File: quoting-test.c

package info (click to toggle)
amanda 1%3A3.5.4-2
  • links: PTS, VCS
  • area: main
  • in suites: trixie
  • size: 23,420 kB
  • sloc: ansic: 197,218; perl: 109,331; xml: 16,126; sh: 4,180; makefile: 2,810; awk: 502; lex: 407; yacc: 347; tcl: 118; sql: 19; sed: 16; php: 2
file content (497 lines) | stat: -rw-r--r-- 12,424 bytes parent folder | download | duplicates (5)
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
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
/*
 * Copyright (c) 2008-2012 Zmanda, Inc.  All Rights Reserved.
 * Copyright (c) 2013-2016 Carbonite, Inc.  All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program 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 General Public License
 * for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 *
 * Contact information: Carbonite Inc., 756 N Pastoria Ave
 * Sunnyvale, CA 94085, or: http://www.zmanda.com
 *
 * Author: Dustin J. Mitchell <dustin@zmanda.com>
 */

#include "amanda.h"
#include "testutils.h"
#include "amutil.h"

/* Utilities */

static char *
safestr(const char *str) {
    static char hex[] = "0123456789abcdef";
    const char *p;
    char *result = malloc(3 + strlen(str) * 3);
    char *r = result;

    *(r++) = '|';
    for (p = str; *p; p++) {
	if (isprint((int)*p)) {
	    *(r++) = *p;
	} else {
	    *(r++) = '#';
	    *(r++) = hex[((*p)&0xf0) >> 4];
	    *(r++) = hex[(*p)&0xf];
	}
    }
    *(r++) = '|';
    *(r++) = '\0';

    return result;
}

char * quotable_strings[] = {
    "",
    "simple",
    "sp a ces",
    "\"foo bar\"",
    "back\\slash",
    "escaped\\ space",
    "escaped\\\"quote",
    "balanced \"internal\" quotes",
    "\"already quoted\" string",
    "string that's \"already quoted\"",
    "internal\"quote",
    "bs-end\\",
    "backslash\\nletter",
    "backslash\\tletter",
    "\t", "\r", "\n", "\f", "\004",
    "new\nline",
    "newline-end\n",
    "ta\tb",
    "tab-end\t",
    "\\\\\\\\",
    "\"",
    NULL
};

/****
 * Round-trip testing of quoting functions
 */

static gboolean
test_round_trip(void)
{
    char **strp;
    gboolean success = TRUE;

    for (strp = quotable_strings; *strp; strp++) {
	char *quoted, *unquoted;

	quoted = quote_string(*strp);
	unquoted = unquote_string(quoted);

	/* if they're not the same, complain */
	if (!g_str_equal(*strp, unquoted)) {
	    char *safe_orig = safestr(*strp);
	    char *safe_quoted = safestr(quoted);
	    char *safe_unquoted = safestr(unquoted);

	    printf("  bad round-trip: %s -quote_string-> %s -unquote_string-> %s\n",
		safe_orig, safe_quoted, safe_unquoted);

	    amfree(safe_orig);
	    amfree(safe_quoted);
	    amfree(safe_unquoted);

	    success = FALSE;
	}

	amfree(quoted);
	amfree(unquoted);
    }

    return success;
}

/***
 * Test that the new split_quoted_strings acts identically to
 * the old split(), albeit with a different set of arguments and
 * return value.  Note that we only test with a delimiter of " ",
 * as split() is not used with any other delimiter.
 */

static gboolean
compare_strv(
    const char **exp,
    char **got,
    const char *source,
    const char *original)
{
    const char **a = exp;
    char **b = got;
    while (*a && *b) {
	if (!g_str_equal(*a, *b))
	    break;
	a++; b++;
    }

    /* did we exit the loop early, or were they different lengths? */
    if (*a || *b) {
	char *safe;

	safe = safestr(original);
	g_printf("  %s: expected [", safe);
	amfree(safe);
	for (a = exp; *a; a++) {
	    safe = safestr(*a);
	    g_printf("%s%s", safe, *(a+1)? ", " : "");
	    amfree(safe);
	}
	g_printf("] but got [");
	for (b = got; *b; b++) {
	    safe = safestr(*b);
	    g_printf("%s%s", safe, *(b+1)? ", " : "");
	    amfree(safe);
	}
	g_printf("] using %s.\n", source);

	return FALSE;
    }

    return TRUE;
}

static gboolean
test_split_quoted_strings(void)
{
    char **iter1, **iter2, **iter3;
    gboolean success = TRUE;
    char *middle_strings[] = {
	"",
	"foo",
	"\"foo\"",
	"sp aces",
	NULL,
    };

    /* the idea here is to loop over all triples of strings, forming a
     * string by quoting them with quote_string and inserting a space, then
     * re-splitting with split_quoted_string.  This should get us back to our
     * starting point. */

    for (iter1 = quotable_strings; *iter1; iter1++) {
	for (iter2 = middle_strings; *iter2; iter2++) {
	    for (iter3 = quotable_strings; *iter3; iter3++) {
		char *q1 = quote_string(*iter1);
		char *q2 = quote_string(*iter2);
		char *q3 = quote_string(*iter3);
		const char *expected[4] = { *iter1, *iter2, *iter3, NULL };
		char *combined = g_strjoin(NULL, q1, " ", q2, " ", q3, NULL);
		char **tokens;

		tokens = split_quoted_strings(combined);

		success = compare_strv(expected, tokens, "split_quoted_strings", combined)
			&& success;

		amfree(q1);
		amfree(q2);
		amfree(q3);
		amfree(combined);
		g_strfreev(tokens);
	    }
	}
    }

    return success;
}

/****
 * Test splitting some edge cases and invalid strings
 */

struct trial {
    const char *combined;
    const char *expected[5];
};

static gboolean
test_split_quoted_strings_edge(void)
{
    gboolean success = TRUE;
    struct trial trials[] = {
	{ "", { "", NULL, } },
	{ " ", { "", "", NULL } },
	{ " x", { "", "x", NULL } },
	{ "x ", { "x", "", NULL } },
	{ "x\\ y", { "x y", NULL } },
	{ "\\", { "", NULL } }, /* inv */
	{ "z\\", { "z", NULL } }, /* inv */
	{ "z\"", { "z", NULL } }, /* inv */
	{ "\" \" \"", { " ", "", NULL } }, /* inv */
	{ NULL, { NULL, } },
    };
    struct trial *trial = trials;

    while (trial->combined) {
	char **tokens = split_quoted_strings(trial->combined);

	success = compare_strv(trial->expected, tokens,
			       "split_quoted_strings", trial->combined)
	    && success;

	g_strfreev(tokens);
	trial++;
    }

    return success;
}

/****
 * Test unquoting of some pathological strings
 */
static gboolean
test_unquote_string(void)
{
    gboolean success = TRUE;
    char *tests[] = {
	"simple",              "simple",
	"\"quoted\"",          "quoted",
	"s p a c e",           "s p a c e",

	/* special escape characters */
	"esc \\\" quote",      "esc \" quote",
	"esc \\t tab",         "esc \t tab",
	"esc \\\\ esc",        "esc \\ esc",
	"esc \\02 oct",         "esc \02 oct",
	"esc \\7 oct",         "esc \7 oct",
	"esc \\17 oct",        "esc \17 oct",
	"esc \\117 oct",       "esc \117 oct",
	"esc \\1117 oct",      "esc \1117 oct", /* '7' is distinct char */

	/* same, but pre-quoted */
	"\"esc \\\" quote\"",  "esc \" quote",
	"\"esc \\t tab\"",     "esc \t tab",
	"\"esc \\\\ esc\"",    "esc \\ esc",
	"\"esc \\02 oct\"",     "esc \02 oct",
	"\"esc \\7 oct\"",     "esc \7 oct",
	"\"esc \\17 oct\"",    "esc \17 oct",
	"\"esc \\117 oct\"",   "esc \117 oct",
	"\"esc \\1117 oct\"",  "esc \1117 oct", /* '7' is distinct char */

	/* strips balanced quotes, even inside the string */
	">>\"x\"<<",           ">>x<<",
	">>\"x\"-\"y\"<<",     ">>x-y<<",

	/* pathological, but valid */
	"\\\\",                "\\",
	"\"\\\"\"",            "\"",
	"\"\\\\\"",            "\\",
	"--\\\"",              "--\"",
	"\\\"--",              "\"--",

	/* invalid strings (handling here is arbitrary, but these tests
	 * will alert us if the handling changes) */
	"\\",                  "", /* trailing backslash is ignored */
	"xx\\",                "xx", /* ditto */
	"\\\\\\\\\\\\\\",      "\\\\\\",   /* ditto */
	"\\777",               "\377", /* 0777 & 0xff = 0xff */
	"\"--",                "--", /* leading quote is dropped */
	"--\"",                "--", /* trailing quote is dropped */

	NULL, NULL,
    };
    char **strp;

    for (strp = tests; *strp;) {
	char *quoted = *(strp++);
	char *expected = *(strp++);
	char *unquoted = unquote_string(quoted);

	/* if they're not the same, complain */
	if (!g_str_equal(expected, unquoted)) {
	    char *safe_quoted = safestr(quoted);
	    char *safe_unquoted = safestr(unquoted);
	    char *safe_expected = safestr(expected);

	    printf("  %s unquoted to %s; expected %s.\n",
		safe_quoted, safe_unquoted, safe_expected);

	    amfree(safe_quoted);
	    amfree(safe_unquoted);
	    amfree(safe_expected);

	    success = FALSE;
	}

	amfree(unquoted);
    }

    return success;
}

/****
 * Test the strquotedstr function
 */
static gboolean
test_strquotedstr_skipping(void)
{
    char **iter1, **iter2;
    gboolean success = TRUE;

    /* the idea here is to loop over all pairs of strings, forming a
     * string by quoting them with quote_string and inserting a space, then
     * re-splitting with strquotedstr.  This should get us back to our
     * starting point. Note that we have to begin with a non-quoted identifier,
     * becuse strquotedstr requires that strtok_r has already been called. */

    for (iter1 = quotable_strings; *iter1; iter1++) {
	for (iter2 = quotable_strings; *iter2; iter2++) {
	    char *q1 = quote_string(*iter1);
	    char *q2 = quote_string(*iter2);
	    char *combined = g_strjoin(NULL, "START ", q1, " ", q2, NULL);
	    char *copy = g_strdup(combined);
	    char *saveptr = NULL;
	    char *tok;
	    int i;

	    tok = strtok_r(copy, " ", &saveptr);

	    for (i = 1; i <= 2; i++) {
		char *expected = (i == 1)? q1:q2;
		tok = strquotedstr(&saveptr);
		if (!tok) {
		    g_fprintf(stderr, "while parsing '%s', call %d to strquotedstr returned NULL\n",
			      combined, i);
		    success = FALSE;
		    goto next;
		}
		if (!g_str_equal(tok, expected)) {
		    char *safe = safestr(tok);

		    g_fprintf(stderr, "while parsing '%s', call %d to strquotedstr returned '%s' "
			      "but '%s' was expected.\n",
			      combined, i, safe, expected);
		    amfree(safe);
		    success = FALSE;
		    goto next;
		}
	    }

	    if (strquotedstr(&saveptr) != NULL) {
		g_fprintf(stderr, "while parsing '%s', call 3 to strquotedstr did not return NULL\n",
			  combined);
		success = FALSE;
		goto next;
	    }
next:
	    amfree(q1);
	    amfree(q2);
	    amfree(copy);
	    amfree(combined);
	}
    }

    return success;
}

static gboolean
test_strquotedstr_edge_invalid(void)
{
    gboolean success = TRUE;
    char *invalid[] = {
	"X \"abc", /* unterminated */
	"X \"ab cd", /* unterminated second token */
	"X a\"b cd", /* unterminated second token with internal quote */
	"X b\\", /* trailing backslash */
	"X \"b\\", /* trailing backslash in quote */
	"X \"b\\\"", /* backslash'd ending quote */
	NULL
    };
    char **iter;

    /* run strquotedstr on a bunch of invalid tokens.  It should return NULL */

    for (iter = invalid; *iter; iter++) {
	char *copy = g_strdup(*iter);
	char *tok;
	char *saveptr = NULL;

	tok = strtok_r(copy, " ", &saveptr);
	tok = strquotedstr(&saveptr);
	if (tok != NULL) {
	    g_fprintf(stderr, "while parsing invalid '%s', strquotedstr did not return NULL\n",
		      *iter);
	    success = FALSE;
	}

	amfree(copy);
    }

    return success;
}

static gboolean
test_strquotedstr_edge_valid(void)
{
    gboolean success = TRUE;
    char *valid[] = {
	/* input */	    /* expected (omitting "X") */
	"X abc\\ def",      "abc\\ def", /* backslashed space */
	"X \"abc\\ def\"",  "\"abc\\ def\"", /* quoted, backslashed space */
	"X a\"  \"b",       "a\"  \"b", /* quoted spaces */
	NULL, NULL
    };
    char **iter;

    /* run strquotedstr on a bunch of valid, but tricky, tokens.  It should return NULL */

    for (iter = valid; *iter; iter += 2) {
	char *copy = g_strdup(*iter);
	char *expected = *(iter+1);
	char *tok;
	char *saveptr = NULL;

	tok = strtok_r(copy, " ", &saveptr);
	tok = strquotedstr(&saveptr);
	if (tok == NULL) {
	    g_fprintf(stderr, "while parsing valid '%s', strquotedstr returned NULL\n",
		      *iter);
	    success = FALSE;
	} else if (!g_str_equal(tok, expected)) {
	    g_fprintf(stderr, "while parsing valid '%s', strquotedstr returned '%s' while "
		      "'%s' was expected\n",
		      *iter, tok, expected);
	    success = FALSE;
	}

	amfree(copy);
    }

    return success;
}

/*
 * Main driver
 */

int
main(int argc, char **argv)
{
    static TestUtilsTest tests[] = {
	TU_TEST(test_round_trip, 90),
	TU_TEST(test_unquote_string, 90),
	TU_TEST(test_split_quoted_strings, 90),
	TU_TEST(test_split_quoted_strings_edge, 90),
	TU_TEST(test_strquotedstr_skipping, 90),
	TU_TEST(test_strquotedstr_edge_invalid, 90),
	TU_TEST(test_strquotedstr_edge_valid, 90),
	TU_END()
    };

    glib_init();

    return testutils_run_tests(argc, argv, tests);
}