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>
44 #include "inputline.h"
47 static int tests, errors;
49 /** @brief Checks that @p expr is nonzero */
50 #define insist(expr) do { \
53 fprintf(stderr, "%s:%d: error checking %s\n", \
54 __FILE__, __LINE__, #expr); \
59 static const char *format(const char *s) {
65 while((c = (unsigned char)*s++)) {
66 if(c >= ' ' && c <= '~')
69 sprintf(buf, "\\x%02X", (unsigned)c);
70 dynstr_append_string(&d, buf);
77 static const char *format_utf32(const uint32_t *s) {
84 if(c >= 32 && c <= 127)
87 sprintf(buf, "\\x%04lX", (unsigned long)c);
88 dynstr_append_string(&d, buf);
95 #define check_string(GOT, WANT) do { \
96 const char *g = GOT; \
97 const char *w = WANT; \
100 fprintf(stderr, "%s:%d: %s returned 0\n", \
101 __FILE__, __LINE__, #GOT); \
103 } else if(strcmp(w, g)) { \
104 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \
105 __FILE__, __LINE__, #GOT, format(g), format(w)); \
111 static uint32_t *ucs4parse(const char *s) {
112 struct dynstr_ucs4 d;
115 dynstr_ucs4_init(&d);
118 dynstr_ucs4_append(&d, strtoul(s, &e, 0));
119 if(errno) fatal(errno, "strtoul (%s)", s);
122 dynstr_ucs4_terminate(&d);
126 static void test_utf8(void) {
127 /* Test validutf8, convert to UCS-4, check the answer is right,
128 * convert back to UTF-8, check we got to where we started */
129 #define U8(CHARS, WORDS) do { \
130 uint32_t *w = ucs4parse(WORDS); \
134 insist(validutf8(CHARS)); \
135 ucs = utf82ucs4(CHARS); \
137 insist(!ucs4cmp(w, ucs)); \
138 u8 = ucs42utf8(ucs); \
140 insist(!strcmp(u8, CHARS)); \
143 fprintf(stderr, "test_utf8\n");
149 /* ASCII characters */
151 U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~",
152 "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d "
153 "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a "
154 "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 "
155 "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 "
156 "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 "
157 "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e "
158 "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b "
160 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",
161 "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 "
162 "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d "
167 /* UTF8-2 = %xC2-DF UTF8-tail */
168 insist(!validutf8("\xC0\x80"));
169 insist(!validutf8("\xC1\x80"));
170 insist(!validutf8("\xC2\x7F"));
171 U8("\xC2\x80", "0x80");
172 U8("\xDF\xBF", "0x7FF");
173 insist(!validutf8("\xDF\xC0"));
175 /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
176 * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
178 insist(!validutf8("\xE0\x9F\x80"));
179 U8("\xE0\xA0\x80", "0x800");
180 U8("\xE0\xBF\xBF", "0xFFF");
181 insist(!validutf8("\xE0\xC0\xBF"));
183 insist(!validutf8("\xE1\x80\x7F"));
184 U8("\xE1\x80\x80", "0x1000");
185 U8("\xEC\xBF\xBF", "0xCFFF");
186 insist(!validutf8("\xEC\xC0\xBF"));
188 U8("\xED\x80\x80", "0xD000");
189 U8("\xED\x9F\xBF", "0xD7FF");
190 insist(!validutf8("\xED\xA0\xBF"));
192 insist(!validutf8("\xEE\x7f\x80"));
193 U8("\xEE\x80\x80", "0xE000");
194 U8("\xEF\xBF\xBF", "0xFFFF");
195 insist(!validutf8("\xEF\xC0\xBF"));
197 /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
198 * %xF4 %x80-8F 2( UTF8-tail )
200 insist(!validutf8("\xF0\x8F\x80\x80"));
201 U8("\xF0\x90\x80\x80", "0x10000");
202 U8("\xF0\xBF\xBF\xBF", "0x3FFFF");
203 insist(!validutf8("\xF0\xC0\x80\x80"));
205 insist(!validutf8("\xF1\x80\x80\x7F"));
206 U8("\xF1\x80\x80\x80", "0x40000");
207 U8("\xF3\xBF\xBF\xBF", "0xFFFFF");
208 insist(!validutf8("\xF3\xC0\x80\x80"));
210 insist(!validutf8("\xF4\x80\x80\x7F"));
211 U8("\xF4\x80\x80\x80", "0x100000");
212 U8("\xF4\x8F\xBF\xBF", "0x10FFFF");
213 insist(!validutf8("\xF4\x90\x80\x80"));
215 /* miscellaneous non-UTF-8 rubbish */
216 insist(!validutf8("\x80"));
217 insist(!validutf8("\xBF"));
218 insist(!validutf8("\xC0"));
219 insist(!validutf8("\xC0\x7F"));
220 insist(!validutf8("\xC0\xC0"));
221 insist(!validutf8("\xE0"));
222 insist(!validutf8("\xE0\x7F"));
223 insist(!validutf8("\xE0\xC0"));
224 insist(!validutf8("\xE0\x80"));
225 insist(!validutf8("\xE0\x80\x7f"));
226 insist(!validutf8("\xE0\x80\xC0"));
227 insist(!validutf8("\xF0"));
228 insist(!validutf8("\xF0\x7F"));
229 insist(!validutf8("\xF0\xC0"));
230 insist(!validutf8("\xF0\x80"));
231 insist(!validutf8("\xF0\x80\x7f"));
232 insist(!validutf8("\xF0\x80\xC0"));
233 insist(!validutf8("\xF0\x80\x80\x7f"));
234 insist(!validutf8("\xF0\x80\x80\xC0"));
235 insist(!validutf8("\xF5\x80\x80\x80"));
236 insist(!validutf8("\xF8"));
239 static void test_mime(void) {
242 fprintf(stderr, "test_mime\n");
245 insist(!mime_content_type("text/plain", &t, &n, &v));
246 insist(!strcmp(t, "text/plain"));
251 insist(!mime_content_type("TEXT ((nested) comment) /plain", &t, &n, &v));
252 insist(!strcmp(t, "text/plain"));
257 insist(!mime_content_type(" text/plain ; Charset=utf-8", &t, &n, &v));
258 insist(!strcmp(t, "text/plain"));
259 insist(!strcmp(n, "charset"));
260 insist(!strcmp(v, "utf-8"));
263 insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t, &n, &v));
264 insist(!strcmp(t, "text/plain"));
265 insist(!strcmp(n, "charset"));
266 insist(!strcmp(v, "ISO-8859-1"));
269 /* XXX mime_multipart */
270 /* XXX mime_rfc2388_content_disposition */
272 check_string(mime_qp(""), "");
273 check_string(mime_qp("foobar"), "foobar");
274 check_string(mime_qp("foo=20bar"), "foo bar");
275 check_string(mime_qp("x \r\ny"), "x\r\ny");
276 check_string(mime_qp("x=\r\ny"), "xy");
277 check_string(mime_qp("x= \r\ny"), "xy");
278 check_string(mime_qp("x =\r\ny"), "x y");
279 check_string(mime_qp("x = \r\ny"), "x y");
282 check_string(mime_qp("Now's the time =\r\n"
283 "for all folk to come=\r\n"
284 " to the aid of their country."),
285 "Now's the time for all folk to come to the aid of their country.");
287 check_string(mime_base64(""), "");
288 check_string(mime_base64("BBBB"), "\x04\x10\x41");
289 check_string(mime_base64("////"), "\xFF\xFF\xFF");
290 check_string(mime_base64("//BB"), "\xFF\xF0\x41");
291 check_string(mime_base64("BBBB//BB////"),
292 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
293 check_string(mime_base64("B B B B / / B B / / / /"),
294 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
295 check_string(mime_base64("B\r\nBBB.// B-B//~//"),
296 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
297 check_string(mime_base64("BBBB="),
299 check_string(mime_base64("BBBBx="), /* not actually valid base64 */
301 check_string(mime_base64("BBBB BB=="),
302 "\x04\x10\x41" "\x04");
303 check_string(mime_base64("BBBB BBB="),
304 "\x04\x10\x41" "\x04\x10");
307 static void test_hex(void) {
309 static const unsigned char h[] = { 0x00, 0xFF, 0x80, 0x7F };
313 fprintf(stderr, "test_hex\n");
315 for(n = 0; n <= UCHAR_MAX; ++n) {
317 insist(unhexdigitq(n) == -1);
319 insist(unhexdigitq('0') == 0);
320 insist(unhexdigitq('1') == 1);
321 insist(unhexdigitq('2') == 2);
322 insist(unhexdigitq('3') == 3);
323 insist(unhexdigitq('4') == 4);
324 insist(unhexdigitq('5') == 5);
325 insist(unhexdigitq('6') == 6);
326 insist(unhexdigitq('7') == 7);
327 insist(unhexdigitq('8') == 8);
328 insist(unhexdigitq('9') == 9);
329 insist(unhexdigitq('a') == 10);
330 insist(unhexdigitq('b') == 11);
331 insist(unhexdigitq('c') == 12);
332 insist(unhexdigitq('d') == 13);
333 insist(unhexdigitq('e') == 14);
334 insist(unhexdigitq('f') == 15);
335 insist(unhexdigitq('A') == 10);
336 insist(unhexdigitq('B') == 11);
337 insist(unhexdigitq('C') == 12);
338 insist(unhexdigitq('D') == 13);
339 insist(unhexdigitq('E') == 14);
340 insist(unhexdigitq('F') == 15);
341 check_string(hex(h, sizeof h), "00ff807f");
342 check_string(hex(0, 0), "");
343 u = unhex("00ff807f", &ul);
345 insist(memcmp(u, h, 4) == 0);
346 u = unhex("00FF807F", &ul);
348 insist(memcmp(u, h, 4) == 0);
351 fprintf(stderr, "2 ERROR reports expected {\n");
352 insist(unhex("F", 0) == 0);
353 insist(unhex("az", 0) == 0);
354 fprintf(stderr, "}\n");
357 static void test_casefold(void) {
359 const char *input, *canon_folded, *compat_folded, *canon_expected, *compat_expected;
361 fprintf(stderr, "test_casefold\n");
363 /* This isn't a very exhaustive test. Unlike for normalization, there don't
364 * seem to be any public test vectors for these algorithms. */
366 for(c = 1; c < 256; ++c) {
367 input = utf32_to_utf8(&c, 1, 0);
368 canon_folded = utf8_casefold_canon(input, strlen(input), 0);
369 compat_folded = utf8_casefold_compat(input, strlen(input), 0);
372 if((c >= 'A' && c <= 'Z')
373 || (c >= 0xC0 && c <= 0xDE && c != 0xD7))
378 case 0xB5: /* MICRO SIGN */
379 l = 0x3BC; /* GREEK SMALL LETTER MU */
381 case 0xDF: /* LATIN SMALL LETTER SHARP S */
382 insist(!strcmp(canon_folded, "ss"));
383 insist(!strcmp(compat_folded, "ss"));
388 /* Case-folded data is now normalized */
389 canon_expected = ucs42utf8(utf32_decompose_canon(&l, 1, 0));
390 if(strcmp(canon_folded, canon_expected)) {
391 fprintf(stderr, "%s:%d: canon-casefolding %#lx got '%s', expected '%s'\n",
392 __FILE__, __LINE__, (unsigned long)c,
393 format(canon_folded), format(canon_expected));
397 compat_expected = ucs42utf8(utf32_decompose_compat(&l, 1, 0));
398 if(strcmp(compat_folded, compat_expected)) {
399 fprintf(stderr, "%s:%d: compat-casefolding %#lx got '%s', expected '%s'\n",
400 __FILE__, __LINE__, (unsigned long)c,
401 format(compat_folded), format(compat_expected));
407 check_string(casefold(""), "");
410 /** @brief Less-than comparison function for integer heap */
411 static inline int int_lt(int a, int b) { return a < b; }
414 * @brief A heap with @c int elements */
415 HEAP_TYPE(iheap, int, int_lt);
416 HEAP_DEFINE(iheap, int, int_lt);
418 /** @brief Tests for @ref heap.h */
419 static void test_heap(void) {
424 fprintf(stderr, "test_heap\n");
427 for(n = 0; n < 1000; ++n)
428 iheap_insert(h, random() % 100);
429 for(n = 0; n < 1000; ++n) {
430 const int latest = iheap_remove(h);
432 fprintf(stderr, "should have %d <= %d\n", last, latest);
433 insist(last <= latest);
439 /** @brief Open a Unicode test file */
440 static FILE *open_unicode_test(const char *path) {
446 if((base = strrchr(path, '/')))
450 if(!(fp = fopen(base, "r"))) {
451 snprintf(buffer, sizeof buffer,
452 "wget http://www.unicode.org/Public/5.0.0/ucd/%s", path);
453 if((w = system(buffer)))
454 fatal(0, "%s: %s", buffer, wstat(w));
455 if(chmod(base, 0444) < 0)
456 fatal(errno, "chmod %s", base);
457 if(!(fp = fopen(base, "r")))
458 fatal(errno, "%s", base);
463 /** @brief Tests for @ref lib/unicode.h */
464 static void test_unicode(void) {
468 uint32_t buffer[1024];
469 uint32_t *c[6], *NFD_c[6], *NFKD_c[6]; /* 1-indexed */
471 char break_allowed[1024];
473 fprintf(stderr, "test_unicode\n");
474 fp = open_unicode_test("NormalizationTest.txt");
475 while(!inputline("NormalizationTest.txt", fp, &l, '\n')) {
477 if(*l == '#' || *l == '@')
482 c[cn++] = &buffer[bn];
483 while(*lp && *lp != '#') {
492 c[cn++] = &buffer[bn];
496 buffer[bn++] = strtoul(lp, &lp, 16);
500 for(cn = 1; cn <= 5; ++cn) {
501 NFD_c[cn] = utf32_decompose_canon(c[cn], utf32_len(c[cn]), 0);
502 NFKD_c[cn] = utf32_decompose_compat(c[cn], utf32_len(c[cn]), 0);
504 #define unt_check(T, A, B) do { \
506 if(utf32_cmp(c[A], T##_c[B])) { \
508 "NormalizationTest.txt:%d: c%d != "#T"(c%d)\n", \
510 fprintf(stderr, " c%d: %s\n", \
511 A, format_utf32(c[A])); \
512 fprintf(stderr, "%4s(c%d): %s\n", \
513 #T, B, format_utf32(T##_c[B])); \
517 unt_check(NFD, 3, 1);
518 unt_check(NFD, 3, 2);
519 unt_check(NFD, 3, 3);
520 unt_check(NFD, 5, 4);
521 unt_check(NFD, 5, 5);
522 unt_check(NFKD, 5, 1);
523 unt_check(NFKD, 5, 2);
524 unt_check(NFKD, 5, 3);
525 unt_check(NFKD, 5, 4);
526 unt_check(NFKD, 5, 5);
527 for(cn = 1; cn <= 5; ++cn) {
534 fp = open_unicode_test("auxiliary/GraphemeBreakTest.txt");
536 while(!inputline("GraphemeBreakTest.txt.txt", fp, &l, '\n')) {
538 if(l[0] == '#') continue;
542 if(*lp == ' ' || *lp == '\t') {
548 if((unsigned char)*lp == 0xC3 && (unsigned char)lp[1] == 0xB7) {
549 /* 00F7 DIVISION SIGN */
550 break_allowed[bn] = 1;
554 if((unsigned char)*lp == 0xC3 && (unsigned char)lp[1] == 0x97) {
555 /* 00D7 MULTIPLICATION SIGN */
556 break_allowed[bn] = 0;
560 if(isxdigit((unsigned char)*lp)) {
561 buffer[bn++] = strtoul(lp, &lp, 16);
564 fatal(0, "GraphemeBreakTest.txt:%d: evil line: %s", lineno, l);
566 for(cn = 0; cn <= bn; ++cn) {
567 if(utf32_is_gcb(buffer, bn, cn) != break_allowed[cn]) {
569 "GraphemeBreakTest.txt:%d: offset %d: utf32_is_gcb wrong\n",
580 insist('\n' == 0x0A);
581 insist('\r' == 0x0D);
595 /* configuration.c */
626 fprintf(stderr, "%d errors out of %d tests\n", errors, tests);