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>
43 #include "inputline.h"
46 static int tests
, errors
;
47 static int fail_first
;
49 static void count_error() {
55 /** @brief Checks that @p expr is nonzero */
56 #define insist(expr) do { \
59 fprintf(stderr, "%s:%d: error checking %s\n", \
60 __FILE__, __LINE__, #expr); \
65 static const char *format(const char *s
) {
71 while((c
= (unsigned char)*s
++)) {
72 if(c
>= ' ' && c
<= '~')
75 sprintf(buf
, "\\x%02X", (unsigned)c
);
76 dynstr_append_string(&d
, buf
);
83 static const char *format_utf32(const uint32_t *s
) {
90 sprintf(buf
, " %04lX", (long)c
);
91 dynstr_append_string(&d
, buf
);
97 #define check_string(GOT, WANT) do { \
98 const char *g = GOT; \
99 const char *w = WANT; \
102 fprintf(stderr, "%s:%d: %s returned 0\n", \
103 __FILE__, __LINE__, #GOT); \
105 } else if(strcmp(w, g)) { \
106 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \
107 __FILE__, __LINE__, #GOT, format(g), format(w)); \
113 static uint32_t *ucs4parse(const char *s
) {
114 struct dynstr_ucs4 d
;
117 dynstr_ucs4_init(&d
);
120 dynstr_ucs4_append(&d
, strtoul(s
, &e
, 0));
121 if(errno
) fatal(errno
, "strtoul (%s)", s
);
124 dynstr_ucs4_terminate(&d
);
128 static void test_utf8(void) {
129 /* Test validutf8, convert to UCS-4, check the answer is right,
130 * convert back to UTF-8, check we got to where we started */
131 #define U8(CHARS, WORDS) do { \
132 uint32_t *w = ucs4parse(WORDS); \
136 insist(validutf8(CHARS)); \
137 ucs = utf8_to_utf32(CHARS, strlen(CHARS), 0); \
139 insist(!utf32_cmp(w, ucs)); \
140 u8 = utf32_to_utf8(ucs, utf32_len(ucs), 0); \
142 insist(!strcmp(u8, CHARS)); \
145 fprintf(stderr
, "test_utf8\n");
146 #define validutf8(S) utf8_valid((S), strlen(S))
152 /* ASCII characters */
154 U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~",
155 "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d "
156 "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a "
157 "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 "
158 "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 "
159 "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 "
160 "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e "
161 "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b "
163 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",
164 "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 "
165 "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d "
170 /* UTF8-2 = %xC2-DF UTF8-tail */
171 insist(!validutf8("\xC0\x80"));
172 insist(!validutf8("\xC1\x80"));
173 insist(!validutf8("\xC2\x7F"));
174 U8("\xC2\x80", "0x80");
175 U8("\xDF\xBF", "0x7FF");
176 insist(!validutf8("\xDF\xC0"));
178 /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
179 * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
181 insist(!validutf8("\xE0\x9F\x80"));
182 U8("\xE0\xA0\x80", "0x800");
183 U8("\xE0\xBF\xBF", "0xFFF");
184 insist(!validutf8("\xE0\xC0\xBF"));
186 insist(!validutf8("\xE1\x80\x7F"));
187 U8("\xE1\x80\x80", "0x1000");
188 U8("\xEC\xBF\xBF", "0xCFFF");
189 insist(!validutf8("\xEC\xC0\xBF"));
191 U8("\xED\x80\x80", "0xD000");
192 U8("\xED\x9F\xBF", "0xD7FF");
193 insist(!validutf8("\xED\xA0\xBF"));
195 insist(!validutf8("\xEE\x7f\x80"));
196 U8("\xEE\x80\x80", "0xE000");
197 U8("\xEF\xBF\xBF", "0xFFFF");
198 insist(!validutf8("\xEF\xC0\xBF"));
200 /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
201 * %xF4 %x80-8F 2( UTF8-tail )
203 insist(!validutf8("\xF0\x8F\x80\x80"));
204 U8("\xF0\x90\x80\x80", "0x10000");
205 U8("\xF0\xBF\xBF\xBF", "0x3FFFF");
206 insist(!validutf8("\xF0\xC0\x80\x80"));
208 insist(!validutf8("\xF1\x80\x80\x7F"));
209 U8("\xF1\x80\x80\x80", "0x40000");
210 U8("\xF3\xBF\xBF\xBF", "0xFFFFF");
211 insist(!validutf8("\xF3\xC0\x80\x80"));
213 insist(!validutf8("\xF4\x80\x80\x7F"));
214 U8("\xF4\x80\x80\x80", "0x100000");
215 U8("\xF4\x8F\xBF\xBF", "0x10FFFF");
216 insist(!validutf8("\xF4\x90\x80\x80"));
218 /* miscellaneous non-UTF-8 rubbish */
219 insist(!validutf8("\x80"));
220 insist(!validutf8("\xBF"));
221 insist(!validutf8("\xC0"));
222 insist(!validutf8("\xC0\x7F"));
223 insist(!validutf8("\xC0\xC0"));
224 insist(!validutf8("\xE0"));
225 insist(!validutf8("\xE0\x7F"));
226 insist(!validutf8("\xE0\xC0"));
227 insist(!validutf8("\xE0\x80"));
228 insist(!validutf8("\xE0\x80\x7f"));
229 insist(!validutf8("\xE0\x80\xC0"));
230 insist(!validutf8("\xF0"));
231 insist(!validutf8("\xF0\x7F"));
232 insist(!validutf8("\xF0\xC0"));
233 insist(!validutf8("\xF0\x80"));
234 insist(!validutf8("\xF0\x80\x7f"));
235 insist(!validutf8("\xF0\x80\xC0"));
236 insist(!validutf8("\xF0\x80\x80\x7f"));
237 insist(!validutf8("\xF0\x80\x80\xC0"));
238 insist(!validutf8("\xF5\x80\x80\x80"));
239 insist(!validutf8("\xF8"));
242 static void test_mime(void) {
245 fprintf(stderr
, "test_mime\n");
248 insist(!mime_content_type("text/plain", &t
, &n
, &v
));
249 insist(!strcmp(t
, "text/plain"));
254 insist(!mime_content_type("TEXT ((nested) comment) /plain", &t
, &n
, &v
));
255 insist(!strcmp(t
, "text/plain"));
260 insist(!mime_content_type(" text/plain ; Charset=utf-8", &t
, &n
, &v
));
261 insist(!strcmp(t
, "text/plain"));
262 insist(!strcmp(n
, "charset"));
263 insist(!strcmp(v
, "utf-8"));
266 insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t
, &n
, &v
));
267 insist(!strcmp(t
, "text/plain"));
268 insist(!strcmp(n
, "charset"));
269 insist(!strcmp(v
, "ISO-8859-1"));
272 /* XXX mime_multipart */
273 /* XXX mime_rfc2388_content_disposition */
275 check_string(mime_qp(""), "");
276 check_string(mime_qp("foobar"), "foobar");
277 check_string(mime_qp("foo=20bar"), "foo bar");
278 check_string(mime_qp("x \r\ny"), "x\r\ny");
279 check_string(mime_qp("x=\r\ny"), "xy");
280 check_string(mime_qp("x= \r\ny"), "xy");
281 check_string(mime_qp("x =\r\ny"), "x y");
282 check_string(mime_qp("x = \r\ny"), "x y");
285 check_string(mime_qp("Now's the time =\r\n"
286 "for all folk to come=\r\n"
287 " to the aid of their country."),
288 "Now's the time for all folk to come to the aid of their country.");
290 check_string(mime_base64(""), "");
291 check_string(mime_base64("BBBB"), "\x04\x10\x41");
292 check_string(mime_base64("////"), "\xFF\xFF\xFF");
293 check_string(mime_base64("//BB"), "\xFF\xF0\x41");
294 check_string(mime_base64("BBBB//BB////"),
295 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
296 check_string(mime_base64("B B B B / / B B / / / /"),
297 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
298 check_string(mime_base64("B\r\nBBB.// B-B//~//"),
299 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
300 check_string(mime_base64("BBBB="),
302 check_string(mime_base64("BBBBx="), /* not actually valid base64 */
304 check_string(mime_base64("BBBB BB=="),
305 "\x04\x10\x41" "\x04");
306 check_string(mime_base64("BBBB BBB="),
307 "\x04\x10\x41" "\x04\x10");
310 static void test_hex(void) {
312 static const unsigned char h
[] = { 0x00, 0xFF, 0x80, 0x7F };
316 fprintf(stderr
, "test_hex\n");
318 for(n
= 0; n
<= UCHAR_MAX
; ++n
) {
320 insist(unhexdigitq(n
) == -1);
322 insist(unhexdigitq('0') == 0);
323 insist(unhexdigitq('1') == 1);
324 insist(unhexdigitq('2') == 2);
325 insist(unhexdigitq('3') == 3);
326 insist(unhexdigitq('4') == 4);
327 insist(unhexdigitq('5') == 5);
328 insist(unhexdigitq('6') == 6);
329 insist(unhexdigitq('7') == 7);
330 insist(unhexdigitq('8') == 8);
331 insist(unhexdigitq('9') == 9);
332 insist(unhexdigitq('a') == 10);
333 insist(unhexdigitq('b') == 11);
334 insist(unhexdigitq('c') == 12);
335 insist(unhexdigitq('d') == 13);
336 insist(unhexdigitq('e') == 14);
337 insist(unhexdigitq('f') == 15);
338 insist(unhexdigitq('A') == 10);
339 insist(unhexdigitq('B') == 11);
340 insist(unhexdigitq('C') == 12);
341 insist(unhexdigitq('D') == 13);
342 insist(unhexdigitq('E') == 14);
343 insist(unhexdigitq('F') == 15);
344 check_string(hex(h
, sizeof h
), "00ff807f");
345 check_string(hex(0, 0), "");
346 u
= unhex("00ff807f", &ul
);
348 insist(memcmp(u
, h
, 4) == 0);
349 u
= unhex("00FF807F", &ul
);
351 insist(memcmp(u
, h
, 4) == 0);
354 fprintf(stderr
, "2 ERROR reports expected {\n");
355 insist(unhex("F", 0) == 0);
356 insist(unhex("az", 0) == 0);
357 fprintf(stderr
, "}\n");
360 static void test_casefold(void) {
362 const char *input
, *canon_folded
, *compat_folded
, *canon_expected
, *compat_expected
;
364 fprintf(stderr
, "test_casefold\n");
366 /* This isn't a very exhaustive test. Unlike for normalization, there don't
367 * seem to be any public test vectors for these algorithms. */
369 for(c
= 1; c
< 256; ++c
) {
370 input
= utf32_to_utf8(&c
, 1, 0);
371 canon_folded
= utf8_casefold_canon(input
, strlen(input
), 0);
372 compat_folded
= utf8_casefold_compat(input
, strlen(input
), 0);
375 if((c
>= 'A' && c
<= 'Z')
376 || (c
>= 0xC0 && c
<= 0xDE && c
!= 0xD7))
381 case 0xB5: /* MICRO SIGN */
382 l
= 0x3BC; /* GREEK SMALL LETTER MU */
384 case 0xDF: /* LATIN SMALL LETTER SHARP S */
385 insist(!strcmp(canon_folded
, "ss"));
386 insist(!strcmp(compat_folded
, "ss"));
392 /* Case-folded data is now normalized */
393 d
= utf32_decompose_canon(&l
, 1, 0);
394 canon_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
395 if(strcmp(canon_folded
, canon_expected
)) {
396 fprintf(stderr
, "%s:%d: canon-casefolding %#lx got '%s', expected '%s'\n",
397 __FILE__
, __LINE__
, (unsigned long)c
,
398 format(canon_folded
), format(canon_expected
));
402 d
= utf32_decompose_compat(&l
, 1, 0);
403 compat_expected
= utf32_to_utf8(d
, utf32_len(d
), 0);
404 if(strcmp(compat_folded
, compat_expected
)) {
405 fprintf(stderr
, "%s:%d: compat-casefolding %#lx got '%s', expected '%s'\n",
406 __FILE__
, __LINE__
, (unsigned long)c
,
407 format(compat_folded
), format(compat_expected
));
413 check_string(utf8_casefold_canon("", 0, 0), "");
418 const char *expect
[10];
422 /* Only whitespace and punctuation */
429 { "wibble", { "wibble", 0 } },
430 { " wibble", { "wibble", 0 } },
431 { " wibble ", { "wibble", 0 } },
432 { "wibble ", { "wibble", 0 } },
433 { "wibble spong", { "wibble", "spong", 0 } },
434 { " wibble spong", { "wibble", "spong", 0 } },
435 { " wibble spong ", { "wibble", "spong", 0 } },
436 { "wibble spong ", { "wibble", "spong", 0 } },
437 { "wibble spong splat foo zot ", { "wibble", "spong", "splat", "foo", "zot", 0 } },
439 { "wibble 'spong", { "wibble", "spong", 0 } },
440 { " wibble's", { "wibble's", 0 } },
441 { " wibblespong' ", { "wibblespong", 0 } },
442 { "wibble sp''ong ", { "wibble", "sp", "ong", 0 } },
444 #define NWTEST (sizeof wtest / sizeof *wtest)
446 static void test_words(void) {
447 size_t t
, nexpect
, ngot
, i
;
450 fprintf(stderr
, "test_words\n");
451 for(t
= 0; t
< NWTEST
; ++t
) {
452 char **got
= utf8_word_split(wtest
[t
].in
, strlen(wtest
[t
].in
), &ngot
, 0);
454 for(nexpect
= 0; wtest
[t
].expect
[nexpect
]; ++nexpect
)
456 if(nexpect
== ngot
) {
457 for(i
= 0; i
< ngot
; ++i
)
458 if(strcmp(wtest
[t
].expect
[i
], got
[i
]))
464 fprintf(stderr
, "word split %zu failed\n", t
);
465 fprintf(stderr
, "input: %s\n", wtest
[t
].in
);
466 fprintf(stderr
, " | %-30s | %-30s\n",
468 for(i
= 0; i
< nexpect
|| i
< ngot
; ++i
) {
469 const char *e
= i
< nexpect ? wtest
[t
].expect
[i
] : "<none>";
470 const char *g
= i
< ngot ? got
[i
] : "<none>";
471 fprintf(stderr
, " %2zu | %-30s | %-30s\n", i
, e
, g
);
479 /** @brief Less-than comparison function for integer heap */
480 static inline int int_lt(int a
, int b
) { return a
< b
; }
483 * @brief A heap with @c int elements */
484 HEAP_TYPE(iheap
, int, int_lt
);
485 HEAP_DEFINE(iheap
, int, int_lt
);
487 /** @brief Tests for @ref heap.h */
488 static void test_heap(void) {
493 fprintf(stderr
, "test_heap\n");
496 for(n
= 0; n
< 1000; ++n
)
497 iheap_insert(h
, random() % 100);
498 for(n
= 0; n
< 1000; ++n
) {
499 const int latest
= iheap_remove(h
);
501 fprintf(stderr
, "should have %d <= %d\n", last
, latest
);
502 insist(last
<= latest
);
508 /** @brief Open a Unicode test file */
509 static FILE *open_unicode_test(const char *path
) {
515 if((base
= strrchr(path
, '/')))
519 if(!(fp
= fopen(base
, "r"))) {
520 snprintf(buffer
, sizeof buffer
,
521 "wget http://www.unicode.org/Public/5.0.0/ucd/%s", path
);
522 if((w
= system(buffer
)))
523 fatal(0, "%s: %s", buffer
, wstat(w
));
524 if(chmod(base
, 0444) < 0)
525 fatal(errno
, "chmod %s", base
);
526 if(!(fp
= fopen(base
, "r")))
527 fatal(errno
, "%s", base
);
532 /** @brief Run breaking tests for utf32_grapheme_boundary() etc */
533 static void breaktest(const char *path
,
534 int (*breakfn
)(const uint32_t *, size_t, size_t)) {
535 FILE *fp
= open_unicode_test(path
);
539 char break_allowed
[1024];
540 uint32_t buffer
[1024];
542 while(!inputline(path
, fp
, &l
, '\n')) {
544 if(l
[0] == '#') continue;
548 if(*lp
== ' ' || *lp
== '\t') {
554 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0xB7) {
555 /* 00F7 DIVISION SIGN */
556 break_allowed
[bn
] = 1;
560 if((unsigned char)*lp
== 0xC3 && (unsigned char)lp
[1] == 0x97) {
561 /* 00D7 MULTIPLICATION SIGN */
562 break_allowed
[bn
] = 0;
566 if(isxdigit((unsigned char)*lp
)) {
567 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
570 fatal(0, "%s:%d: evil line: %s", path
, lineno
, l
);
572 for(n
= 0; n
<= bn
; ++n
) {
573 if(breakfn(buffer
, bn
, n
) != break_allowed
[n
]) {
575 "%s:%d: offset %zu: mismatch\n"
588 /** @brief Tests for @ref lib/unicode.h */
589 static void test_unicode(void) {
593 uint32_t buffer
[1024];
594 uint32_t *c
[6], *NFD_c
[6], *NFKD_c
[6], *NFC_c
[6], *NFKC_c
[6]; /* 1-indexed */
597 fprintf(stderr
, "test_unicode\n");
598 fp
= open_unicode_test("NormalizationTest.txt");
599 while(!inputline("NormalizationTest.txt", fp
, &l
, '\n')) {
601 if(*l
== '#' || *l
== '@')
606 c
[cn
++] = &buffer
[bn
];
607 while(*lp
&& *lp
!= '#') {
616 c
[cn
++] = &buffer
[bn
];
620 buffer
[bn
++] = strtoul(lp
, &lp
, 16);
624 for(cn
= 1; cn
<= 5; ++cn
) {
625 NFD_c
[cn
] = utf32_decompose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
626 NFKD_c
[cn
] = utf32_decompose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
627 NFC_c
[cn
] = utf32_compose_canon(c
[cn
], utf32_len(c
[cn
]), 0);
628 NFKC_c
[cn
] = utf32_compose_compat(c
[cn
], utf32_len(c
[cn
]), 0);
630 #define unt_check(T, A, B) do { \
632 if(utf32_cmp(c[A], T##_c[B])) { \
634 "NormalizationTest.txt:%d: c%d != "#T"(c%d)\n", \
636 fprintf(stderr, " c%d:%s\n", \
637 A, format_utf32(c[A])); \
638 fprintf(stderr, " c%d:%s\n", \
639 B, format_utf32(c[B])); \
640 fprintf(stderr, "%4s(c%d):%s\n", \
641 #T, B, format_utf32(T##_c[B])); \
645 unt_check(NFD
, 3, 1);
646 unt_check(NFD
, 3, 2);
647 unt_check(NFD
, 3, 3);
648 unt_check(NFD
, 5, 4);
649 unt_check(NFD
, 5, 5);
650 unt_check(NFKD
, 5, 1);
651 unt_check(NFKD
, 5, 2);
652 unt_check(NFKD
, 5, 3);
653 unt_check(NFKD
, 5, 4);
654 unt_check(NFKD
, 5, 5);
655 unt_check(NFC
, 2, 1);
656 unt_check(NFC
, 2, 2);
657 unt_check(NFC
, 2, 3);
658 unt_check(NFC
, 4, 4);
659 unt_check(NFC
, 4, 5);
660 unt_check(NFKC
, 4, 1);
661 unt_check(NFKC
, 4, 2);
662 unt_check(NFKC
, 4, 3);
663 unt_check(NFKC
, 4, 4);
664 unt_check(NFKC
, 4, 5);
665 for(cn
= 1; cn
<= 5; ++cn
) {
672 breaktest("auxiliary/GraphemeBreakTest.txt", utf32_is_grapheme_boundary
);
673 breaktest("auxiliary/WordBreakTest.txt", utf32_is_word_boundary
);
677 fail_first
= !!getenv("FAIL_FIRST");
678 insist('\n' == 0x0A);
679 insist('\r' == 0x0D);
693 /* configuration.c */
725 fprintf(stderr
, "%d errors out of %d tests\n", errors
, tests
);