chiark / gitweb /
Generate, but do not use, composition mappings.
[disorder] / lib / test.c
CommitLineData
460b9539 1/*
2 * This file is part of DisOrder.
033fd4e3 3 * Copyright (C) 2005, 2007 Richard Kettlewell
460b9539 4 *
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.
9 *
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.
14 *
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
18 * USA
19 */
033fd4e3 20/** @file lib/test.c @brief Library tests */
460b9539 21
22#include <config.h>
23#include "types.h"
24
25#include <stdio.h>
26#include <string.h>
27#include <stdlib.h>
28#include <errno.h>
29#include <ctype.h>
033fd4e3 30#include <assert.h>
e5a5a138
RK
31#include <sys/types.h>
32#include <sys/stat.h>
460b9539 33
34#include "utf8.h"
35#include "mem.h"
36#include "log.h"
37#include "vector.h"
38#include "charset.h"
39#include "mime.h"
40#include "hex.h"
41#include "words.h"
033fd4e3 42#include "heap.h"
e5a5a138
RK
43#include "unicode.h"
44#include "inputline.h"
e2452add 45#include "wstat.h"
460b9539 46
47static int tests, errors;
bb48024f
RK
48static int fail_first;
49
50static void count_error() {
51 ++errors;
52 if(fail_first)
53 abort();
54}
460b9539 55
033fd4e3 56/** @brief Checks that @p expr is nonzero */
460b9539 57#define insist(expr) do { \
033fd4e3 58 if(!(expr)) { \
bb48024f 59 count_error(); \
460b9539 60 fprintf(stderr, "%s:%d: error checking %s\n", \
61 __FILE__, __LINE__, #expr); \
62 } \
63 ++tests; \
64} while(0)
65
66static const char *format(const char *s) {
67 struct dynstr d;
68 int c;
69 char buf[10];
70
71 dynstr_init(&d);
72 while((c = (unsigned char)*s++)) {
73 if(c >= ' ' && c <= '~')
74 dynstr_append(&d, c);
75 else {
76 sprintf(buf, "\\x%02X", (unsigned)c);
77 dynstr_append_string(&d, buf);
78 }
79 }
80 dynstr_terminate(&d);
81 return d.vec;
82}
83
e5a5a138
RK
84static const char *format_utf32(const uint32_t *s) {
85 struct dynstr d;
86 uint32_t c;
87 char buf[64];
88
89 dynstr_init(&d);
90 while((c = *s++)) {
91 if(c >= 32 && c <= 127)
92 dynstr_append(&d, c);
93 else {
94 sprintf(buf, "\\x%04lX", (unsigned long)c);
95 dynstr_append_string(&d, buf);
96 }
97 }
98 dynstr_terminate(&d);
99 return d.vec;
100}
101
460b9539 102#define check_string(GOT, WANT) do { \
103 const char *g = GOT; \
104 const char *w = WANT; \
105 \
106 if(w == 0) { \
107 fprintf(stderr, "%s:%d: %s returned 0\n", \
108 __FILE__, __LINE__, #GOT); \
bb48024f 109 count_error(); \
460b9539 110 } else if(strcmp(w, g)) { \
111 fprintf(stderr, "%s:%d: %s returned:\n%s\nexpected:\n%s\n", \
112 __FILE__, __LINE__, #GOT, format(g), format(w)); \
bb48024f 113 count_error(); \
460b9539 114 } \
115 ++tests; \
116 } while(0)
117
118static uint32_t *ucs4parse(const char *s) {
119 struct dynstr_ucs4 d;
120 char *e;
121
122 dynstr_ucs4_init(&d);
123 while(*s) {
124 errno = 0;
125 dynstr_ucs4_append(&d, strtoul(s, &e, 0));
126 if(errno) fatal(errno, "strtoul (%s)", s);
127 s = e;
128 }
129 dynstr_ucs4_terminate(&d);
130 return d.vec;
131}
132
133static void test_utf8(void) {
134 /* Test validutf8, convert to UCS-4, check the answer is right,
135 * convert back to UTF-8, check we got to where we started */
136#define U8(CHARS, WORDS) do { \
137 uint32_t *w = ucs4parse(WORDS); \
138 uint32_t *ucs; \
139 char *u8; \
140 \
141 insist(validutf8(CHARS)); \
caecd4f4 142 ucs = utf8_to_utf32(CHARS, strlen(CHARS), 0); \
460b9539 143 insist(ucs != 0); \
caecd4f4
RK
144 insist(!utf32_cmp(w, ucs)); \
145 u8 = utf32_to_utf8(ucs, utf32_len(ucs), 0); \
460b9539 146 insist(u8 != 0); \
147 insist(!strcmp(u8, CHARS)); \
148} while(0)
149
033fd4e3 150 fprintf(stderr, "test_utf8\n");
18cda350 151#define validutf8(S) utf8_valid((S), strlen(S))
033fd4e3 152
460b9539 153 /* empty string */
154
155 U8("", "");
156
157 /* ASCII characters */
158
159 U8(" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~",
160 "0x20 0x21 0x22 0x23 0x24 0x25 0x26 0x27 0x28 0x29 0x2a 0x2b 0x2c 0x2d "
161 "0x2e 0x2f 0x30 0x31 0x32 0x33 0x34 0x35 0x36 0x37 0x38 0x39 0x3a "
162 "0x3b 0x3c 0x3d 0x3e 0x3f 0x40 0x41 0x42 0x43 0x44 0x45 0x46 0x47 "
163 "0x48 0x49 0x4a 0x4b 0x4c 0x4d 0x4e 0x4f 0x50 0x51 0x52 0x53 0x54 "
164 "0x55 0x56 0x57 0x58 0x59 0x5a 0x5b 0x5c 0x5d 0x5e 0x5f 0x60 0x61 "
165 "0x62 0x63 0x64 0x65 0x66 0x67 0x68 0x69 0x6a 0x6b 0x6c 0x6d 0x6e "
166 "0x6f 0x70 0x71 0x72 0x73 0x74 0x75 0x76 0x77 0x78 0x79 0x7a 0x7b "
167 "0x7c 0x7d 0x7e");
168 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",
169 "0x1 0x2 0x3 0x4 0x5 0x6 0x7 0x8 0x9 0xa 0xb 0xc 0xd 0xe 0xf 0x10 "
170 "0x11 0x12 0x13 0x14 0x15 0x16 0x17 0x18 0x19 0x1a 0x1b 0x1c 0x1d "
171 "0x1e 0x1f 0x7f");
172
173 /* from RFC3629 */
174
175 /* UTF8-2 = %xC2-DF UTF8-tail */
176 insist(!validutf8("\xC0\x80"));
177 insist(!validutf8("\xC1\x80"));
178 insist(!validutf8("\xC2\x7F"));
179 U8("\xC2\x80", "0x80");
180 U8("\xDF\xBF", "0x7FF");
181 insist(!validutf8("\xDF\xC0"));
182
183 /* UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
184 * %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
185 */
186 insist(!validutf8("\xE0\x9F\x80"));
187 U8("\xE0\xA0\x80", "0x800");
188 U8("\xE0\xBF\xBF", "0xFFF");
189 insist(!validutf8("\xE0\xC0\xBF"));
190
191 insist(!validutf8("\xE1\x80\x7F"));
192 U8("\xE1\x80\x80", "0x1000");
193 U8("\xEC\xBF\xBF", "0xCFFF");
194 insist(!validutf8("\xEC\xC0\xBF"));
195
196 U8("\xED\x80\x80", "0xD000");
197 U8("\xED\x9F\xBF", "0xD7FF");
198 insist(!validutf8("\xED\xA0\xBF"));
199
200 insist(!validutf8("\xEE\x7f\x80"));
201 U8("\xEE\x80\x80", "0xE000");
202 U8("\xEF\xBF\xBF", "0xFFFF");
203 insist(!validutf8("\xEF\xC0\xBF"));
204
205 /* UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
206 * %xF4 %x80-8F 2( UTF8-tail )
207 */
208 insist(!validutf8("\xF0\x8F\x80\x80"));
209 U8("\xF0\x90\x80\x80", "0x10000");
210 U8("\xF0\xBF\xBF\xBF", "0x3FFFF");
211 insist(!validutf8("\xF0\xC0\x80\x80"));
212
213 insist(!validutf8("\xF1\x80\x80\x7F"));
214 U8("\xF1\x80\x80\x80", "0x40000");
215 U8("\xF3\xBF\xBF\xBF", "0xFFFFF");
216 insist(!validutf8("\xF3\xC0\x80\x80"));
217
218 insist(!validutf8("\xF4\x80\x80\x7F"));
219 U8("\xF4\x80\x80\x80", "0x100000");
220 U8("\xF4\x8F\xBF\xBF", "0x10FFFF");
221 insist(!validutf8("\xF4\x90\x80\x80"));
222
223 /* miscellaneous non-UTF-8 rubbish */
224 insist(!validutf8("\x80"));
225 insist(!validutf8("\xBF"));
226 insist(!validutf8("\xC0"));
227 insist(!validutf8("\xC0\x7F"));
228 insist(!validutf8("\xC0\xC0"));
229 insist(!validutf8("\xE0"));
230 insist(!validutf8("\xE0\x7F"));
231 insist(!validutf8("\xE0\xC0"));
232 insist(!validutf8("\xE0\x80"));
233 insist(!validutf8("\xE0\x80\x7f"));
234 insist(!validutf8("\xE0\x80\xC0"));
235 insist(!validutf8("\xF0"));
236 insist(!validutf8("\xF0\x7F"));
237 insist(!validutf8("\xF0\xC0"));
238 insist(!validutf8("\xF0\x80"));
239 insist(!validutf8("\xF0\x80\x7f"));
240 insist(!validutf8("\xF0\x80\xC0"));
241 insist(!validutf8("\xF0\x80\x80\x7f"));
242 insist(!validutf8("\xF0\x80\x80\xC0"));
243 insist(!validutf8("\xF5\x80\x80\x80"));
244 insist(!validutf8("\xF8"));
245}
246
247static void test_mime(void) {
248 char *t, *n, *v;
249
033fd4e3
RK
250 fprintf(stderr, "test_mime\n");
251
460b9539 252 t = n = v = 0;
253 insist(!mime_content_type("text/plain", &t, &n, &v));
254 insist(!strcmp(t, "text/plain"));
255 insist(n == 0);
256 insist(v == 0);
257
258 t = n = v = 0;
259 insist(!mime_content_type("TEXT ((nested) comment) /plain", &t, &n, &v));
260 insist(!strcmp(t, "text/plain"));
261 insist(n == 0);
262 insist(v == 0);
263
264 t = n = v = 0;
265 insist(!mime_content_type(" text/plain ; Charset=utf-8", &t, &n, &v));
266 insist(!strcmp(t, "text/plain"));
267 insist(!strcmp(n, "charset"));
268 insist(!strcmp(v, "utf-8"));
269
270 t = n = v = 0;
271 insist(!mime_content_type("text/plain;charset = ISO-8859-1 ", &t, &n, &v));
272 insist(!strcmp(t, "text/plain"));
273 insist(!strcmp(n, "charset"));
274 insist(!strcmp(v, "ISO-8859-1"));
275
276 /* XXX mime_parse */
277 /* XXX mime_multipart */
278 /* XXX mime_rfc2388_content_disposition */
279
280 check_string(mime_qp(""), "");
281 check_string(mime_qp("foobar"), "foobar");
282 check_string(mime_qp("foo=20bar"), "foo bar");
283 check_string(mime_qp("x \r\ny"), "x\r\ny");
284 check_string(mime_qp("x=\r\ny"), "xy");
285 check_string(mime_qp("x= \r\ny"), "xy");
286 check_string(mime_qp("x =\r\ny"), "x y");
287 check_string(mime_qp("x = \r\ny"), "x y");
288
289 /* from RFC2045 */
290 check_string(mime_qp("Now's the time =\r\n"
291"for all folk to come=\r\n"
292" to the aid of their country."),
293 "Now's the time for all folk to come to the aid of their country.");
294
295 check_string(mime_base64(""), "");
296 check_string(mime_base64("BBBB"), "\x04\x10\x41");
297 check_string(mime_base64("////"), "\xFF\xFF\xFF");
298 check_string(mime_base64("//BB"), "\xFF\xF0\x41");
299 check_string(mime_base64("BBBB//BB////"),
300 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
301 check_string(mime_base64("B B B B / / B B / / / /"),
302 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
303 check_string(mime_base64("B\r\nBBB.// B-B//~//"),
304 "\x04\x10\x41" "\xFF\xF0\x41" "\xFF\xFF\xFF");
305 check_string(mime_base64("BBBB="),
306 "\x04\x10\x41");
307 check_string(mime_base64("BBBBx="), /* not actually valid base64 */
308 "\x04\x10\x41");
309 check_string(mime_base64("BBBB BB=="),
310 "\x04\x10\x41" "\x04");
311 check_string(mime_base64("BBBB BBB="),
312 "\x04\x10\x41" "\x04\x10");
313}
314
315static void test_hex(void) {
316 unsigned n;
317 static const unsigned char h[] = { 0x00, 0xFF, 0x80, 0x7F };
318 uint8_t *u;
319 size_t ul;
320
033fd4e3
RK
321 fprintf(stderr, "test_hex\n");
322
460b9539 323 for(n = 0; n <= UCHAR_MAX; ++n) {
324 if(!isxdigit(n))
325 insist(unhexdigitq(n) == -1);
326 }
327 insist(unhexdigitq('0') == 0);
328 insist(unhexdigitq('1') == 1);
329 insist(unhexdigitq('2') == 2);
330 insist(unhexdigitq('3') == 3);
331 insist(unhexdigitq('4') == 4);
332 insist(unhexdigitq('5') == 5);
333 insist(unhexdigitq('6') == 6);
334 insist(unhexdigitq('7') == 7);
335 insist(unhexdigitq('8') == 8);
336 insist(unhexdigitq('9') == 9);
337 insist(unhexdigitq('a') == 10);
338 insist(unhexdigitq('b') == 11);
339 insist(unhexdigitq('c') == 12);
340 insist(unhexdigitq('d') == 13);
341 insist(unhexdigitq('e') == 14);
342 insist(unhexdigitq('f') == 15);
343 insist(unhexdigitq('A') == 10);
344 insist(unhexdigitq('B') == 11);
345 insist(unhexdigitq('C') == 12);
346 insist(unhexdigitq('D') == 13);
347 insist(unhexdigitq('E') == 14);
348 insist(unhexdigitq('F') == 15);
349 check_string(hex(h, sizeof h), "00ff807f");
350 check_string(hex(0, 0), "");
351 u = unhex("00ff807f", &ul);
352 insist(ul == 4);
353 insist(memcmp(u, h, 4) == 0);
354 u = unhex("00FF807F", &ul);
355 insist(ul == 4);
356 insist(memcmp(u, h, 4) == 0);
357 u = unhex("", &ul);
358 insist(ul == 0);
033fd4e3 359 fprintf(stderr, "2 ERROR reports expected {\n");
460b9539 360 insist(unhex("F", 0) == 0);
361 insist(unhex("az", 0) == 0);
033fd4e3 362 fprintf(stderr, "}\n");
460b9539 363}
364
365static void test_casefold(void) {
e5a5a138 366 uint32_t c, l;
56fd389c 367 const char *input, *canon_folded, *compat_folded, *canon_expected, *compat_expected;
460b9539 368
033fd4e3 369 fprintf(stderr, "test_casefold\n");
56fd389c
RK
370
371 /* This isn't a very exhaustive test. Unlike for normalization, there don't
372 * seem to be any public test vectors for these algorithms. */
e5a5a138 373
460b9539 374 for(c = 1; c < 256; ++c) {
e5a5a138 375 input = utf32_to_utf8(&c, 1, 0);
56fd389c
RK
376 canon_folded = utf8_casefold_canon(input, strlen(input), 0);
377 compat_folded = utf8_casefold_compat(input, strlen(input), 0);
460b9539 378 switch(c) {
379 default:
380 if((c >= 'A' && c <= 'Z')
381 || (c >= 0xC0 && c <= 0xDE && c != 0xD7))
382 l = c ^ 0x20;
383 else
384 l = c;
385 break;
386 case 0xB5: /* MICRO SIGN */
e5a5a138 387 l = 0x3BC; /* GREEK SMALL LETTER MU */
460b9539 388 break;
389 case 0xDF: /* LATIN SMALL LETTER SHARP S */
56fd389c
RK
390 insist(!strcmp(canon_folded, "ss"));
391 insist(!strcmp(compat_folded, "ss"));
460b9539 392 l = 0;
393 break;
394 }
395 if(l) {
caecd4f4 396 uint32_t *d;
e5a5a138 397 /* Case-folded data is now normalized */
caecd4f4
RK
398 d = utf32_decompose_canon(&l, 1, 0);
399 canon_expected = utf32_to_utf8(d, utf32_len(d), 0);
56fd389c
RK
400 if(strcmp(canon_folded, canon_expected)) {
401 fprintf(stderr, "%s:%d: canon-casefolding %#lx got '%s', expected '%s'\n",
402 __FILE__, __LINE__, (unsigned long)c,
403 format(canon_folded), format(canon_expected));
bb48024f 404 count_error();
56fd389c
RK
405 }
406 ++tests;
caecd4f4
RK
407 d = utf32_decompose_compat(&l, 1, 0);
408 compat_expected = utf32_to_utf8(d, utf32_len(d), 0);
56fd389c
RK
409 if(strcmp(compat_folded, compat_expected)) {
410 fprintf(stderr, "%s:%d: compat-casefolding %#lx got '%s', expected '%s'\n",
460b9539 411 __FILE__, __LINE__, (unsigned long)c,
56fd389c 412 format(compat_folded), format(compat_expected));
bb48024f 413 count_error();
460b9539 414 }
415 ++tests;
416 }
417 }
418 check_string(casefold(""), "");
419}
420
033fd4e3
RK
421/** @brief Less-than comparison function for integer heap */
422static inline int int_lt(int a, int b) { return a < b; }
423
dab22732
RK
424/** @struct iheap
425 * @brief A heap with @c int elements */
033fd4e3 426HEAP_TYPE(iheap, int, int_lt);
8e3fe3d8 427HEAP_DEFINE(iheap, int, int_lt);
033fd4e3
RK
428
429/** @brief Tests for @ref heap.h */
430static void test_heap(void) {
431 struct iheap h[1];
432 int n;
433 int last = -1;
434
435 fprintf(stderr, "test_heap\n");
436
437 iheap_init(h);
438 for(n = 0; n < 1000; ++n)
439 iheap_insert(h, random() % 100);
440 for(n = 0; n < 1000; ++n) {
441 const int latest = iheap_remove(h);
442 if(last > latest)
443 fprintf(stderr, "should have %d <= %d\n", last, latest);
444 insist(last <= latest);
445 last = latest;
446 }
447 putchar('\n');
448}
449
e2452add
RK
450/** @brief Open a Unicode test file */
451static FILE *open_unicode_test(const char *path) {
452 const char *base;
453 FILE *fp;
454 char buffer[1024];
455 int w;
456
457 if((base = strrchr(path, '/')))
458 ++base;
459 else
460 base = path;
461 if(!(fp = fopen(base, "r"))) {
462 snprintf(buffer, sizeof buffer,
463 "wget http://www.unicode.org/Public/5.0.0/ucd/%s", path);
464 if((w = system(buffer)))
465 fatal(0, "%s: %s", buffer, wstat(w));
466 if(chmod(base, 0444) < 0)
467 fatal(errno, "chmod %s", base);
468 if(!(fp = fopen(base, "r")))
469 fatal(errno, "%s", base);
470 }
471 return fp;
472}
473
1625e11a 474/** @brief Run breaking tests for utf32_grapheme_boundary() etc */
bb48024f
RK
475static void breaktest(const char *path,
476 int (*breakfn)(const uint32_t *, size_t, size_t)) {
477 FILE *fp = open_unicode_test(path);
478 int lineno = 0;
479 char *l, *lp;
480 size_t bn, n;
481 char break_allowed[1024];
482 uint32_t buffer[1024];
483
484 while(!inputline(path, fp, &l, '\n')) {
485 ++lineno;
486 if(l[0] == '#') continue;
487 bn = 0;
488 lp = l;
489 while(*lp) {
490 if(*lp == ' ' || *lp == '\t') {
491 ++lp;
492 continue;
493 }
494 if(*lp == '#')
495 break;
496 if((unsigned char)*lp == 0xC3 && (unsigned char)lp[1] == 0xB7) {
497 /* 00F7 DIVISION SIGN */
498 break_allowed[bn] = 1;
499 lp += 2;
500 continue;
501 }
502 if((unsigned char)*lp == 0xC3 && (unsigned char)lp[1] == 0x97) {
503 /* 00D7 MULTIPLICATION SIGN */
504 break_allowed[bn] = 0;
505 lp += 2;
506 continue;
507 }
508 if(isxdigit((unsigned char)*lp)) {
509 buffer[bn++] = strtoul(lp, &lp, 16);
510 continue;
511 }
512 fatal(0, "%s:%d: evil line: %s", path, lineno, l);
513 }
514 for(n = 0; n <= bn; ++n) {
515 if(breakfn(buffer, bn, n) != break_allowed[n]) {
516 fprintf(stderr,
b21a155c
RK
517 "%s:%d: offset %zu: mismatch\n"
518 "%s\n"
519 "\n",
520 path, lineno, n, l);
bb48024f
RK
521 count_error();
522 }
523 ++tests;
524 }
525 xfree(l);
526 }
527 fclose(fp);
528}
529
e5a5a138
RK
530/** @brief Tests for @ref lib/unicode.h */
531static void test_unicode(void) {
532 FILE *fp;
533 int lineno = 0;
534 char *l, *lp;
535 uint32_t buffer[1024];
536 uint32_t *c[6], *NFD_c[6], *NFKD_c[6]; /* 1-indexed */
537 int cn, bn;
538
539 fprintf(stderr, "test_unicode\n");
e2452add 540 fp = open_unicode_test("NormalizationTest.txt");
e5a5a138
RK
541 while(!inputline("NormalizationTest.txt", fp, &l, '\n')) {
542 ++lineno;
543 if(*l == '#' || *l == '@')
544 continue;
545 bn = 0;
546 cn = 1;
547 lp = l;
548 c[cn++] = &buffer[bn];
549 while(*lp && *lp != '#') {
550 if(*lp == ' ') {
551 ++lp;
552 continue;
553 }
554 if(*lp == ';') {
555 buffer[bn++] = 0;
556 if(cn == 6)
557 break;
558 c[cn++] = &buffer[bn];
559 ++lp;
560 continue;
561 }
562 buffer[bn++] = strtoul(lp, &lp, 16);
563 }
564 buffer[bn] = 0;
565 assert(cn == 6);
566 for(cn = 1; cn <= 5; ++cn) {
567 NFD_c[cn] = utf32_decompose_canon(c[cn], utf32_len(c[cn]), 0);
568 NFKD_c[cn] = utf32_decompose_compat(c[cn], utf32_len(c[cn]), 0);
569 }
570#define unt_check(T, A, B) do { \
571 ++tests; \
572 if(utf32_cmp(c[A], T##_c[B])) { \
e2452add
RK
573 fprintf(stderr, \
574 "NormalizationTest.txt:%d: c%d != "#T"(c%d)\n", \
575 lineno, A, B); \
bcf9ed7f 576 fprintf(stderr, " c%d: %s\n", \
e5a5a138
RK
577 A, format_utf32(c[A])); \
578 fprintf(stderr, "%4s(c%d): %s\n", \
579 #T, B, format_utf32(T##_c[B])); \
bcf9ed7f 580 count_error(); \
e5a5a138
RK
581 } \
582 } while(0)
583 unt_check(NFD, 3, 1);
584 unt_check(NFD, 3, 2);
585 unt_check(NFD, 3, 3);
586 unt_check(NFD, 5, 4);
587 unt_check(NFD, 5, 5);
588 unt_check(NFKD, 5, 1);
589 unt_check(NFKD, 5, 2);
590 unt_check(NFKD, 5, 3);
591 unt_check(NFKD, 5, 4);
592 unt_check(NFKD, 5, 5);
593 for(cn = 1; cn <= 5; ++cn) {
594 xfree(NFD_c[cn]);
595 xfree(NFKD_c[cn]);
596 }
597 xfree(l);
598 }
e2452add 599 fclose(fp);
1625e11a 600 breaktest("auxiliary/GraphemeBreakTest.txt", utf32_is_grapheme_boundary);
bb48024f 601 breaktest("auxiliary/WordBreakTest.txt", utf32_is_word_boundary);
e5a5a138
RK
602}
603
460b9539 604int main(void) {
bb48024f 605 fail_first = !!getenv("FAIL_FIRST");
460b9539 606 insist('\n' == 0x0A);
607 insist('\r' == 0x0D);
608 insist(' ' == 0x20);
609 insist('0' == 0x30);
610 insist('9' == 0x39);
611 insist('A' == 0x41);
612 insist('Z' == 0x5A);
613 insist('a' == 0x61);
614 insist('z' == 0x7A);
615 /* addr.c */
616 /* asprintf.c */
617 /* authhash.c */
618 /* basen.c */
619 /* charset.c */
620 /* client.c */
621 /* configuration.c */
622 /* event.c */
623 /* fprintf.c */
033fd4e3
RK
624 /* heap.c */
625 test_heap();
460b9539 626 /* hex.c */
627 test_hex();
628 /* inputline.c */
629 /* kvp.c */
630 /* log.c */
631 /* mem.c */
632 /* mime.c */
633 test_mime();
634 /* mixer.c */
635 /* plugin.c */
636 /* printf.c */
637 /* queue.c */
638 /* sink.c */
639 /* snprintf.c */
640 /* split.c */
641 /* syscalls.c */
642 /* table.c */
e5a5a138
RK
643 /* unicode.c */
644 test_unicode();
460b9539 645 /* utf8.c */
646 test_utf8();
647 /* vector.c */
648 /* words.c */
649 test_casefold();
650 /* XXX words() */
651 /* wstat.c */
652 fprintf(stderr, "%d errors out of %d tests\n", errors, tests);
653 return !!errors;
654}
655
656/*
657Local Variables:
658c-basic-offset:2
659comment-column:40
56fd389c
RK
660fill-column:79
661indent-tabs-mode:nil
460b9539 662End:
663*/