (len + 1) * CHARBYTES >= page_size)
    return;

  /* Put them close to the end of page.  */
  i = align1 + CHARBYTES * (len + 2);
  s1 = (CHAR *) (buf1 + ((page_size - i) / 16 * 16) + align1);
  i = align2 + CHARBYTES * (len + 2);
  s2 = (CHAR *) (buf2 + ((page_size - i) / 16 * 16)  + align2);

  for (i = 0; i < len; i++)
    s1[i] = s2[i] = 1 + (23 << ((CHARBYTES - 1) * 8)) * i % max_char;

  s1[len] = s2[len] = 0;
  s1[len + 1] = 23;
  s2[len + 1] = 24 + exp_result;
  s2[len - 1] -= exp_result;

  FOR_EACH_IMPL (impl, 0)
    do_one_test (impl, s1, s2, exp_result);
}

static void
do_random_tests (void)
{
	UCHAR *p1 = (UCHAR *) (buf1 + page_size - 512 * CHARBYTES);
	UCHAR *p2 = (UCHAR *) (buf2 + page_size - 512 * CHARBYTES);

	for (size_t n = 0; n < ITERATIONS; n++)
	  {
	    /* for wcscmp case align1 and align2 mean here alignment
	       in wchar_t symbols, it equal 4*k alignment in bytes, we
	       don't check other alignments like for example
	       p1 = (wchar_t *)(buf1 + 1)
	       because it's wrong using of wchar_t type.  */
	    size_t align1 = random () & 31;
	    size_t align2;
	    if (random () & 1)
	      align2 = random () & 31;
	    else
	      align2 = align1 + (random () & 24);
	    size_t pos = random () & 511;
	    size_t j = align1 > align2 ? align1 : align2;
	    if (pos + j >= 511)
	      pos = 510 - j - (random () & 7);
	    size_t len1 = random () & 511;
	    if (pos >= len1 && (random () & 1))
	      len1 = pos + (random () & 7);
	    if (len1 + j >= 512)
	      len1 = 511 - j - (random () & 7);
	    size_t len2;
	    if (pos >= len1)
	      len2 = len1;
	    else
	      len2 = len1 + (len1 != 511 - j ? random () % (511 - j - len1) : 0);
	    j = (pos > len2 ? pos : len2) + align1 + 64;
	    if (j > 512)
	      j = 512;
	    for (size_t i = 0; i < j; ++i)
	      {
		p1[i] = random () & 255;
		if (i < len1 + align1 && !p1[i])
		  {
		    p1[i] = random () & 255;
		    if (!p1[i])
		      p1[i] = 1 + (random () & 127);
		  }
	      }
	    for (size_t i = 0; i < j; ++i)
	      {
		p2[i] = random () & 255;
		if (i < len2 + align2 && !p2[i])
		  {
		    p2[i] = random () & 255;
		    if (!p2[i])
		      p2[i] = 1 + (random () & 127);
		  }
	      }

	    int result = 0;
	    MEMCPY (p2 + align2, p1 + align1, pos);
	    if (pos < len1)
	      {
		if (p2[align2 + pos] == p1[align1 + pos])
		  {
		    p2[align2 + pos] = random () & 255;
		    if (p2[align2 + pos] == p1[align1 + pos])
		      p2[align2 + pos] = p1[align1 + pos] + 3 + (random () & 127);
		  }

		if (p1[align1 + pos] < p2[align2 + pos])
		  result = -1;
		else
		  result = 1;
	      }
	    p1[len1 + align1] = 0;
	    p2[len2 + align2] = 0;

	    FOR_EACH_IMPL (impl, 1)
	      {
		int r = CALL (impl, (CHAR *) (p1 + align1), (CHAR *) (p2 + align2));
		/* Test whether on 64-bit architectures where ABI requires
		   callee to promote has the promotion been done.  */
		asm ("" : "=g" (r) : "0" (r));
		if ((r == 0 && result)
		    || (r < 0 && result >= 0)
		    || (r > 0 && result <= 0))
		  {
		    error (0, 0, "Iteration %zd - wrong result in function %s (align in bytes: %zd, align in bytes: %zd, len1:  %zd, len2: %zd, pos: %zd) %d != %d, p1 %p p2 %p",
			   n, impl->name, (size_t) (p1 + align1) & 63, (size_t) (p1 + align2) & 63, len1, len2, pos, r, result, p1, p2);
		    ret = 1;
		  }
	      }
     }
}

static void
check (void)
{
  CHAR *s1 = (CHAR *) (buf1 + 0xb2c);
  CHAR *s2 = (CHAR *) (buf1 + 0xfd8);

  STRCPY(s1, L("abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrs"));
  STRCPY(s2, L("abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyzabcdefghijkLMNOPQRSTUV"));

  /* Check correct working for negatives values */

  s1[0] = 1;
  s2[0] = 1;
  s1[1] = 1;
  s2[1] = 1;
  s1[2] = -1;
  s2[2] = 3;
  s1[3] = 0;
  s2[3] = -1;

  /* Check possible overflow bug, actual more for wcscmp */

  s1[7] = CHAR__MIN;
  s2[7] = CHAR__MAX;

  size_t l1 = STRLEN (s1);
  size_t l2 = STRLEN (s2);

  for (size_t i1 = 0; i1 < l1; i1++)
    for (size_t i2 = 0; i2 < l2; i2++)
      {
		int exp_result = SIMPLE_STRCMP (s1 + i1, s2 + i2);
		FOR_EACH_IMPL (impl, 0)
		check_result (impl, s1 + i1, s2 + i2, exp_result);
      }

  /* Test cases where there are multiple zero bytes after the first.  */

  for (size_t i = 0; i < 16 + 1; i++)
    {
      s1[i] = 0x00;
      s2[i] = 0x00;
    }

  for (size_t i = 0; i < 16; i++)
    {
      int exp_result;

      for (int val = 0x01; val < 0x100; val++)
	{
	  for (size_t j = 0; j < i; j++)
	    {
	      s1[j] = val;
	      s2[j] = val;
	    }

	  s2[i] = val;

	  exp_result = SIMPLE_STRCMP (s1, s2);
	  FOR_EACH_IMPL (impl, 0)
	    check_result (impl, s1, s2, exp_result);
	}
    }
}


int
test_main (void)
{
  size_t i;

  test_init ();
  check();

  printf ("%23s", "");
  FOR_EACH_IMPL (impl, 0)
    printf ("\t%s", impl->name);
  putchar ('\n');

  for (i = 1; i < 32; ++i)
    {
      do_test (CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 0);
      do_test (CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 1);
      do_test (CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, -1);
    }

  for (i = 1; i < 10 + CHARBYTESLOG; ++i)
    {
      do_test (0, 0, 2 << i, MIDCHAR, 0);
      do_test (0, 0, 2 << i, LARGECHAR, 0);
      do_test (0, 0, 2 << i, MIDCHAR, 1);
      do_test (0, 0, 2 << i, LARGECHAR, 1);
      do_test (0, 0, 2 << i, MIDCHAR, -1);
      do_test (0, 0, 2 << i, LARGECHAR, -1);
      do_test (0, CHARBYTES * i, 2 << i, MIDCHAR, 1);
      do_test (CHARBYTES * i, CHARBYTES * (i + 1), 2 << i, LARGECHAR, 1);
    }

  for (i = 1; i < 8; ++i)
    {
      do_test (CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, 0);
      do_test (2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, 0);
      do_test (CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, 1);
      do_test (2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, 1);
      do_test (CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, -1);
      do_test (2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, -1);
    }

  do_random_tests ();
  return ret;
}

#include "../test-skeleton.c"