2 * This file is part of DisOrder.
3 * Copyright (C) 2005, 2007 Richard Kettlewell
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
10 * This program is distributed in the hope that it will be useful, but
11 * WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * General Public License for more details.
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
20 /** @file lib/test.c @brief Library tests */
31 #include <sys/types.h>
47 #include "inputline.h"
53 #include "selection.h"
61 static int tests
, errors
;
62 static int fail_first
;
64 static void count_error() {
70 /** @brief Checks that @p expr is nonzero */
71 #define insist(expr) do { \
74 fprintf(stderr, "%s:%d: error checking %s\n", \
75 __FILE__, __LINE__, #expr); \
80 static const char *format(const char *s
) {
86 while((c
= (unsigned char)*s
++)) {
87 if(c
>= ' ' && c
<= '~')
90 sprintf(buf
, "\\x%02X", (unsigned)c
);
91 dynstr_append_string(&d
, buf
);
98 static const char *format_utf32(const uint32_t *s
) {
105 sprintf(buf
, " %04lX", (long)c
);
106 dynstr_append_string(&d
, buf
);
108 dynstr_terminate(&d
);
112 #define check_string(GOT, WANT) do { \
113 const char *got = GOT; \
114 const char *want = WANT; \
117 fprintf(stderr, "%s:%d: %s returned 0\n", \
118 __FILE__, __LINE__, #GOT); \
120 } else if(strcmp(want, got)) { \
121 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \
122 __FILE__, __LINE__, #GOT, format(got), format(want)); \
128 #define check_string_prefix(GOT, WANT) do { \
129 const char *got = GOT; \
130 const char *want = WANT; \
133 fprintf(stderr, "%s:%d: %s returned 0\n", \
134 __FILE__, __LINE__, #GOT); \
136 } else if(strncmp(want, got, strlen(want))) { \
137 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s...\n", \
138 __FILE__, __LINE__, #GOT, format(got), format(want)); \
144 #define check_integer(GOT, WANT) do { \
145 const intmax_t got = GOT, want = WANT; \
147 fprintf(stderr, "%s:%d: %s returned: %jd expected: %jd\n", \
148 __FILE__, __LINE__, #GOT, got, want); \
154 static uint32_t *ucs4parse(const char *s
) {
155 struct dynstr_ucs4 d
;
158 dynstr_ucs4_init(&d
);
161 dynstr_ucs4_append(&d
, strtoul(s
, &e
, 0));
162 if(errno
) fatal(errno
, "strtoul (%s)", s
);
165 dynstr_ucs4_terminate(&d
);
169 static void test_utf8(void) {
170 /* Test validutf8, convert to UCS-4, check the answer is right,
171 * convert back to UTF-8, check we got to where we started */
172 #define U8(CHARS, WORDS) do { \
173 uint32_t *w = ucs4parse(WORDS); \
177 insist(validutf8(CHARS)); \
178 ucs = utf8_to_utf32(CHARS, strlen(CHARS), 0); \
180 insist(!utf32_cmp(w, ucs)); \
181 u8 = utf32_to_utf8(ucs, utf32_len(ucs), 0); \
183 check_string(u8, CHARS); \
186 fprintf(stderr
, "test_utf8\n");
187 #define validutf8(S) utf8_valid((S), strlen(S))
193 /* ASCII characters */
195 U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~",
196 "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d "
197 "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a "
198 "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 "
199 "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 "
200 "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 "
201 "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e "
202 "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b "
204 U8("\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\177",
205 "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 "
206 "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d "
211 /* UTF8-2 = %xC2-DF UTF8-tail */
212 insist(!validutf8("\xC0\x80"));
213 insist(!validutf8("\xC1\x80"));
214 insist(!validutf8("\xC2\x7F"));
215 U8("\xC2\x80", "0x80");
216 U8("\xDF\xBF", "0x7FF");
217 insist(!validutf8("\xDF\xC0"));
219 /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
220 * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
222 insist(!validutf8("\xE0\x9F\x80"));
223 U8("\xE0\xA0\x80", "0x800");
224 U8("\xE0\xBF\xBF", "0xFFF");
225 insist(!validutf8("\xE0\xC0\xBF"));
227 insist(!validutf8("\xE1\x80\x7F"));
228 U8("\xE1\x80\x80", "0x1000");
229 U8("\xEC\xBF\xBF", "0xCFFF");
230 insist(!validutf8("\xEC\xC0\xBF"));
232 U8("\xED\x80\x80", "0xD000");
233 U8("\xED\x9F\xBF", "0xD7FF");
234 insist(!validutf8("\xED\xA0\xBF"));
236 insist(!validutf8("\xEE\x7f\x80"));
237 U8("\xEE\x80\x80", "0xE000");
238 U8("\xEF\xBF\xBF", "0xFFFF");
239 insist(!validutf8("\xEF\xC0\xBF"));
241 /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
242 * %xF4 %x80-8F 2( UTF8-tail )
244 insist(!validutf8("\xF0\x8F\x80\x80"));
245 U8("\xF0\x90\x80\x80", "0x10000");
246 U8("\xF0\xBF\xBF\xBF", "0x3FFFF");
247 insist(!validutf8("\xF0\xC0\x80\x80"));
249 insist(!validutf8("\xF1\x80\x80\x7F"));
250 U8("\xF1\x80\x80\x80", "0x40000");
251 U8("\xF3\xBF\xBF\xBF", "0xFFFFF");
252 insist(!validutf8("\xF3\xC0\x80\x80"));
254 insist(!validutf8("\xF4\x80\x80\x7F"));
255 U8("\xF4\x80\x80\x80", "0x100000");
256 U8("\xF4\x8F\xBF\xBF", "0x10FFFF");
257 insist(!validutf8("\xF4\x90\x80\x80"));
258 insist(!validutf8("\xF4\x80\xFF\x80"));
260 /* miscellaneous non-UTF-8 rubbish */
261 insist(!validutf8("\x80"));
262 insist(!validutf8("\xBF"));
263 insist(!validutf8("\xC0"));
264 insist(!validutf8("\xC0\x7F"));
265 insist(!validutf8("\xC0\xC0"));
266 insist(!validutf8("\xE0"));
267 insist(!validutf8("\xE0\x7F"));
268 insist(!validutf8("\xE0\xC0"));
269 insist(!validutf8("\xE0\x80"));
270 insist(!validutf8("\xE0\x80\x7f"));
271 insist(!validutf8("\xE0\x80\xC0"));
272 insist(!validutf8("\xF0"));
273 insist(!validutf8("\xF0\x7F"));
274 insist(!validutf8("\xF0\xC0"));
275 insist(!validutf8("\xF0\x80"));
276 insist(!validutf8("\xF0\x80\x7f"));
277 insist(!validutf8("\xF0\x80\xC0"));
278 insist(!validutf8("\xF0\x80\x80\x7f"));
279 insist(!validutf8("\xF0\x80\x80\xC0"));
280 insist(!validutf8("\xF5\x80\x80\x80"));
281 insist(!validutf8("\xF8"));
284 static int test_multipart_callback(const char *s
, void *u
) {
285 struct vector
*parts
= u
;
287 vector_append(parts
, (char *)s
);
291 static void test_mime(void) {
293 struct vector parts
[1];
295 fprintf(stderr
, "test_mime\n");
298 insist(!mime_content_type("text/plain", &t
, &n
, &v
));
299 check_string(t
, "text/plain");
303 insist(mime_content_type("TEXT ((broken) comment", &t
, &n
, &v
) < 0);
304 insist(mime_content_type("TEXT ((broken) comment\\", &t
, &n
, &v
) < 0);
307 insist(!mime_content_type("TEXT ((nested)\\ comment) /plain", &t
, &n
, &v
));
308 check_string(t
, "text/plain");
313 insist(!mime_content_type(" text/plain ; Charset=\"utf-\\8\"", &t
, &n
, &v
));
314 check_string(t
, "text/plain");
315 check_string(n
, "charset");
316 check_string(v
, "utf-8");
319 insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t
, &n
, &v
));
320 check_string(t
, "text/plain");
321 check_string(n
, "charset");
322 check_string(v
, "ISO-8859-1");
325 insist(!mime_rfc2388_content_disposition("form-data; name=\"field1\"", &t
, &n
, &v
));
326 check_string(t
, "form-data");
327 check_string(n
, "name");
328 check_string(v
, "field1");
330 insist(!mime_rfc2388_content_disposition("inline", &t
, &n
, &v
));
331 check_string(t
, "inline");
335 /* Current versions of the code only understand a single arg to these
336 * headers. This is a bug at the level they work at but suffices for
337 * DisOrder's current purposes. */
339 insist(!mime_rfc2388_content_disposition(
340 "attachment; filename=genome.jpeg;\n"
341 "modification-date=\"Wed, 12 Feb 1997 16:29:51 -0500\"",
343 check_string(t
, "attachment");
344 check_string(n
, "filename");
345 check_string(v
, "genome.jpeg");
348 insist(mime_multipart("--outer\r\n"
349 "Content-Type: text/plain\r\n"
350 "Content-Disposition: inline\r\n"
351 "Content-Description: text-part-1\r\n"
353 "Some text goes here\r\n"
356 "Content-Type: multipart/mixed; boundary=inner\r\n"
357 "Content-Disposition: attachment\r\n"
358 "Content-Description: multipart-2\r\n"
361 "Content-Type: text/plain\r\n"
362 "Content-Disposition: inline\r\n"
363 "Content-Description: text-part-2\r\n"
365 "Some more text here.\r\n"
368 "Content-Type: image/jpeg\r\n"
369 "Content-Disposition: attachment\r\n"
370 "Content-Description: jpeg-1\r\n"
375 test_multipart_callback
,
378 check_integer(parts
->nvec
, 2);
379 check_string(parts
->vec
[0],
380 "Content-Type: text/plain\r\n"
381 "Content-Disposition: inline\r\n"
382 "Content-Description: text-part-1\r\n"
384 "Some text goes here\r\n");
385 check_string(parts
->vec
[1],
386 "Content-Type: multipart/mixed; boundary=inner\r\n"
387 "Content-Disposition: attachment\r\n"
388 "Content-Description: multipart-2\r\n"
391 "Content-Type: text/plain\r\n"
392 "Content-Disposition: inline\r\n"
393 "Content-Description: text-part-2\r\n"
395 "Some more text here.\r\n"
398 "Content-Type: image/jpeg\r\n"
399 "Content-Disposition: attachment\r\n"
400 "Content-Description: jpeg-1\r\n"
404 /* No trailing CRLF is _correct_ - see RFC2046 5.1.1 note regarding CRLF
405 * preceding the boundary delimiter line. An implication of this is that we
406 * must cope with partial lines at the end of the input when recursively
407 * decomposing a multipart message. */
409 insist(mime_multipart("--inner\r\n"
410 "Content-Type: text/plain\r\n"
411 "Content-Disposition: inline\r\n"
412 "Content-Description: text-part-2\r\n"
414 "Some more text here.\r\n"
417 "Content-Type: image/jpeg\r\n"
418 "Content-Disposition: attachment\r\n"
419 "Content-Description: jpeg-1\r\n"
423 test_multipart_callback
,
426 check_integer(parts
->nvec
, 2);
427 check_string(parts
->vec
[0],
428 "Content-Type: text/plain\r\n"
429 "Content-Disposition: inline\r\n"
430 "Content-Description: text-part-2\r\n"
432 "Some more text here.\r\n");
433 check_string(parts
->vec
[1],
434 "Content-Type: image/jpeg\r\n"
435 "Content-Disposition: attachment\r\n"
436 "Content-Description: jpeg-1\r\n"
442 check_string(mime_qp(""), "");
443 check_string(mime_qp("foobar"), "foobar");
444 check_string(mime_qp("foo=20bar"), "foo bar");
445 check_string(mime_qp("x \r\ny"), "x\r\ny");
446 check_string(mime_qp("x=\r\ny"), "xy");
447 check_string(mime_qp("x= \r\ny"), "xy");
448 check_string(mime_qp("x =\r\ny"), "x y");
449 check_string(mime_qp("x = \r\ny"), "x y");
452 check_string(mime_qp("Now's the time =\r\n"
453 "for all folk to come=\r\n"
454 " to the aid of their country."),
455 "Now's the time for all folk to come to the aid of their country.");
457 check_string(mime_base64(""), "");
458 check_string(mime_base64("BBBB"), "\x04\x10\x41");
459 check_string(mime_base64("////"), "\xFF\xFF\xFF");
460 check_string(mime_base64("//BB"), "\xFF\xF0\x41");
461 check_string(mime_base64("BBBB//BB////"),
462 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
463 check_string(mime_base64("B B B B / / B B / / / /"),
464 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
465 check_string(mime_base64("B\r\nBBB.// B-B//~//"),
466 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
467 check_string(mime_base64("BBBB="),
469 check_string(mime_base64("BBBBx="), /* not actually valid base64 */
471 check_string(mime_base64("BBBB BB=="),
472 "\x04\x10\x41" "\x04");
473 check_string(mime_base64("BBBB BBB="),
474 "\x04\x10\x41" "\x04\x10");
477 static void test_hex(void) {
479 static const unsigned char h
[] = { 0x00, 0xFF, 0x80, 0x7F };
483 fprintf(stderr
, "test_hex\n");
485 for(n
= 0; n
<= UCHAR_MAX
; ++n
) {
487 insist(unhexdigitq(n
) == -1);
489 insist(unhexdigitq('0') == 0);
490 insist(unhexdigitq('1') == 1);
491 insist(unhexdigitq('2') == 2);
492 insist(unhexdigitq('3') == 3);
493 insist(unhexdigitq('4') == 4);
494 insist(unhexdigitq('5') == 5);
495 insist(unhexdigitq('6') == 6);
496 insist(unhexdigitq('7') == 7);
497 insist(unhexdigitq('8') == 8);
498 insist(unhexdigitq('9') == 9);
499 insist(unhexdigitq('a') == 10);
500 insist(unhexdigitq('b') == 11);
501 insist(unhexdigitq('c') == 12);
502 insist(unhexdigitq('d') == 13);
503 insist(unhexdigitq('e') == 14);
504 insist(unhexdigitq('f') == 15);
505 insist(unhexdigitq('A') == 10);
506 insist(unhexdigitq('B') == 11);
507 insist(unhexdigitq('C') == 12);
508 insist(unhexdigitq('D') == 13);
509 insist(unhexdigitq('E') == 14);
510 insist(unhexdigitq('F') == 15);
511 check_string(hex(h
, sizeof h
), "00ff807f");
512 check_string(hex(0, 0), "");
513 u
= unhex("00ff807f", &ul
);
515 insist(memcmp(u
, h
, 4) == 0);
516 u
= unhex("00FF807F", &ul
);
518 insist(memcmp(u
, h
, 4) == 0);
521 fprintf(stderr
, "2 ERROR reports expected {\n");
522 insist(unhex("F", 0) == 0);
523 insist(unhex("az", 0) == 0);
524 fprintf(stderr
, "}\n");
527 static void test_casefold(void) {
529 const char *input
, *canon_folded
, *compat_folded
, *canon_expected
, *compat_expected
;
531 fprintf(stderr
, "test_casefold\n");
533 /* This isn't a very exhaustive test. Unlike for normalization, there don't
534 * seem to be any public test vectors for these algorithms. */
536 for(c
= 1; c
< 256; ++c
) {
537 input
= utf32_to_utf8(&c
, 1, 0);
538 canon_folded
= utf8_casefold_canon(input
, strlen(input
), 0);
539 compat_folded
= utf8_casefold_compat(input
, strlen(input
), 0);
542 if((c
>= 'A' && c
<= 'Z')
543 || (c
>= 0xC0 && c
<= 0xDE && c
!= 0xD7))
548 case 0xB5: /* MICRO SIGN */
549 l
= 0x3BC; /* GREEK SMALL LETTER MU */
551 case 0xDF: /* LATIN SMALL LETTER SHARP S */
552 check_string(canon_folded
, "ss");
553 check_string(compat_folded
, "ss");
559 /* Case-folded data is now normalized */
560 d
= utf32_decompose_canon(&l
, 1, 0);
561 canon_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
562 if(strcmp(canon_folded
, canon_expected
)) {
563 fprintf(stderr
, "%s:%d: canon-casefolding %#lx got '%s', expected '%s'\n",
564 __FILE__
, __LINE__
, (unsigned long)c
,
565 format(canon_folded
), format(canon_expected
));
569 d
= utf32_decompose_compat(&l
, 1, 0);
570 compat_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
571 if(strcmp(compat_folded
, compat_expected
)) {
572 fprintf(stderr
, "%s:%d: compat-casefolding %#lx got '%s', expected '%s'\n",
573 __FILE__
, __LINE__
, (unsigned long)c
,
574 format(compat_folded
), format(compat_expected
));
580 check_string(utf8_casefold_canon("", 0, 0), "");
585 const char *expect
[10];
589 /* Only whitespace and punctuation */
596 { "wibble", { "wibble", 0 } },
597 { " wibble", { "wibble", 0 } },
598 { " wibble ", { "wibble", 0 } },
599 { "wibble ", { "wibble", 0 } },
600 { "wibble spong", { "wibble", "spong", 0 } },
601 { " wibble spong", { "wibble", "spong", 0 } },
602 { " wibble spong ", { "wibble", "spong", 0 } },
603 { "wibble spong ", { "wibble", "spong", 0 } },
604 { "wibble spong splat foo zot ", { "wibble", "spong", "splat", "foo", "zot", 0 } },
606 { "wibble 'spong", { "wibble", "spong", 0 } },
607 { " wibble's", { "wibble's", 0 } },
608 { " wibblespong' ", { "wibblespong", 0 } },
609 { "wibble sp''ong ", { "wibble", "sp", "ong", 0 } },
611 #define NWTEST (sizeof wtest / sizeof *wtest)
613 static void test_words(void) {
614 size_t t
, nexpect
, ngot
, i
;
617 fprintf(stderr
, "test_words\n");
618 for(t
= 0; t
< NWTEST
; ++t
) {
619 char **got
= utf8_word_split(wtest
[t
].in
, strlen(wtest
[t
].in
), &ngot
, 0);
621 for(nexpect
= 0; wtest
[t
].expect
[nexpect
]; ++nexpect
)
623 if(nexpect
== ngot
) {
624 for(i
= 0; i
< ngot
; ++i
)
625 if(strcmp(wtest
[t
].expect
[i
], got
[i
]))
631 fprintf(stderr
, "word split %zu failed\n", t
);
632 fprintf(stderr
, "input: %s\n", wtest
[t
].in
);
633 fprintf(stderr
, " | %-30s | %-30s\n",
635 for(i
= 0; i
< nexpect
|| i
< ngot
; ++i
) {
636 const char *e
= i
< nexpect ? wtest
[t
].expect
[i
] : "<none>";
637 const char *g
= i
< ngot ? got
[i
] : "<none>";
638 fprintf(stderr
, " %2zu | %-30s | %-30s\n", i
, e
, g
);
646 /** @brief Less-than comparison function for integer heap */
647 static inline int int_lt(int a
, int b
) { return a
< b
; }
650 * @brief A heap with @c int elements */
651 HEAP_TYPE(iheap
, int, int_lt
);
652 HEAP_DEFINE(iheap
, int, int_lt
);
654 /** @brief Tests for @ref heap.h */
655 static void test_heap(void) {
660 fprintf(stderr
, "test_heap\n");
663 for(n
= 0; n
< 1000; ++n
)
664 iheap_insert(h
, random() % 100);
665 for(n
= 0; n
< 1000; ++n
) {
666 const int latest
= iheap_remove(h
);
668 fprintf(stderr
, "should have %d <= %d\n", last
, latest
);
669 insist(last
<= latest
);
675 /** @brief Open a Unicode test file */
676 static FILE *open_unicode_test(const char *path
) {
682 if((base
= strrchr(path
, '/')))
686 if(!(fp
= fopen(base
, "r"))) {
687 snprintf(buffer
, sizeof buffer
,
688 "wget http://www.unicode.org/Public/5.0.0/ucd/%s", path
);
689 if((w
= system(buffer
)))
690 fatal(0, "%s: %s", buffer
, wstat(w
));
691 if(chmod(base
, 0444) < 0)
692 fatal(errno
, "chmod %s", base
);
693 if(!(fp
= fopen(base
, "r")))
694 fatal(errno
, "%s", base
);
699 /** @brief Run breaking tests for utf32_grapheme_boundary() etc */
700 static void breaktest(const char *path
,
701 int (*breakfn
)(const uint32_t *, size_t, size_t)) {
702 FILE *fp
= open_unicode_test(path
);
706 char break_allowed
[1024];
707 uint32_t buffer
[1024];
709 while(!inputline(path
, fp
, &l
, '\n')) {
711 if(l
[0] == '#') continue;
715 if(*lp
== ' ' || *lp
== '\t') {
721 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0xB7) {
722 /* 00F7 DIVISION SIGN */
723 break_allowed
[bn
] = 1;
727 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0x97) {
728 /* 00D7 MULTIPLICATION SIGN */
729 break_allowed
[bn
] = 0;
733 if(isxdigit((unsigned char)*lp
)) {
734 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
737 fatal(0, "%s:%d: evil line: %s", path
, lineno
, l
);
739 for(n
= 0; n
<= bn
; ++n
) {
740 if(breakfn(buffer
, bn
, n
) != break_allowed
[n
]) {
742 "%s:%d: offset %zu: mismatch\n"
755 /** @brief Tests for @ref lib/unicode.h */
756 static void test_unicode(void) {
760 uint32_t buffer
[1024];
761 uint32_t *c
[6], *NFD_c
[6], *NFKD_c
[6], *NFC_c
[6], *NFKC_c
[6]; /* 1-indexed */
764 fprintf(stderr
, "test_unicode\n");
765 fp
= open_unicode_test("NormalizationTest.txt");
766 while(!inputline("NormalizationTest.txt", fp
, &l
, '\n')) {
768 if(*l
== '#' || *l
== '@')
773 c
[cn
++] = &buffer
[bn
];
774 while(*lp
&& *lp
!= '#') {
783 c
[cn
++] = &buffer
[bn
];
787 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
791 for(cn
= 1; cn
<= 5; ++cn
) {
792 NFD_c
[cn
] = utf32_decompose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
793 NFKD_c
[cn
] = utf32_decompose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
794 NFC_c
[cn
] = utf32_compose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
795 NFKC_c
[cn
] = utf32_compose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
797 #define unt_check(T, A, B) do { \
799 if(utf32_cmp(c[A], T##_c[B])) { \
801 "NormalizationTest.txt:%d: c%d != "#T"(c%d)\n", \
803 fprintf(stderr, " c%d:%s\n", \
804 A, format_utf32(c[A])); \
805 fprintf(stderr, " c%d:%s\n", \
806 B, format_utf32(c[B])); \
807 fprintf(stderr, "%4s(c%d):%s\n", \
808 #T, B, format_utf32(T##_c[B])); \
812 unt_check(NFD
, 3, 1);
813 unt_check(NFD
, 3, 2);
814 unt_check(NFD
, 3, 3);
815 unt_check(NFD
, 5, 4);
816 unt_check(NFD
, 5, 5);
817 unt_check(NFKD
, 5, 1);
818 unt_check(NFKD
, 5, 2);
819 unt_check(NFKD
, 5, 3);
820 unt_check(NFKD
, 5, 4);
821 unt_check(NFKD
, 5, 5);
822 unt_check(NFC
, 2, 1);
823 unt_check(NFC
, 2, 2);
824 unt_check(NFC
, 2, 3);
825 unt_check(NFC
, 4, 4);
826 unt_check(NFC
, 4, 5);
827 unt_check(NFKC
, 4, 1);
828 unt_check(NFKC
, 4, 2);
829 unt_check(NFKC
, 4, 3);
830 unt_check(NFKC
, 4, 4);
831 unt_check(NFKC
, 4, 5);
832 for(cn
= 1; cn
<= 5; ++cn
) {
839 breaktest("auxiliary/GraphemeBreakTest.txt", utf32_is_grapheme_boundary
);
840 breaktest("auxiliary/WordBreakTest.txt", utf32_is_word_boundary
);
841 insist(utf32_combining_class(0x40000) == 0);
842 insist(utf32_combining_class(0xE0000) == 0);
845 static void test_signame(void) {
846 fprintf(stderr
, "test_signame\n");
847 insist(find_signal("SIGTERM") == SIGTERM
);
848 insist(find_signal("SIGHUP") == SIGHUP
);
849 insist(find_signal("SIGINT") == SIGINT
);
850 insist(find_signal("SIGQUIT") == SIGQUIT
);
851 insist(find_signal("SIGKILL") == SIGKILL
);
852 insist(find_signal("SIGYOURMUM") == -1);
855 static void test_cache(void) {
856 const struct cache_type t1
= { 1 }, t2
= { 10 };
857 const char v11
[] = "spong", v12
[] = "wibble", v2
[] = "blat";
858 fprintf(stderr
, "test_cache\n");
859 cache_put(&t1
, "1_1", v11
);
860 cache_put(&t1
, "1_2", v12
);
861 cache_put(&t2
, "2", v2
);
862 insist(cache_count() == 3);
863 insist(cache_get(&t2
, "2") == v2
);
864 insist(cache_get(&t1
, "1_1") == v11
);
865 insist(cache_get(&t1
, "1_2") == v12
);
866 insist(cache_get(&t1
, "2") == 0);
867 insist(cache_get(&t2
, "1_1") == 0);
868 insist(cache_get(&t2
, "1_2") == 0);
869 insist(cache_get(&t1
, "2") == 0);
870 insist(cache_get(&t2
, "1_1") == 0);
871 insist(cache_get(&t2
, "1_2") == 0);
874 insist(cache_count() == 1);
875 insist(cache_get(&t1
, "1_1") == 0);
876 insist(cache_get(&t1
, "1_2") == 0);
877 insist(cache_get(&t2
, "2") == v2
);
879 insist(cache_count() == 0);
880 insist(cache_get(&t2
, "2") == 0);
883 static void test_filepart(void) {
884 fprintf(stderr
, "test_filepart\n");
885 check_string(d_dirname("/"), "/");
886 check_string(d_dirname("/spong"), "/");
887 check_string(d_dirname("/foo/bar"), "/foo");
888 check_string(d_dirname("./bar"), ".");
889 check_string(d_dirname("."), ".");
890 check_string(d_dirname(".."), ".");
891 check_string(d_dirname("../blat"), "..");
892 check_string(d_dirname("wibble"), ".");
893 check_string(extension("foo.c"), ".c");
894 check_string(extension(".c"), ".c");
895 check_string(extension("."), ".");
896 check_string(extension("foo"), "");
897 check_string(extension("./foo"), "");
898 check_string(extension("./foo.c"), ".c");
901 static void test_selection(void) {
903 fprintf(stderr
, "test_selection\n");
904 insist((h
= selection_new()) != 0);
905 selection_set(h
, "one", 1);
906 selection_set(h
, "two", 1);
907 selection_set(h
, "three", 0);
908 selection_set(h
, "four", 1);
909 insist(selection_selected(h
, "one") == 1);
910 insist(selection_selected(h
, "two") == 1);
911 insist(selection_selected(h
, "three") == 0);
912 insist(selection_selected(h
, "four") == 1);
913 insist(selection_selected(h
, "five") == 0);
914 insist(hash_count(h
) == 3);
915 selection_flip(h
, "one");
916 selection_flip(h
, "three");
917 insist(selection_selected(h
, "one") == 0);
918 insist(selection_selected(h
, "three") == 1);
919 insist(hash_count(h
) == 3);
920 selection_live(h
, "one");
921 selection_live(h
, "two");
922 selection_live(h
, "three");
923 selection_cleanup(h
);
924 insist(selection_selected(h
, "one") == 0);
925 insist(selection_selected(h
, "two") == 1);
926 insist(selection_selected(h
, "three") == 1);
927 insist(selection_selected(h
, "four") == 0);
928 insist(selection_selected(h
, "five") == 0);
929 insist(hash_count(h
) == 2);
931 insist(selection_selected(h
, "one") == 0);
932 insist(selection_selected(h
, "two") == 0);
933 insist(selection_selected(h
, "three") == 0);
934 insist(selection_selected(h
, "four") == 0);
935 insist(selection_selected(h
, "five") == 0);
936 insist(hash_count(h
) == 0);
939 static void test_wstat(void) {
943 fprintf(stderr
, "test_wstat\n");
944 if(!(pid
= xfork())) {
947 while(waitpid(pid
, &w
, 0) < 0 && errno
== EINTR
)
949 check_string(wstat(w
), "exited with status 1");
950 if(!(pid
= xfork())) {
951 kill(getpid(), SIGTERM
);
954 while(waitpid(pid
, &w
, 0) < 0 && errno
== EINTR
)
956 check_string_prefix(wstat(w
), "terminated by signal 15");
959 static void test_kvp(void) {
963 fprintf(stderr
, "test_kvp\n");
965 #define KVP_URLDECODE(S) kvp_urldecode((S), strlen(S))
966 insist(KVP_URLDECODE("=%zz") == 0);
967 insist(KVP_URLDECODE("=%0") == 0);
968 insist(KVP_URLDECODE("=%0z") == 0);
969 insist(KVP_URLDECODE("=%%") == 0);
970 insist(KVP_URLDECODE("==%") == 0);
971 insist(KVP_URLDECODE("wibble") == 0);
972 insist(KVP_URLDECODE("") == 0);
973 insist(KVP_URLDECODE("wibble&") == 0);
974 insist((k
= KVP_URLDECODE("one=bl%61t+foo")) != 0);
975 check_string(kvp_get(k
, "one"), "blat foo");
976 insist(kvp_get(k
, "ONE") == 0);
977 insist(k
->next
== 0);
978 insist((k
= KVP_URLDECODE("wibble=splat&bar=spong")) != 0);
979 check_string(kvp_get(k
, "wibble"), "splat");
980 check_string(kvp_get(k
, "bar"), "spong");
981 insist(kvp_get(k
, "ONE") == 0);
982 insist(k
->next
->next
== 0);
984 insist(kvp_set(&k
, "bar", "spong") == 0);
985 insist(kvp_set(&k
, "bar", "foo") == 1);
986 insist(kvp_set(&k
, "zog", "%") == 1);
987 insist(kvp_set(&k
, "wibble", 0) == 1);
988 insist(kvp_set(&k
, "wibble", 0) == 0);
989 check_string(kvp_urlencode(k
, 0),
991 check_string(kvp_urlencode(k
, &n
),
993 insist(n
== strlen("bar=foo&zog=%25"));
994 check_string(urlencodestring("abc% +\n"),
998 static void test_sink(void) {
1004 fprintf(stderr
, "test_sink\n");
1008 s
= sink_stdio("tmpfile", fp
);
1009 insist(sink_printf(s
, "test: %d\n", 999) == 10);
1010 insist(sink_printf(s
, "wibble: %s\n", "foobar") == 15);
1012 insist(inputline("tmpfile", fp
, &l
, '\n') == 0);
1013 check_string(l
, "test: 999");
1014 insist(inputline("tmpfile", fp
, &l
, '\n') == 0);
1015 check_string(l
, "wibble: foobar");
1016 insist(inputline("tmpfile", fp
, &l
, '\n') == -1);
1020 insist(sink_printf(s
, "test: %d\n", 999) == 10);
1021 insist(sink_printf(s
, "wibble: %s\n", "foobar") == 15);
1022 dynstr_terminate(d
);
1023 check_string(d
->vec
, "test: 999\nwibble: foobar\n");
1026 static const char *do_printf(const char *fmt
, ...) {
1032 rc
= byte_vasprintf(&s
, fmt
, ap
);
1039 static void test_printf(void) {
1049 fprintf(stderr
, "test_printf\n");
1050 check_string(do_printf("%d", 999), "999");
1051 check_string(do_printf("%d", -999), "-999");
1052 check_string(do_printf("%i", 999), "999");
1053 check_string(do_printf("%i", -999), "-999");
1054 check_string(do_printf("%u", 999), "999");
1055 check_string(do_printf("%2u", 999), "999");
1056 check_string(do_printf("%10u", 999), " 999");
1057 check_string(do_printf("%-10u", 999), "999 ");
1058 check_string(do_printf("%010u", 999), "0000000999");
1059 check_string(do_printf("%-10d", -999), "-999 ");
1060 check_string(do_printf("%-010d", -999), "-999 "); /* "-" beats "0" */
1061 check_string(do_printf("%66u", 999), " 999");
1062 check_string(do_printf("%o", 999), "1747");
1063 check_string(do_printf("%#o", 999), "01747");
1064 check_string(do_printf("%#o", 0), "0");
1065 check_string(do_printf("%x", 999), "3e7");
1066 check_string(do_printf("%#x", 999), "0x3e7");
1067 check_string(do_printf("%#X", 999), "0X3E7");
1068 check_string(do_printf("%#x", 0), "0");
1069 check_string(do_printf("%hd", (short)999), "999");
1070 check_string(do_printf("%hhd", (short)99), "99");
1071 check_string(do_printf("%ld", 100000L), "100000");
1072 check_string(do_printf("%lld", 10000000000LL), "10000000000");
1073 check_string(do_printf("%qd", 10000000000LL), "10000000000");
1074 check_string(do_printf("%jd", (intmax_t)10000000000LL), "10000000000");
1075 check_string(do_printf("%zd", (ssize_t
)2000000000), "2000000000");
1076 check_string(do_printf("%td", (ptrdiff_t)2000000000), "2000000000");
1077 check_string(do_printf("%hu", (short)999), "999");
1078 check_string(do_printf("%hhu", (short)99), "99");
1079 check_string(do_printf("%lu", 100000L), "100000");
1080 check_string(do_printf("%llu", 10000000000LL), "10000000000");
1081 check_string(do_printf("%ju", (uintmax_t)10000000000LL), "10000000000");
1082 check_string(do_printf("%zu", (size_t)2000000000), "2000000000");
1083 check_string(do_printf("%tu", (ptrdiff_t)2000000000), "2000000000");
1084 check_string(do_printf("%p", (void *)0x100), "0x100");
1085 check_string(do_printf("%s", "wibble"), "wibble");
1086 check_string(do_printf("%s-%s", "wibble", "wobble"), "wibble-wobble");
1087 check_string(do_printf("%10s", "wibble"), " wibble");
1088 check_string(do_printf("%010s", "wibble"), " wibble"); /* 0 ignored for %s */
1089 check_string(do_printf("%-10s", "wibble"), "wibble ");
1090 check_string(do_printf("%2s", "wibble"), "wibble");
1091 check_string(do_printf("%.2s", "wibble"), "wi");
1092 check_string(do_printf("%.2s", "w"), "w");
1093 check_string(do_printf("%4.2s", "wibble"), " wi");
1094 check_string(do_printf("%c", 'a'), "a");
1095 check_string(do_printf("%4c", 'a'), " a");
1096 check_string(do_printf("%-4c", 'a'), "a ");
1097 check_string(do_printf("%*c", 0, 'a'), "a");
1098 check_string(do_printf("x%hhny", &c
), "xy");
1100 check_string(do_printf("xx%hnyy", &s
), "xxyy");
1102 check_string(do_printf("xxx%nyyy", &i
), "xxxyyy");
1104 check_string(do_printf("xxxx%lnyyyy", &l
), "xxxxyyyy");
1106 check_string(do_printf("xxxxx%llnyyyyy", &ll
), "xxxxxyyyyy");
1108 check_string(do_printf("xxxxxx%jnyyyyyy", &m
), "xxxxxxyyyyyy");
1110 check_string(do_printf("xxxxxxx%znyyyyyyy", &ssz
), "xxxxxxxyyyyyyy");
1112 check_string(do_printf("xxxxxxxx%tnyyyyyyyy", &p
), "xxxxxxxxyyyyyyyy");
1114 check_string(do_printf("%*d", 5, 99), " 99");
1115 check_string(do_printf("%*d", -5, 99), "99 ");
1116 check_string(do_printf("%.*d", 5, 99), "00099");
1117 check_string(do_printf("%.*d", -5, 99), "99");
1118 check_string(do_printf("%.0d", 0), "");
1119 check_string(do_printf("%.d", 0), "");
1120 check_string(do_printf("%.d", 0), "");
1121 check_string(do_printf("%%"), "%");
1122 check_string(do_printf("wibble"), "wibble");
1123 insist(do_printf("%") == 0);
1124 insist(do_printf("%=") == 0);
1127 static void test_basen(void) {
1128 unsigned long v
[64];
1131 fprintf(stderr
, "test_basen\n");
1133 insist(basen(v
, 1, buffer
, sizeof buffer
, 10) == 0);
1134 check_string(buffer
, "999");
1136 v
[0] = 1+2*7+3*7*7+4*7*7*7;
1137 insist(basen(v
, 1, buffer
, sizeof buffer
, 7) == 0);
1138 check_string(buffer
, "4321");
1144 insist(basen(v
, 4, buffer
, sizeof buffer
, 256) == 0);
1145 check_string(buffer
, "123456789abcdef");
1151 insist(basen(v
, 4, buffer
, sizeof buffer
, 16) == 0);
1152 check_string(buffer
, "102030405060708090a0b0c0d0e0f");
1158 insist(basen(v
, 4, buffer
, 10, 16) == -1);
1161 static void test_split(void) {
1165 fprintf(stderr
, "test_split\n");
1166 insist(split("\"misquoted", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0) == 0);
1167 insist(split("\'misquoted", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0) == 0);
1168 insist(split("\'misquoted\\", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0) == 0);
1169 insist(split("\'misquoted\\\"", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0) == 0);
1170 insist(split("\'mis\\escaped\'", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0) == 0);
1172 insist((v
= split("", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1173 check_integer(nv
, 0);
1176 insist((v
= split("wibble", &nv
, SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1177 check_integer(nv
, 1);
1178 check_string(v
[0], "wibble");
1181 insist((v
= split(" wibble \t\r\n wobble ", &nv
,
1182 SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1183 check_integer(nv
, 2);
1184 check_string(v
[0], "wibble");
1185 check_string(v
[1], "wobble");
1188 insist((v
= split("wibble wobble #splat", &nv
,
1189 SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1190 check_integer(nv
, 2);
1191 check_string(v
[0], "wibble");
1192 check_string(v
[1], "wobble");
1195 insist((v
= split("\"wibble wobble\" #splat", &nv
,
1196 SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1197 check_integer(nv
, 1);
1198 check_string(v
[0], "wibble wobble");
1201 insist((v
= split("\"wibble \\\"\\nwobble\"", &nv
,
1202 SPLIT_COMMENTS
|SPLIT_QUOTES
, 0, 0)));
1203 check_integer(nv
, 1);
1204 check_string(v
[0], "wibble \"\nwobble");
1207 insist((v
= split("\"wibble wobble\" #splat", &nv
,
1208 SPLIT_QUOTES
, 0, 0)));
1209 check_integer(nv
, 2);
1210 check_string(v
[0], "wibble wobble");
1211 check_string(v
[1], "#splat");
1214 insist((v
= split("\"wibble wobble\" #splat", &nv
,
1215 SPLIT_COMMENTS
, 0, 0)));
1216 check_integer(nv
, 2);
1217 check_string(v
[0], "\"wibble");
1218 check_string(v
[1], "wobble\"");
1221 check_string(quoteutf8("wibble"), "wibble");
1222 check_string(quoteutf8(" wibble "), "\" wibble \"");
1223 check_string(quoteutf8("wibble wobble"), "\"wibble wobble\"");
1224 check_string(quoteutf8("wibble\"wobble"), "\"wibble\\\"wobble\"");
1225 check_string(quoteutf8("wibble\nwobble"), "\"wibble\\nwobble\"");
1226 check_string(quoteutf8("wibble\\wobble"), "\"wibble\\\\wobble\"");
1227 check_string(quoteutf8("wibble'wobble"), "\"wibble'wobble\"");
1231 fail_first
= !!getenv("FAIL_FIRST");
1232 insist('\n' == 0x0A);
1233 insist('\r' == 0x0D);
1234 insist(' ' == 0x20);
1235 insist('0' == 0x30);
1236 insist('9' == 0x39);
1237 insist('A' == 0x41);
1238 insist('Z' == 0x5A);
1239 insist('a' == 0x61);
1240 insist('z' == 0x7A);
1248 /* configuration.c */
1292 fprintf(stderr
, "%d errors out of %d tests\n", errors
, tests
);
1301 indent-tabs-mode:nil