]> git.ipfire.org Git - thirdparty/u-boot.git/blob - test/unicode_ut.c
Merge branch '2020-04-11-CI-further-improvements' into next
[thirdparty/u-boot.git] / test / unicode_ut.c
1 // SPDX-License-Identifier: GPL-2.0+
2 /*
3 * Unit tests for Unicode functions
4 *
5 * Copyright (c) 2018 Heinrich Schuchardt <xypron.glpk@gmx.de>
6 */
7
8 #include <common.h>
9 #include <charset.h>
10 #include <command.h>
11 #include <errno.h>
12 #include <malloc.h>
13 #include <test/test.h>
14 #include <test/suites.h>
15 #include <test/ut.h>
16
17 /* Linker list entry for a Unicode test */
18 #define UNICODE_TEST(_name) UNIT_TEST(_name, 0, unicode_test)
19
20 /* Constants c1-c4 and d1-d4 encode the same letters */
21
22 /* Six characters translating to one utf-8 byte each. */
23 static const u16 c1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
24 /* One character translating to two utf-8 bytes */
25 static const u16 c2[] = {0x6b, 0x61, 0x66, 0x62, 0xe1, 0x74, 0x75, 0x72, 0x00};
26 /* Three characters translating to three utf-8 bytes each */
27 static const u16 c3[] = {0x6f5c, 0x6c34, 0x8266, 0x00};
28 /* Three letters translating to four utf-8 bytes each */
29 static const u16 c4[] = {0xd801, 0xdc8d, 0xd801, 0xdc96, 0xd801, 0xdc87,
30 0x0000};
31
32 /* Illegal utf-16 strings */
33 static const u16 i1[] = {0x69, 0x31, 0xdc87, 0x6c, 0x00};
34 static const u16 i2[] = {0x69, 0x32, 0xd801, 0xd801, 0x6c, 0x00};
35 static const u16 i3[] = {0x69, 0x33, 0xd801, 0x00};
36
37 /* Six characters translating to one utf-16 word each. */
38 static const char d1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
39 /* Eight characters translating to one utf-16 word each */
40 static const char d2[] = {0x6b, 0x61, 0x66, 0x62, 0xc3, 0xa1, 0x74, 0x75,
41 0x72, 0x00};
42 /* Three characters translating to one utf-16 word each */
43 static const char d3[] = {0xe6, 0xbd, 0x9c, 0xe6, 0xb0, 0xb4, 0xe8, 0x89,
44 0xa6, 0x00};
45 /* Three letters translating to two utf-16 word each */
46 static const char d4[] = {0xf0, 0x90, 0x92, 0x8d, 0xf0, 0x90, 0x92, 0x96,
47 0xf0, 0x90, 0x92, 0x87, 0x00};
48
49 /* Illegal utf-8 strings */
50 static const char j1[] = {0x6a, 0x31, 0xa1, 0x6c, 0x00};
51 static const char j2[] = {0x6a, 0x32, 0xc3, 0xc3, 0x6c, 0x00};
52 static const char j3[] = {0x6a, 0x33, 0xf0, 0x90, 0xf0, 0x00};
53
54 static int unicode_test_u16_strlen(struct unit_test_state *uts)
55 {
56 ut_asserteq(6, u16_strlen(c1));
57 ut_asserteq(8, u16_strlen(c2));
58 ut_asserteq(3, u16_strlen(c3));
59 ut_asserteq(6, u16_strlen(c4));
60 return 0;
61 }
62 UNICODE_TEST(unicode_test_u16_strlen);
63
64 static int unicode_test_u16_strdup(struct unit_test_state *uts)
65 {
66 u16 *copy = u16_strdup(c4);
67
68 ut_assert(copy != c4);
69 ut_assert(!memcmp(copy, c4, sizeof(c4)));
70 free(copy);
71 return 0;
72 }
73 UNICODE_TEST(unicode_test_u16_strdup);
74
75 static int unicode_test_u16_strcpy(struct unit_test_state *uts)
76 {
77 u16 *r;
78 u16 copy[10];
79
80 r = u16_strcpy(copy, c1);
81 ut_assert(r == copy);
82 ut_assert(!memcmp(copy, c1, sizeof(c1)));
83 return 0;
84 }
85 UNICODE_TEST(unicode_test_u16_strcpy);
86
87 /* U-Boot uses UTF-16 strings in the EFI context only. */
88 #if CONFIG_IS_ENABLED(EFI_LOADER) && !defined(API_BUILD)
89 static int unicode_test_string16(struct unit_test_state *uts)
90 {
91 char buf[20];
92
93 /* Test length and precision */
94 memset(buf, 0xff, sizeof(buf));
95 sprintf(buf, "%8.6ls", c2);
96 ut_asserteq(' ', buf[1]);
97 ut_assert(!strncmp(&buf[2], d2, 7));
98 ut_assert(!buf[9]);
99
100 memset(buf, 0xff, sizeof(buf));
101 sprintf(buf, "%8.6ls", c4);
102 ut_asserteq(' ', buf[4]);
103 ut_assert(!strncmp(&buf[5], d4, 12));
104 ut_assert(!buf[17]);
105
106 memset(buf, 0xff, sizeof(buf));
107 sprintf(buf, "%-8.2ls", c4);
108 ut_asserteq(' ', buf[8]);
109 ut_assert(!strncmp(buf, d4, 8));
110 ut_assert(!buf[14]);
111
112 /* Test handling of illegal utf-16 sequences */
113 memset(buf, 0xff, sizeof(buf));
114 sprintf(buf, "%ls", i1);
115 ut_asserteq_str("i1?l", buf);
116
117 memset(buf, 0xff, sizeof(buf));
118 sprintf(buf, "%ls", i2);
119 ut_asserteq_str("i2?l", buf);
120
121 memset(buf, 0xff, sizeof(buf));
122 sprintf(buf, "%ls", i3);
123 ut_asserteq_str("i3?", buf);
124
125 return 0;
126 }
127 UNICODE_TEST(unicode_test_string16);
128 #endif
129
130 static int unicode_test_utf8_get(struct unit_test_state *uts)
131 {
132 const char *s;
133 s32 code;
134 int i;
135
136 /* Check characters less than 0x800 */
137 s = d2;
138 for (i = 0; i < 8; ++i) {
139 code = utf8_get((const char **)&s);
140 /* c2 is the utf-8 encoding of d2 */
141 ut_asserteq(c2[i], code);
142 if (!code)
143 break;
144 }
145 ut_asserteq_ptr(s, d2 + 9)
146
147 /* Check characters less than 0x10000 */
148 s = d3;
149 for (i = 0; i < 4; ++i) {
150 code = utf8_get((const char **)&s);
151 /* c3 is the utf-8 encoding of d3 */
152 ut_asserteq(c3[i], code);
153 if (!code)
154 break;
155 }
156 ut_asserteq_ptr(s, d3 + 9)
157
158 /* Check character greater 0xffff */
159 s = d4;
160 code = utf8_get((const char **)&s);
161 ut_asserteq(0x0001048d, code);
162 ut_asserteq_ptr(s, d4 + 4);
163
164 return 0;
165 }
166 UNICODE_TEST(unicode_test_utf8_get);
167
168 static int unicode_test_utf8_put(struct unit_test_state *uts)
169 {
170 char buffer[8] = { 0, };
171 char *pos;
172
173 /* Commercial at, translates to one character */
174 pos = buffer;
175 ut_assert(!utf8_put('@', &pos))
176 ut_asserteq(1, pos - buffer);
177 ut_asserteq('@', buffer[0]);
178 ut_assert(!buffer[1]);
179
180 /* Latin letter G with acute, translates to two charactes */
181 pos = buffer;
182 ut_assert(!utf8_put(0x1f4, &pos));
183 ut_asserteq(2, pos - buffer);
184 ut_asserteq_str("\xc7\xb4", buffer);
185
186 /* Tagalog letter i, translates to three characters */
187 pos = buffer;
188 ut_assert(!utf8_put(0x1701, &pos));
189 ut_asserteq(3, pos - buffer);
190 ut_asserteq_str("\xe1\x9c\x81", buffer);
191
192 /* Hamster face, translates to four characters */
193 pos = buffer;
194 ut_assert(!utf8_put(0x1f439, &pos));
195 ut_asserteq(4, pos - buffer);
196 ut_asserteq_str("\xf0\x9f\x90\xb9", buffer);
197
198 /* Illegal code */
199 pos = buffer;
200 ut_asserteq(-1, utf8_put(0xd888, &pos));
201
202 return 0;
203 }
204 UNICODE_TEST(unicode_test_utf8_put);
205
206 static int unicode_test_utf8_utf16_strlen(struct unit_test_state *uts)
207 {
208 ut_asserteq(6, utf8_utf16_strlen(d1));
209 ut_asserteq(8, utf8_utf16_strlen(d2));
210 ut_asserteq(3, utf8_utf16_strlen(d3));
211 ut_asserteq(6, utf8_utf16_strlen(d4));
212
213 /* illegal utf-8 sequences */
214 ut_asserteq(4, utf8_utf16_strlen(j1));
215 ut_asserteq(4, utf8_utf16_strlen(j2));
216 ut_asserteq(3, utf8_utf16_strlen(j3));
217
218 return 0;
219 }
220 UNICODE_TEST(unicode_test_utf8_utf16_strlen);
221
222 static int unicode_test_utf8_utf16_strnlen(struct unit_test_state *uts)
223 {
224 ut_asserteq(3, utf8_utf16_strnlen(d1, 3));
225 ut_asserteq(6, utf8_utf16_strnlen(d1, 13));
226 ut_asserteq(6, utf8_utf16_strnlen(d2, 6));
227 ut_asserteq(2, utf8_utf16_strnlen(d3, 2));
228 ut_asserteq(4, utf8_utf16_strnlen(d4, 2));
229 ut_asserteq(6, utf8_utf16_strnlen(d4, 3));
230
231 /* illegal utf-8 sequences */
232 ut_asserteq(4, utf8_utf16_strnlen(j1, 16));
233 ut_asserteq(4, utf8_utf16_strnlen(j2, 16));
234 ut_asserteq(3, utf8_utf16_strnlen(j3, 16));
235
236 return 0;
237 }
238 UNICODE_TEST(unicode_test_utf8_utf16_strnlen);
239
240 /**
241 * ut_u16_strcmp() - Compare to u16 strings.
242 *
243 * @a1: first string
244 * @a2: second string
245 * @count: number of u16 to compare
246 * Return: -1 if a1 < a2, 0 if a1 == a2, 1 if a1 > a2
247 */
248 static int unicode_test_u16_strcmp(const u16 *a1, const u16 *a2, size_t count)
249 {
250 for (; (*a1 || *a2) && count; ++a1, ++a2, --count) {
251 if (*a1 < *a2)
252 return -1;
253 if (*a1 > *a2)
254 return 1;
255 }
256 return 0;
257 }
258
259 static int unicode_test_utf8_utf16_strcpy(struct unit_test_state *uts)
260 {
261 u16 buf[16];
262 u16 *pos;
263
264 pos = buf;
265 utf8_utf16_strcpy(&pos, d1);
266 ut_asserteq(6, pos - buf);
267 ut_assert(!unicode_test_u16_strcmp(buf, c1, SIZE_MAX));
268
269 pos = buf;
270 utf8_utf16_strcpy(&pos, d2);
271 ut_asserteq(8, pos - buf);
272 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
273
274 pos = buf;
275 utf8_utf16_strcpy(&pos, d3);
276 ut_asserteq(3, pos - buf);
277 ut_assert(!unicode_test_u16_strcmp(buf, c3, SIZE_MAX));
278
279 pos = buf;
280 utf8_utf16_strcpy(&pos, d4);
281 ut_asserteq(6, pos - buf);
282 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
283
284 /* Illegal utf-8 strings */
285 pos = buf;
286 utf8_utf16_strcpy(&pos, j1);
287 ut_asserteq(4, pos - buf);
288 ut_assert(!unicode_test_u16_strcmp(buf, L"j1?l", SIZE_MAX));
289
290 pos = buf;
291 utf8_utf16_strcpy(&pos, j2);
292 ut_asserteq(4, pos - buf);
293 ut_assert(!unicode_test_u16_strcmp(buf, L"j2?l", SIZE_MAX));
294
295 pos = buf;
296 utf8_utf16_strcpy(&pos, j3);
297 ut_asserteq(3, pos - buf);
298 ut_assert(!unicode_test_u16_strcmp(buf, L"j3?", SIZE_MAX));
299
300 return 0;
301 }
302 UNICODE_TEST(unicode_test_utf8_utf16_strcpy);
303
304 static int unicode_test_utf8_utf16_strncpy(struct unit_test_state *uts)
305 {
306 u16 buf[16];
307 u16 *pos;
308
309 pos = buf;
310 memset(buf, 0, sizeof(buf));
311 utf8_utf16_strncpy(&pos, d1, 4);
312 ut_asserteq(4, pos - buf);
313 ut_assert(!buf[4]);
314 ut_assert(!unicode_test_u16_strcmp(buf, c1, 4));
315
316 pos = buf;
317 memset(buf, 0, sizeof(buf));
318 utf8_utf16_strncpy(&pos, d2, 10);
319 ut_asserteq(8, pos - buf);
320 ut_assert(buf[4]);
321 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
322
323 pos = buf;
324 memset(buf, 0, sizeof(buf));
325 utf8_utf16_strncpy(&pos, d3, 2);
326 ut_asserteq(2, pos - buf);
327 ut_assert(!buf[2]);
328 ut_assert(!unicode_test_u16_strcmp(buf, c3, 2));
329
330 pos = buf;
331 memset(buf, 0, sizeof(buf));
332 utf8_utf16_strncpy(&pos, d4, 2);
333 ut_asserteq(4, pos - buf);
334 ut_assert(!buf[4]);
335 ut_assert(!unicode_test_u16_strcmp(buf, c4, 4));
336
337 pos = buf;
338 memset(buf, 0, sizeof(buf));
339 utf8_utf16_strncpy(&pos, d4, 10);
340 ut_asserteq(6, pos - buf);
341 ut_assert(buf[5]);
342 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
343
344 return 0;
345 }
346 UNICODE_TEST(unicode_test_utf8_utf16_strncpy);
347
348 static int unicode_test_utf16_get(struct unit_test_state *uts)
349 {
350 const u16 *s;
351 s32 code;
352 int i;
353
354 /* Check characters less than 0x10000 */
355 s = c2;
356 for (i = 0; i < 9; ++i) {
357 code = utf16_get((const u16 **)&s);
358 ut_asserteq(c2[i], code);
359 if (!code)
360 break;
361 }
362 ut_asserteq_ptr(c2 + 8, s);
363
364 /* Check character greater 0xffff */
365 s = c4;
366 code = utf16_get((const u16 **)&s);
367 ut_asserteq(0x0001048d, code);
368 ut_asserteq_ptr(c4 + 2, s);
369
370 return 0;
371 }
372 UNICODE_TEST(unicode_test_utf16_get);
373
374 static int unicode_test_utf16_put(struct unit_test_state *uts)
375 {
376 u16 buffer[4] = { 0, };
377 u16 *pos;
378
379 /* Commercial at, translates to one word */
380 pos = buffer;
381 ut_assert(!utf16_put('@', &pos));
382 ut_asserteq(1, pos - buffer);
383 ut_asserteq((u16)'@', buffer[0]);
384 ut_assert(!buffer[1]);
385
386 /* Hamster face, translates to two words */
387 pos = buffer;
388 ut_assert(!utf16_put(0x1f439, &pos));
389 ut_asserteq(2, pos - buffer);
390 ut_asserteq((u16)0xd83d, buffer[0]);
391 ut_asserteq((u16)0xdc39, buffer[1]);
392 ut_assert(!buffer[2]);
393
394 /* Illegal code */
395 pos = buffer;
396 ut_asserteq(-1, utf16_put(0xd888, &pos));
397
398 return 0;
399 }
400 UNICODE_TEST(unicode_test_utf16_put);
401
402 static int unicode_test_utf16_strnlen(struct unit_test_state *uts)
403 {
404 ut_asserteq(3, utf16_strnlen(c1, 3));
405 ut_asserteq(6, utf16_strnlen(c1, 13));
406 ut_asserteq(6, utf16_strnlen(c2, 6));
407 ut_asserteq(2, utf16_strnlen(c3, 2));
408 ut_asserteq(2, utf16_strnlen(c4, 2));
409 ut_asserteq(3, utf16_strnlen(c4, 3));
410
411 /* illegal utf-16 word sequences */
412 ut_asserteq(4, utf16_strnlen(i1, 16));
413 ut_asserteq(4, utf16_strnlen(i2, 16));
414 ut_asserteq(3, utf16_strnlen(i3, 16));
415
416 return 0;
417 }
418 UNICODE_TEST(unicode_test_utf16_strnlen);
419
420 static int unicode_test_utf16_utf8_strlen(struct unit_test_state *uts)
421 {
422 ut_asserteq(6, utf16_utf8_strlen(c1));
423 ut_asserteq(9, utf16_utf8_strlen(c2));
424 ut_asserteq(9, utf16_utf8_strlen(c3));
425 ut_asserteq(12, utf16_utf8_strlen(c4));
426
427 /* illegal utf-16 word sequences */
428 ut_asserteq(4, utf16_utf8_strlen(i1));
429 ut_asserteq(4, utf16_utf8_strlen(i2));
430 ut_asserteq(3, utf16_utf8_strlen(i3));
431
432 return 0;
433 }
434 UNICODE_TEST(unicode_test_utf16_utf8_strlen);
435
436 static int unicode_test_utf16_utf8_strnlen(struct unit_test_state *uts)
437 {
438 ut_asserteq(3, utf16_utf8_strnlen(c1, 3));
439 ut_asserteq(6, utf16_utf8_strnlen(c1, 13));
440 ut_asserteq(7, utf16_utf8_strnlen(c2, 6));
441 ut_asserteq(6, utf16_utf8_strnlen(c3, 2));
442 ut_asserteq(8, utf16_utf8_strnlen(c4, 2));
443 ut_asserteq(12, utf16_utf8_strnlen(c4, 3));
444 return 0;
445 }
446 UNICODE_TEST(unicode_test_utf16_utf8_strnlen);
447
448 static int unicode_test_utf16_utf8_strcpy(struct unit_test_state *uts)
449 {
450 char buf[16];
451 char *pos;
452
453 pos = buf;
454 utf16_utf8_strcpy(&pos, c1);
455 ut_asserteq(6, pos - buf);
456 ut_asserteq_str(d1, buf);
457
458 pos = buf;
459 utf16_utf8_strcpy(&pos, c2);
460 ut_asserteq(9, pos - buf);
461 ut_asserteq_str(d2, buf);
462
463 pos = buf;
464 utf16_utf8_strcpy(&pos, c3);
465 ut_asserteq(9, pos - buf);
466 ut_asserteq_str(d3, buf);
467
468 pos = buf;
469 utf16_utf8_strcpy(&pos, c4);
470 ut_asserteq(12, pos - buf);
471 ut_asserteq_str(d4, buf);
472
473 /* Illegal utf-16 strings */
474 pos = buf;
475 utf16_utf8_strcpy(&pos, i1);
476 ut_asserteq(4, pos - buf);
477 ut_asserteq_str("i1?l", buf);
478
479 pos = buf;
480 utf16_utf8_strcpy(&pos, i2);
481 ut_asserteq(4, pos - buf);
482 ut_asserteq_str("i2?l", buf);
483
484 pos = buf;
485 utf16_utf8_strcpy(&pos, i3);
486 ut_asserteq(3, pos - buf);
487 ut_asserteq_str("i3?", buf);
488
489 return 0;
490 }
491 UNICODE_TEST(unicode_test_utf16_utf8_strcpy);
492
493 static int unicode_test_utf16_utf8_strncpy(struct unit_test_state *uts)
494 {
495 char buf[16];
496 char *pos;
497
498 pos = buf;
499 memset(buf, 0, sizeof(buf));
500 utf16_utf8_strncpy(&pos, c1, 4);
501 ut_asserteq(4, pos - buf);
502 ut_assert(!buf[4]);
503 ut_assert(!strncmp(buf, d1, 4));
504
505 pos = buf;
506 memset(buf, 0, sizeof(buf));
507 utf16_utf8_strncpy(&pos, c2, 10);
508 ut_asserteq(9, pos - buf);
509 ut_assert(buf[4]);
510 ut_assert(!strncmp(buf, d2, SIZE_MAX));
511
512 pos = buf;
513 memset(buf, 0, sizeof(buf));
514 utf16_utf8_strncpy(&pos, c3, 2);
515 ut_asserteq(6, pos - buf);
516 ut_assert(!buf[6]);
517 ut_assert(!strncmp(buf, d3, 6));
518
519 pos = buf;
520 memset(buf, 0, sizeof(buf));
521 utf16_utf8_strncpy(&pos, c4, 2);
522 ut_asserteq(8, pos - buf);
523 ut_assert(!buf[8]);
524 ut_assert(!strncmp(buf, d4, 8));
525
526 pos = buf;
527 memset(buf, 0, sizeof(buf));
528 utf16_utf8_strncpy(&pos, c4, 10);
529 ut_asserteq(12, pos - buf);
530 ut_assert(buf[5]);
531 ut_assert(!strncmp(buf, d4, SIZE_MAX));
532
533 return 0;
534 }
535 UNICODE_TEST(unicode_test_utf16_utf8_strncpy);
536
537 static int unicode_test_utf_to_lower(struct unit_test_state *uts)
538 {
539 ut_asserteq('@', utf_to_lower('@'));
540 ut_asserteq('a', utf_to_lower('A'));
541 ut_asserteq('z', utf_to_lower('Z'));
542 ut_asserteq('[', utf_to_lower('['));
543 ut_asserteq('m', utf_to_lower('m'));
544 /* Latin letter O with diaresis (umlaut) */
545 ut_asserteq(0x00f6, utf_to_lower(0x00d6));
546 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
547 /* Cyrillic letter I*/
548 ut_asserteq(0x0438, utf_to_lower(0x0418));
549 #endif
550 return 0;
551 }
552 UNICODE_TEST(unicode_test_utf_to_lower);
553
554 static int unicode_test_utf_to_upper(struct unit_test_state *uts)
555 {
556 ut_asserteq('`', utf_to_upper('`'));
557 ut_asserteq('A', utf_to_upper('a'));
558 ut_asserteq('Z', utf_to_upper('z'));
559 ut_asserteq('{', utf_to_upper('{'));
560 ut_asserteq('M', utf_to_upper('M'));
561 /* Latin letter O with diaresis (umlaut) */
562 ut_asserteq(0x00d6, utf_to_upper(0x00f6));
563 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
564 /* Cyrillic letter I */
565 ut_asserteq(0x0418, utf_to_upper(0x0438));
566 #endif
567 return 0;
568 }
569 UNICODE_TEST(unicode_test_utf_to_upper);
570
571 static int unicode_test_u16_strncmp(struct unit_test_state *uts)
572 {
573 ut_assert(u16_strncmp(L"abc", L"abc", 3) == 0);
574 ut_assert(u16_strncmp(L"abcdef", L"abcghi", 3) == 0);
575 ut_assert(u16_strncmp(L"abcdef", L"abcghi", 6) < 0);
576 ut_assert(u16_strncmp(L"abcghi", L"abcdef", 6) > 0);
577 ut_assert(u16_strcmp(L"abc", L"abc") == 0);
578 ut_assert(u16_strcmp(L"abcdef", L"deghi") < 0);
579 ut_assert(u16_strcmp(L"deghi", L"abcdef") > 0);
580 return 0;
581 }
582 UNICODE_TEST(unicode_test_u16_strncmp);
583
584 int do_ut_unicode(cmd_tbl_t *cmdtp, int flag, int argc, char * const argv[])
585 {
586 struct unit_test *tests = ll_entry_start(struct unit_test, unicode_test);
587 const int n_ents = ll_entry_count(struct unit_test, unicode_test);
588
589 return cmd_ut_category("Unicode", "unicode_test_",
590 tests, n_ents, argc, argv);
591 }