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"
59 static int tests
, errors
;
60 static int fail_first
;
62 static void count_error() {
68 /** @brief Checks that @p expr is nonzero */
69 #define insist(expr) do { \
72 fprintf(stderr, "%s:%d: error checking %s\n", \
73 __FILE__, __LINE__, #expr); \
78 static const char *format(const char *s
) {
84 while((c
= (unsigned char)*s
++)) {
85 if(c
>= ' ' && c
<= '~')
88 sprintf(buf
, "\\x%02X", (unsigned)c
);
89 dynstr_append_string(&d
, buf
);
96 static const char *format_utf32(const uint32_t *s
) {
103 sprintf(buf
, " %04lX", (long)c
);
104 dynstr_append_string(&d
, buf
);
106 dynstr_terminate(&d
);
110 #define check_string(GOT, WANT) do { \
111 const char *got = GOT; \
112 const char *want = WANT; \
115 fprintf(stderr, "%s:%d: %s returned 0\n", \
116 __FILE__, __LINE__, #GOT); \
118 } else if(strcmp(want, got)) { \
119 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \
120 __FILE__, __LINE__, #GOT, format(got), format(want)); \
126 #define check_string_prefix(GOT, WANT) do { \
127 const char *got = GOT; \
128 const char *want = WANT; \
131 fprintf(stderr, "%s:%d: %s returned 0\n", \
132 __FILE__, __LINE__, #GOT); \
134 } else if(strncmp(want, got, strlen(want))) { \
135 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s...\n", \
136 __FILE__, __LINE__, #GOT, format(got), format(want)); \
142 #define check_integer(GOT, WANT) do { \
143 const intmax_t got = GOT, want = WANT; \
145 fprintf(stderr, "%s:%d: %s returned: %jd expected: %jd\n", \
146 __FILE__, __LINE__, #GOT, got, want); \
152 static uint32_t *ucs4parse(const char *s
) {
153 struct dynstr_ucs4 d
;
156 dynstr_ucs4_init(&d
);
159 dynstr_ucs4_append(&d
, strtoul(s
, &e
, 0));
160 if(errno
) fatal(errno
, "strtoul (%s)", s
);
163 dynstr_ucs4_terminate(&d
);
167 static void test_utf8(void) {
168 /* Test validutf8, convert to UCS-4, check the answer is right,
169 * convert back to UTF-8, check we got to where we started */
170 #define U8(CHARS, WORDS) do { \
171 uint32_t *w = ucs4parse(WORDS); \
175 insist(validutf8(CHARS)); \
176 ucs = utf8_to_utf32(CHARS, strlen(CHARS), 0); \
178 insist(!utf32_cmp(w, ucs)); \
179 u8 = utf32_to_utf8(ucs, utf32_len(ucs), 0); \
181 check_string(u8, CHARS); \
184 fprintf(stderr
, "test_utf8\n");
185 #define validutf8(S) utf8_valid((S), strlen(S))
191 /* ASCII characters */
193 U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~",
194 "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d "
195 "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a "
196 "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 "
197 "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 "
198 "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 "
199 "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e "
200 "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b "
202 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",
203 "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 "
204 "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d "
209 /* UTF8-2 = %xC2-DF UTF8-tail */
210 insist(!validutf8("\xC0\x80"));
211 insist(!validutf8("\xC1\x80"));
212 insist(!validutf8("\xC2\x7F"));
213 U8("\xC2\x80", "0x80");
214 U8("\xDF\xBF", "0x7FF");
215 insist(!validutf8("\xDF\xC0"));
217 /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
218 * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
220 insist(!validutf8("\xE0\x9F\x80"));
221 U8("\xE0\xA0\x80", "0x800");
222 U8("\xE0\xBF\xBF", "0xFFF");
223 insist(!validutf8("\xE0\xC0\xBF"));
225 insist(!validutf8("\xE1\x80\x7F"));
226 U8("\xE1\x80\x80", "0x1000");
227 U8("\xEC\xBF\xBF", "0xCFFF");
228 insist(!validutf8("\xEC\xC0\xBF"));
230 U8("\xED\x80\x80", "0xD000");
231 U8("\xED\x9F\xBF", "0xD7FF");
232 insist(!validutf8("\xED\xA0\xBF"));
234 insist(!validutf8("\xEE\x7f\x80"));
235 U8("\xEE\x80\x80", "0xE000");
236 U8("\xEF\xBF\xBF", "0xFFFF");
237 insist(!validutf8("\xEF\xC0\xBF"));
239 /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
240 * %xF4 %x80-8F 2( UTF8-tail )
242 insist(!validutf8("\xF0\x8F\x80\x80"));
243 U8("\xF0\x90\x80\x80", "0x10000");
244 U8("\xF0\xBF\xBF\xBF", "0x3FFFF");
245 insist(!validutf8("\xF0\xC0\x80\x80"));
247 insist(!validutf8("\xF1\x80\x80\x7F"));
248 U8("\xF1\x80\x80\x80", "0x40000");
249 U8("\xF3\xBF\xBF\xBF", "0xFFFFF");
250 insist(!validutf8("\xF3\xC0\x80\x80"));
252 insist(!validutf8("\xF4\x80\x80\x7F"));
253 U8("\xF4\x80\x80\x80", "0x100000");
254 U8("\xF4\x8F\xBF\xBF", "0x10FFFF");
255 insist(!validutf8("\xF4\x90\x80\x80"));
256 insist(!validutf8("\xF4\x80\xFF\x80"));
258 /* miscellaneous non-UTF-8 rubbish */
259 insist(!validutf8("\x80"));
260 insist(!validutf8("\xBF"));
261 insist(!validutf8("\xC0"));
262 insist(!validutf8("\xC0\x7F"));
263 insist(!validutf8("\xC0\xC0"));
264 insist(!validutf8("\xE0"));
265 insist(!validutf8("\xE0\x7F"));
266 insist(!validutf8("\xE0\xC0"));
267 insist(!validutf8("\xE0\x80"));
268 insist(!validutf8("\xE0\x80\x7f"));
269 insist(!validutf8("\xE0\x80\xC0"));
270 insist(!validutf8("\xF0"));
271 insist(!validutf8("\xF0\x7F"));
272 insist(!validutf8("\xF0\xC0"));
273 insist(!validutf8("\xF0\x80"));
274 insist(!validutf8("\xF0\x80\x7f"));
275 insist(!validutf8("\xF0\x80\xC0"));
276 insist(!validutf8("\xF0\x80\x80\x7f"));
277 insist(!validutf8("\xF0\x80\x80\xC0"));
278 insist(!validutf8("\xF5\x80\x80\x80"));
279 insist(!validutf8("\xF8"));
282 static int test_multipart_callback(const char *s
, void *u
) {
283 struct vector
*parts
= u
;
285 vector_append(parts
, (char *)s
);
289 static void test_mime(void) {
291 struct vector parts
[1];
293 fprintf(stderr
, "test_mime\n");
296 insist(!mime_content_type("text/plain", &t
, &n
, &v
));
297 check_string(t
, "text/plain");
301 insist(mime_content_type("TEXT ((broken) comment", &t
, &n
, &v
) < 0);
302 insist(mime_content_type("TEXT ((broken) comment\\", &t
, &n
, &v
) < 0);
305 insist(!mime_content_type("TEXT ((nested)\\ comment) /plain", &t
, &n
, &v
));
306 check_string(t
, "text/plain");
311 insist(!mime_content_type(" text/plain ; Charset=\"utf-\\8\"", &t
, &n
, &v
));
312 check_string(t
, "text/plain");
313 check_string(n
, "charset");
314 check_string(v
, "utf-8");
317 insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t
, &n
, &v
));
318 check_string(t
, "text/plain");
319 check_string(n
, "charset");
320 check_string(v
, "ISO-8859-1");
323 insist(!mime_rfc2388_content_disposition("form-data; name=\"field1\"", &t
, &n
, &v
));
324 check_string(t
, "form-data");
325 check_string(n
, "name");
326 check_string(v
, "field1");
328 insist(!mime_rfc2388_content_disposition("inline", &t
, &n
, &v
));
329 check_string(t
, "inline");
333 /* Current versions of the code only understand a single arg to these
334 * headers. This is a bug at the level they work at but suffices for
335 * DisOrder's current purposes. */
337 insist(!mime_rfc2388_content_disposition(
338 "attachment; filename=genome.jpeg;\n"
339 "modification-date=\"Wed, 12 Feb 1997 16:29:51 -0500\"",
341 check_string(t
, "attachment");
342 check_string(n
, "filename");
343 check_string(v
, "genome.jpeg");
346 insist(mime_multipart("--outer\r\n"
347 "Content-Type: text/plain\r\n"
348 "Content-Disposition: inline\r\n"
349 "Content-Description: text-part-1\r\n"
351 "Some text goes here\r\n"
354 "Content-Type: multipart/mixed; boundary=inner\r\n"
355 "Content-Disposition: attachment\r\n"
356 "Content-Description: multipart-2\r\n"
359 "Content-Type: text/plain\r\n"
360 "Content-Disposition: inline\r\n"
361 "Content-Description: text-part-2\r\n"
363 "Some more text here.\r\n"
366 "Content-Type: image/jpeg\r\n"
367 "Content-Disposition: attachment\r\n"
368 "Content-Description: jpeg-1\r\n"
373 test_multipart_callback
,
376 check_integer(parts
->nvec
, 2);
377 check_string(parts
->vec
[0],
378 "Content-Type: text/plain\r\n"
379 "Content-Disposition: inline\r\n"
380 "Content-Description: text-part-1\r\n"
382 "Some text goes here\r\n");
383 check_string(parts
->vec
[1],
384 "Content-Type: multipart/mixed; boundary=inner\r\n"
385 "Content-Disposition: attachment\r\n"
386 "Content-Description: multipart-2\r\n"
389 "Content-Type: text/plain\r\n"
390 "Content-Disposition: inline\r\n"
391 "Content-Description: text-part-2\r\n"
393 "Some more text here.\r\n"
396 "Content-Type: image/jpeg\r\n"
397 "Content-Disposition: attachment\r\n"
398 "Content-Description: jpeg-1\r\n"
402 /* No trailing CRLF is _correct_ - see RFC2046 5.1.1 note regarding CRLF
403 * preceding the boundary delimiter line. An implication of this is that we
404 * must cope with partial lines at the end of the input when recursively
405 * decomposing a multipart message. */
407 insist(mime_multipart("--inner\r\n"
408 "Content-Type: text/plain\r\n"
409 "Content-Disposition: inline\r\n"
410 "Content-Description: text-part-2\r\n"
412 "Some more text here.\r\n"
415 "Content-Type: image/jpeg\r\n"
416 "Content-Disposition: attachment\r\n"
417 "Content-Description: jpeg-1\r\n"
421 test_multipart_callback
,
424 check_integer(parts
->nvec
, 2);
425 check_string(parts
->vec
[0],
426 "Content-Type: text/plain\r\n"
427 "Content-Disposition: inline\r\n"
428 "Content-Description: text-part-2\r\n"
430 "Some more text here.\r\n");
431 check_string(parts
->vec
[1],
432 "Content-Type: image/jpeg\r\n"
433 "Content-Disposition: attachment\r\n"
434 "Content-Description: jpeg-1\r\n"
440 check_string(mime_qp(""), "");
441 check_string(mime_qp("foobar"), "foobar");
442 check_string(mime_qp("foo=20bar"), "foo bar");
443 check_string(mime_qp("x \r\ny"), "x\r\ny");
444 check_string(mime_qp("x=\r\ny"), "xy");
445 check_string(mime_qp("x= \r\ny"), "xy");
446 check_string(mime_qp("x =\r\ny"), "x y");
447 check_string(mime_qp("x = \r\ny"), "x y");
450 check_string(mime_qp("Now's the time =\r\n"
451 "for all folk to come=\r\n"
452 " to the aid of their country."),
453 "Now's the time for all folk to come to the aid of their country.");
455 check_string(mime_base64(""), "");
456 check_string(mime_base64("BBBB"), "\x04\x10\x41");
457 check_string(mime_base64("////"), "\xFF\xFF\xFF");
458 check_string(mime_base64("//BB"), "\xFF\xF0\x41");
459 check_string(mime_base64("BBBB//BB////"),
460 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
461 check_string(mime_base64("B B B B / / B B / / / /"),
462 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
463 check_string(mime_base64("B\r\nBBB.// B-B//~//"),
464 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
465 check_string(mime_base64("BBBB="),
467 check_string(mime_base64("BBBBx="), /* not actually valid base64 */
469 check_string(mime_base64("BBBB BB=="),
470 "\x04\x10\x41" "\x04");
471 check_string(mime_base64("BBBB BBB="),
472 "\x04\x10\x41" "\x04\x10");
475 static void test_hex(void) {
477 static const unsigned char h
[] = { 0x00, 0xFF, 0x80, 0x7F };
481 fprintf(stderr
, "test_hex\n");
483 for(n
= 0; n
<= UCHAR_MAX
; ++n
) {
485 insist(unhexdigitq(n
) == -1);
487 insist(unhexdigitq('0') == 0);
488 insist(unhexdigitq('1') == 1);
489 insist(unhexdigitq('2') == 2);
490 insist(unhexdigitq('3') == 3);
491 insist(unhexdigitq('4') == 4);
492 insist(unhexdigitq('5') == 5);
493 insist(unhexdigitq('6') == 6);
494 insist(unhexdigitq('7') == 7);
495 insist(unhexdigitq('8') == 8);
496 insist(unhexdigitq('9') == 9);
497 insist(unhexdigitq('a') == 10);
498 insist(unhexdigitq('b') == 11);
499 insist(unhexdigitq('c') == 12);
500 insist(unhexdigitq('d') == 13);
501 insist(unhexdigitq('e') == 14);
502 insist(unhexdigitq('f') == 15);
503 insist(unhexdigitq('A') == 10);
504 insist(unhexdigitq('B') == 11);
505 insist(unhexdigitq('C') == 12);
506 insist(unhexdigitq('D') == 13);
507 insist(unhexdigitq('E') == 14);
508 insist(unhexdigitq('F') == 15);
509 check_string(hex(h
, sizeof h
), "00ff807f");
510 check_string(hex(0, 0), "");
511 u
= unhex("00ff807f", &ul
);
513 insist(memcmp(u
, h
, 4) == 0);
514 u
= unhex("00FF807F", &ul
);
516 insist(memcmp(u
, h
, 4) == 0);
519 fprintf(stderr
, "2 ERROR reports expected {\n");
520 insist(unhex("F", 0) == 0);
521 insist(unhex("az", 0) == 0);
522 fprintf(stderr
, "}\n");
525 static void test_casefold(void) {
527 const char *input
, *canon_folded
, *compat_folded
, *canon_expected
, *compat_expected
;
529 fprintf(stderr
, "test_casefold\n");
531 /* This isn't a very exhaustive test. Unlike for normalization, there don't
532 * seem to be any public test vectors for these algorithms. */
534 for(c
= 1; c
< 256; ++c
) {
535 input
= utf32_to_utf8(&c
, 1, 0);
536 canon_folded
= utf8_casefold_canon(input
, strlen(input
), 0);
537 compat_folded
= utf8_casefold_compat(input
, strlen(input
), 0);
540 if((c
>= 'A' && c
<= 'Z')
541 || (c
>= 0xC0 && c
<= 0xDE && c
!= 0xD7))
546 case 0xB5: /* MICRO SIGN */
547 l
= 0x3BC; /* GREEK SMALL LETTER MU */
549 case 0xDF: /* LATIN SMALL LETTER SHARP S */
550 check_string(canon_folded
, "ss");
551 check_string(compat_folded
, "ss");
557 /* Case-folded data is now normalized */
558 d
= utf32_decompose_canon(&l
, 1, 0);
559 canon_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
560 if(strcmp(canon_folded
, canon_expected
)) {
561 fprintf(stderr
, "%s:%d: canon-casefolding %#lx got '%s', expected '%s'\n",
562 __FILE__
, __LINE__
, (unsigned long)c
,
563 format(canon_folded
), format(canon_expected
));
567 d
= utf32_decompose_compat(&l
, 1, 0);
568 compat_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
569 if(strcmp(compat_folded
, compat_expected
)) {
570 fprintf(stderr
, "%s:%d: compat-casefolding %#lx got '%s', expected '%s'\n",
571 __FILE__
, __LINE__
, (unsigned long)c
,
572 format(compat_folded
), format(compat_expected
));
578 check_string(utf8_casefold_canon("", 0, 0), "");
583 const char *expect
[10];
587 /* Only whitespace and punctuation */
594 { "wibble", { "wibble", 0 } },
595 { " wibble", { "wibble", 0 } },
596 { " wibble ", { "wibble", 0 } },
597 { "wibble ", { "wibble", 0 } },
598 { "wibble spong", { "wibble", "spong", 0 } },
599 { " wibble spong", { "wibble", "spong", 0 } },
600 { " wibble spong ", { "wibble", "spong", 0 } },
601 { "wibble spong ", { "wibble", "spong", 0 } },
602 { "wibble spong splat foo zot ", { "wibble", "spong", "splat", "foo", "zot", 0 } },
604 { "wibble 'spong", { "wibble", "spong", 0 } },
605 { " wibble's", { "wibble's", 0 } },
606 { " wibblespong' ", { "wibblespong", 0 } },
607 { "wibble sp''ong ", { "wibble", "sp", "ong", 0 } },
609 #define NWTEST (sizeof wtest / sizeof *wtest)
611 static void test_words(void) {
612 size_t t
, nexpect
, ngot
, i
;
615 fprintf(stderr
, "test_words\n");
616 for(t
= 0; t
< NWTEST
; ++t
) {
617 char **got
= utf8_word_split(wtest
[t
].in
, strlen(wtest
[t
].in
), &ngot
, 0);
619 for(nexpect
= 0; wtest
[t
].expect
[nexpect
]; ++nexpect
)
621 if(nexpect
== ngot
) {
622 for(i
= 0; i
< ngot
; ++i
)
623 if(strcmp(wtest
[t
].expect
[i
], got
[i
]))
629 fprintf(stderr
, "word split %zu failed\n", t
);
630 fprintf(stderr
, "input: %s\n", wtest
[t
].in
);
631 fprintf(stderr
, " | %-30s | %-30s\n",
633 for(i
= 0; i
< nexpect
|| i
< ngot
; ++i
) {
634 const char *e
= i
< nexpect ? wtest
[t
].expect
[i
] : "<none>";
635 const char *g
= i
< ngot ? got
[i
] : "<none>";
636 fprintf(stderr
, " %2zu | %-30s | %-30s\n", i
, e
, g
);
644 /** @brief Less-than comparison function for integer heap */
645 static inline int int_lt(int a
, int b
) { return a
< b
; }
648 * @brief A heap with @c int elements */
649 HEAP_TYPE(iheap
, int, int_lt
);
650 HEAP_DEFINE(iheap
, int, int_lt
);
652 /** @brief Tests for @ref heap.h */
653 static void test_heap(void) {
658 fprintf(stderr
, "test_heap\n");
661 for(n
= 0; n
< 1000; ++n
)
662 iheap_insert(h
, random() % 100);
663 for(n
= 0; n
< 1000; ++n
) {
664 const int latest
= iheap_remove(h
);
666 fprintf(stderr
, "should have %d <= %d\n", last
, latest
);
667 insist(last
<= latest
);
673 /** @brief Open a Unicode test file */
674 static FILE *open_unicode_test(const char *path
) {
680 if((base
= strrchr(path
, '/')))
684 if(!(fp
= fopen(base
, "r"))) {
685 snprintf(buffer
, sizeof buffer
,
686 "wget http://www.unicode.org/Public/5.0.0/ucd/%s", path
);
687 if((w
= system(buffer
)))
688 fatal(0, "%s: %s", buffer
, wstat(w
));
689 if(chmod(base
, 0444) < 0)
690 fatal(errno
, "chmod %s", base
);
691 if(!(fp
= fopen(base
, "r")))
692 fatal(errno
, "%s", base
);
697 /** @brief Run breaking tests for utf32_grapheme_boundary() etc */
698 static void breaktest(const char *path
,
699 int (*breakfn
)(const uint32_t *, size_t, size_t)) {
700 FILE *fp
= open_unicode_test(path
);
704 char break_allowed
[1024];
705 uint32_t buffer
[1024];
707 while(!inputline(path
, fp
, &l
, '\n')) {
709 if(l
[0] == '#') continue;
713 if(*lp
== ' ' || *lp
== '\t') {
719 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0xB7) {
720 /* 00F7 DIVISION SIGN */
721 break_allowed
[bn
] = 1;
725 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0x97) {
726 /* 00D7 MULTIPLICATION SIGN */
727 break_allowed
[bn
] = 0;
731 if(isxdigit((unsigned char)*lp
)) {
732 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
735 fatal(0, "%s:%d: evil line: %s", path
, lineno
, l
);
737 for(n
= 0; n
<= bn
; ++n
) {
738 if(breakfn(buffer
, bn
, n
) != break_allowed
[n
]) {
740 "%s:%d: offset %zu: mismatch\n"
753 /** @brief Tests for @ref lib/unicode.h */
754 static void test_unicode(void) {
758 uint32_t buffer
[1024];
759 uint32_t *c
[6], *NFD_c
[6], *NFKD_c
[6], *NFC_c
[6], *NFKC_c
[6]; /* 1-indexed */
762 fprintf(stderr
, "test_unicode\n");
763 fp
= open_unicode_test("NormalizationTest.txt");
764 while(!inputline("NormalizationTest.txt", fp
, &l
, '\n')) {
766 if(*l
== '#' || *l
== '@')
771 c
[cn
++] = &buffer
[bn
];
772 while(*lp
&& *lp
!= '#') {
781 c
[cn
++] = &buffer
[bn
];
785 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
789 for(cn
= 1; cn
<= 5; ++cn
) {
790 NFD_c
[cn
] = utf32_decompose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
791 NFKD_c
[cn
] = utf32_decompose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
792 NFC_c
[cn
] = utf32_compose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
793 NFKC_c
[cn
] = utf32_compose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
795 #define unt_check(T, A, B) do { \
797 if(utf32_cmp(c[A], T##_c[B])) { \
799 "NormalizationTest.txt:%d: c%d != "#T"(c%d)\n", \
801 fprintf(stderr, " c%d:%s\n", \
802 A, format_utf32(c[A])); \
803 fprintf(stderr, " c%d:%s\n", \
804 B, format_utf32(c[B])); \
805 fprintf(stderr, "%4s(c%d):%s\n", \
806 #T, B, format_utf32(T##_c[B])); \
810 unt_check(NFD
, 3, 1);
811 unt_check(NFD
, 3, 2);
812 unt_check(NFD
, 3, 3);
813 unt_check(NFD
, 5, 4);
814 unt_check(NFD
, 5, 5);
815 unt_check(NFKD
, 5, 1);
816 unt_check(NFKD
, 5, 2);
817 unt_check(NFKD
, 5, 3);
818 unt_check(NFKD
, 5, 4);
819 unt_check(NFKD
, 5, 5);
820 unt_check(NFC
, 2, 1);
821 unt_check(NFC
, 2, 2);
822 unt_check(NFC
, 2, 3);
823 unt_check(NFC
, 4, 4);
824 unt_check(NFC
, 4, 5);
825 unt_check(NFKC
, 4, 1);
826 unt_check(NFKC
, 4, 2);
827 unt_check(NFKC
, 4, 3);
828 unt_check(NFKC
, 4, 4);
829 unt_check(NFKC
, 4, 5);
830 for(cn
= 1; cn
<= 5; ++cn
) {
837 breaktest("auxiliary/GraphemeBreakTest.txt", utf32_is_grapheme_boundary
);
838 breaktest("auxiliary/WordBreakTest.txt", utf32_is_word_boundary
);
839 insist(utf32_combining_class(0x40000) == 0);
840 insist(utf32_combining_class(0xE0000) == 0);
843 static void test_signame(void) {
844 fprintf(stderr
, "test_signame\n");
845 insist(find_signal("SIGTERM") == SIGTERM
);
846 insist(find_signal("SIGHUP") == SIGHUP
);
847 insist(find_signal("SIGINT") == SIGINT
);
848 insist(find_signal("SIGQUIT") == SIGQUIT
);
849 insist(find_signal("SIGKILL") == SIGKILL
);
850 insist(find_signal("SIGYOURMUM") == -1);
853 static void test_cache(void) {
854 const struct cache_type t1
= { 1 }, t2
= { 10 };
855 const char v11
[] = "spong", v12
[] = "wibble", v2
[] = "blat";
856 fprintf(stderr
, "test_cache\n");
857 cache_put(&t1
, "1_1", v11
);
858 cache_put(&t1
, "1_2", v12
);
859 cache_put(&t2
, "2", v2
);
860 insist(cache_count() == 3);
861 insist(cache_get(&t2
, "2") == v2
);
862 insist(cache_get(&t1
, "1_1") == v11
);
863 insist(cache_get(&t1
, "1_2") == v12
);
864 insist(cache_get(&t1
, "2") == 0);
865 insist(cache_get(&t2
, "1_1") == 0);
866 insist(cache_get(&t2
, "1_2") == 0);
867 insist(cache_get(&t1
, "2") == 0);
868 insist(cache_get(&t2
, "1_1") == 0);
869 insist(cache_get(&t2
, "1_2") == 0);
872 insist(cache_count() == 1);
873 insist(cache_get(&t1
, "1_1") == 0);
874 insist(cache_get(&t1
, "1_2") == 0);
875 insist(cache_get(&t2
, "2") == v2
);
877 insist(cache_count() == 0);
878 insist(cache_get(&t2
, "2") == 0);
881 static void test_filepart(void) {
882 fprintf(stderr
, "test_filepart\n");
883 check_string(d_dirname("/"), "/");
884 check_string(d_dirname("/spong"), "/");
885 check_string(d_dirname("/foo/bar"), "/foo");
886 check_string(d_dirname("./bar"), ".");
887 check_string(d_dirname("."), ".");
888 check_string(d_dirname(".."), ".");
889 check_string(d_dirname("../blat"), "..");
890 check_string(d_dirname("wibble"), ".");
891 check_string(extension("foo.c"), ".c");
892 check_string(extension(".c"), ".c");
893 check_string(extension("."), ".");
894 check_string(extension("foo"), "");
895 check_string(extension("./foo"), "");
896 check_string(extension("./foo.c"), ".c");
899 static void test_selection(void) {
901 fprintf(stderr
, "test_selection\n");
902 insist((h
= selection_new()) != 0);
903 selection_set(h
, "one", 1);
904 selection_set(h
, "two", 1);
905 selection_set(h
, "three", 0);
906 selection_set(h
, "four", 1);
907 insist(selection_selected(h
, "one") == 1);
908 insist(selection_selected(h
, "two") == 1);
909 insist(selection_selected(h
, "three") == 0);
910 insist(selection_selected(h
, "four") == 1);
911 insist(selection_selected(h
, "five") == 0);
912 insist(hash_count(h
) == 3);
913 selection_flip(h
, "one");
914 selection_flip(h
, "three");
915 insist(selection_selected(h
, "one") == 0);
916 insist(selection_selected(h
, "three") == 1);
917 insist(hash_count(h
) == 3);
918 selection_live(h
, "one");
919 selection_live(h
, "two");
920 selection_live(h
, "three");
921 selection_cleanup(h
);
922 insist(selection_selected(h
, "one") == 0);
923 insist(selection_selected(h
, "two") == 1);
924 insist(selection_selected(h
, "three") == 1);
925 insist(selection_selected(h
, "four") == 0);
926 insist(selection_selected(h
, "five") == 0);
927 insist(hash_count(h
) == 2);
929 insist(selection_selected(h
, "one") == 0);
930 insist(selection_selected(h
, "two") == 0);
931 insist(selection_selected(h
, "three") == 0);
932 insist(selection_selected(h
, "four") == 0);
933 insist(selection_selected(h
, "five") == 0);
934 insist(hash_count(h
) == 0);
937 static void test_wstat(void) {
941 fprintf(stderr
, "test_wstat\n");
942 if(!(pid
= xfork())) {
945 while(waitpid(pid
, &w
, 0) < 0 && errno
== EINTR
)
947 check_string(wstat(w
), "exited with status 1");
948 if(!(pid
= xfork())) {
949 kill(getpid(), SIGTERM
);
952 while(waitpid(pid
, &w
, 0) < 0 && errno
== EINTR
)
954 check_string_prefix(wstat(w
), "terminated by signal 15");
957 static void test_kvp(void) {
961 fprintf(stderr
, "test_kvp\n");
963 #define KVP_URLDECODE(S) kvp_urldecode((S), strlen(S))
964 insist(KVP_URLDECODE("=%zz") == 0);
965 insist(KVP_URLDECODE("=%0") == 0);
966 insist(KVP_URLDECODE("=%0z") == 0);
967 insist(KVP_URLDECODE("=%%") == 0);
968 insist(KVP_URLDECODE("==%") == 0);
969 insist(KVP_URLDECODE("wibble") == 0);
970 insist(KVP_URLDECODE("") == 0);
971 insist(KVP_URLDECODE("wibble&") == 0);
972 insist((k
= KVP_URLDECODE("one=bl%61t+foo")) != 0);
973 check_string(kvp_get(k
, "one"), "blat foo");
974 insist(kvp_get(k
, "ONE") == 0);
975 insist(k
->next
== 0);
976 insist((k
= KVP_URLDECODE("wibble=splat&bar=spong")) != 0);
977 check_string(kvp_get(k
, "wibble"), "splat");
978 check_string(kvp_get(k
, "bar"), "spong");
979 insist(kvp_get(k
, "ONE") == 0);
980 insist(k
->next
->next
== 0);
982 insist(kvp_set(&k
, "bar", "spong") == 0);
983 insist(kvp_set(&k
, "bar", "foo") == 1);
984 insist(kvp_set(&k
, "zog", "%") == 1);
985 insist(kvp_set(&k
, "wibble", 0) == 1);
986 insist(kvp_set(&k
, "wibble", 0) == 0);
987 check_string(kvp_urlencode(k
, 0),
989 check_string(kvp_urlencode(k
, &n
),
991 insist(n
== strlen("bar=foo&zog=%25"));
992 check_string(urlencodestring("abc% +\n"),
996 static void test_sink(void) {
1002 fprintf(stderr
, "test_sink\n");
1006 s
= sink_stdio("tmpfile", fp
);
1007 insist(sink_printf(s
, "test: %d\n", 999) == 10);
1008 insist(sink_printf(s
, "wibble: %s\n", "foobar") == 15);
1010 insist(inputline("tmpfile", fp
, &l
, '\n') == 0);
1011 check_string(l
, "test: 999");
1012 insist(inputline("tmpfile", fp
, &l
, '\n') == 0);
1013 check_string(l
, "wibble: foobar");
1014 insist(inputline("tmpfile", fp
, &l
, '\n') == -1);
1018 insist(sink_printf(s
, "test: %d\n", 999) == 10);
1019 insist(sink_printf(s
, "wibble: %s\n", "foobar") == 15);
1020 dynstr_terminate(d
);
1021 check_string(d
->vec
, "test: 999\nwibble: foobar\n");
1024 static const char *do_printf(const char *fmt
, ...) {
1030 rc
= byte_vasprintf(&s
, fmt
, ap
);
1037 static void test_printf(void) {
1047 fprintf(stderr
, "test_printf\n");
1048 check_string(do_printf("%d", 999), "999");
1049 check_string(do_printf("%d", -999), "-999");
1050 check_string(do_printf("%i", 999), "999");
1051 check_string(do_printf("%i", -999), "-999");
1052 check_string(do_printf("%u", 999), "999");
1053 check_string(do_printf("%2u", 999), "999");
1054 check_string(do_printf("%10u", 999), " 999");
1055 check_string(do_printf("%-10u", 999), "999 ");
1056 check_string(do_printf("%010u", 999), "0000000999");
1057 check_string(do_printf("%-10d", -999), "-999 ");
1058 check_string(do_printf("%-010d", -999), "-999 "); /* "-" beats "0" */
1059 check_string(do_printf("%66u", 999), " 999");
1060 check_string(do_printf("%o", 999), "1747");
1061 check_string(do_printf("%#o", 999), "01747");
1062 check_string(do_printf("%#o", 0), "0");
1063 check_string(do_printf("%x", 999), "3e7");
1064 check_string(do_printf("%#x", 999), "0x3e7");
1065 check_string(do_printf("%#X", 999), "0X3E7");
1066 check_string(do_printf("%#x", 0), "0");
1067 check_string(do_printf("%hd", (short)999), "999");
1068 check_string(do_printf("%hhd", (short)99), "99");
1069 check_string(do_printf("%ld", 100000L), "100000");
1070 check_string(do_printf("%lld", 10000000000LL), "10000000000");
1071 check_string(do_printf("%qd", 10000000000LL), "10000000000");
1072 check_string(do_printf("%jd", (intmax_t)10000000000LL), "10000000000");
1073 check_string(do_printf("%zd", (ssize_t
)2000000000), "2000000000");
1074 check_string(do_printf("%td", (ptrdiff_t)2000000000), "2000000000");
1075 check_string(do_printf("%hu", (short)999), "999");
1076 check_string(do_printf("%hhu", (short)99), "99");
1077 check_string(do_printf("%lu", 100000L), "100000");
1078 check_string(do_printf("%llu", 10000000000LL), "10000000000");
1079 check_string(do_printf("%ju", (uintmax_t)10000000000LL), "10000000000");
1080 check_string(do_printf("%zu", (size_t)2000000000), "2000000000");
1081 check_string(do_printf("%tu", (ptrdiff_t)2000000000), "2000000000");
1082 check_string(do_printf("%p", (void *)0x100), "0x100");
1083 check_string(do_printf("%s", "wibble"), "wibble");
1084 check_string(do_printf("%s-%s", "wibble", "wobble"), "wibble-wobble");
1085 check_string(do_printf("%10s", "wibble"), " wibble");
1086 check_string(do_printf("%010s", "wibble"), " wibble"); /* 0 ignored for %s */
1087 check_string(do_printf("%-10s", "wibble"), "wibble ");
1088 check_string(do_printf("%2s", "wibble"), "wibble");
1089 check_string(do_printf("%.2s", "wibble"), "wi");
1090 check_string(do_printf("%.2s", "w"), "w");
1091 check_string(do_printf("%4.2s", "wibble"), " wi");
1092 check_string(do_printf("%c", 'a'), "a");
1093 check_string(do_printf("%4c", 'a'), " a");
1094 check_string(do_printf("%-4c", 'a'), "a ");
1095 check_string(do_printf("%*c", 0, 'a'), "a");
1096 check_string(do_printf("x%hhny", &c
), "xy");
1098 check_string(do_printf("xx%hnyy", &s
), "xxyy");
1100 check_string(do_printf("xxx%nyyy", &i
), "xxxyyy");
1102 check_string(do_printf("xxxx%lnyyyy", &l
), "xxxxyyyy");
1104 check_string(do_printf("xxxxx%llnyyyyy", &ll
), "xxxxxyyyyy");
1106 check_string(do_printf("xxxxxx%jnyyyyyy", &m
), "xxxxxxyyyyyy");
1108 check_string(do_printf("xxxxxxx%znyyyyyyy", &ssz
), "xxxxxxxyyyyyyy");
1110 check_string(do_printf("xxxxxxxx%tnyyyyyyyy", &p
), "xxxxxxxxyyyyyyyy");
1112 check_string(do_printf("%*d", 5, 99), " 99");
1113 check_string(do_printf("%*d", -5, 99), "99 ");
1114 check_string(do_printf("%.*d", 5, 99), "00099");
1115 check_string(do_printf("%.*d", -5, 99), "99");
1116 check_string(do_printf("%.0d", 0), "");
1117 check_string(do_printf("%.d", 0), "");
1118 check_string(do_printf("%.d", 0), "");
1119 check_string(do_printf("%%"), "%");
1120 check_string(do_printf("wibble"), "wibble");
1121 insist(do_printf("%") == 0);
1122 insist(do_printf("%=") == 0);
1126 fail_first
= !!getenv("FAIL_FIRST");
1127 insist('\n' == 0x0A);
1128 insist('\r' == 0x0D);
1129 insist(' ' == 0x20);
1130 insist('0' == 0x30);
1131 insist('9' == 0x39);
1132 insist('A' == 0x41);
1133 insist('Z' == 0x5A);
1134 insist('a' == 0x61);
1135 insist('z' == 0x7A);
1142 /* configuration.c */
1185 fprintf(stderr
, "%d errors out of %d tests\n", errors
, tests
);
1194 indent-tabs-mode:nil