]> git.ipfire.org Git - thirdparty/u-boot.git/blob - test/unicode_ut.c
test: add unit test for u16_strnlen()
[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 <efi_loader.h>
12 #include <errno.h>
13 #include <log.h>
14 #include <malloc.h>
15 #include <test/test.h>
16 #include <test/suites.h>
17 #include <test/ut.h>
18
19 /* Linker list entry for a Unicode test */
20 #define UNICODE_TEST(_name) UNIT_TEST(_name, 0, unicode_test)
21
22 /* Constants c1-c4 and d1-d4 encode the same letters */
23
24 /* Six characters translating to one utf-8 byte each. */
25 static const u16 c1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
26 /* One character translating to two utf-8 bytes */
27 static const u16 c2[] = {0x6b, 0x61, 0x66, 0x62, 0xe1, 0x74, 0x75, 0x72, 0x00};
28 /* Three characters translating to three utf-8 bytes each */
29 static const u16 c3[] = {0x6f5c, 0x6c34, 0x8266, 0x00};
30 /* Three letters translating to four utf-8 bytes each */
31 static const u16 c4[] = {0xd801, 0xdc8d, 0xd801, 0xdc96, 0xd801, 0xdc87,
32 0x0000};
33
34 /* Illegal utf-16 strings */
35 static const u16 i1[] = {0x69, 0x31, 0xdc87, 0x6c, 0x00};
36 static const u16 i2[] = {0x69, 0x32, 0xd801, 0xd801, 0x6c, 0x00};
37 static const u16 i3[] = {0x69, 0x33, 0xd801, 0x00};
38
39 /* Six characters translating to one utf-16 word each. */
40 static const char d1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
41 /* Eight characters translating to one utf-16 word each */
42 static const char d2[] = {0x6b, 0x61, 0x66, 0x62, 0xc3, 0xa1, 0x74, 0x75,
43 0x72, 0x00};
44 /* Three characters translating to one utf-16 word each */
45 static const char d3[] = {0xe6, 0xbd, 0x9c, 0xe6, 0xb0, 0xb4, 0xe8, 0x89,
46 0xa6, 0x00};
47 /* Three letters translating to two utf-16 word each */
48 static const char d4[] = {0xf0, 0x90, 0x92, 0x8d, 0xf0, 0x90, 0x92, 0x96,
49 0xf0, 0x90, 0x92, 0x87, 0x00};
50 /* Letter not in code page 437 */
51 static const char d5[] = {0xCE, 0x92, 0x20, 0x69, 0x73, 0x20, 0x6E, 0x6F,
52 0x74, 0x20, 0x42, 0x00};
53
54 /* Illegal utf-8 strings */
55 static const char j1[] = {0x6a, 0x31, 0xa1, 0x6c, 0x00};
56 static const char j2[] = {0x6a, 0x32, 0xc3, 0xc3, 0x6c, 0x00};
57 static const char j3[] = {0x6a, 0x33, 0xf0, 0x90, 0xf0, 0x00};
58 static const char j4[] = {0xa1, 0x00};
59
60 static int unicode_test_u16_strlen(struct unit_test_state *uts)
61 {
62 ut_asserteq(6, u16_strlen(c1));
63 ut_asserteq(8, u16_strlen(c2));
64 ut_asserteq(3, u16_strlen(c3));
65 ut_asserteq(6, u16_strlen(c4));
66 return 0;
67 }
68 UNICODE_TEST(unicode_test_u16_strlen);
69
70 static int unicode_test_u16_strnlen(struct unit_test_state *uts)
71 {
72 ut_asserteq(0, u16_strnlen(c1, 0));
73 ut_asserteq(4, u16_strnlen(c1, 4));
74 ut_asserteq(6, u16_strnlen(c1, 6));
75 ut_asserteq(6, u16_strnlen(c1, 7));
76
77 return 0;
78 }
79 UNICODE_TEST(unicode_test_u16_strnlen);
80
81 static int unicode_test_u16_strdup(struct unit_test_state *uts)
82 {
83 u16 *copy = u16_strdup(c4);
84
85 ut_assert(copy != c4);
86 ut_asserteq_mem(copy, c4, sizeof(c4));
87 free(copy);
88
89 return 0;
90 }
91 UNICODE_TEST(unicode_test_u16_strdup);
92
93 static int unicode_test_u16_strcpy(struct unit_test_state *uts)
94 {
95 u16 *r;
96 u16 copy[10];
97
98 r = u16_strcpy(copy, c1);
99 ut_assert(r == copy);
100 ut_asserteq_mem(copy, c1, sizeof(c1));
101
102 return 0;
103 }
104 UNICODE_TEST(unicode_test_u16_strcpy);
105
106 /* U-Boot uses UTF-16 strings in the EFI context only. */
107 #if CONFIG_IS_ENABLED(EFI_LOADER) && !defined(API_BUILD)
108 static int unicode_test_string16(struct unit_test_state *uts)
109 {
110 char buf[20];
111 int ret;
112
113 /* Test length and precision */
114 memset(buf, 0xff, sizeof(buf));
115 sprintf(buf, "%8.6ls", c2);
116 ut_asserteq(' ', buf[1]);
117 ut_assert(!strncmp(&buf[2], d2, 7));
118 ut_assert(!buf[9]);
119
120 memset(buf, 0xff, sizeof(buf));
121 sprintf(buf, "%8.6ls", c4);
122 ut_asserteq(' ', buf[4]);
123 ut_assert(!strncmp(&buf[5], d4, 12));
124 ut_assert(!buf[17]);
125
126 memset(buf, 0xff, sizeof(buf));
127 sprintf(buf, "%-8.2ls", c4);
128 ut_asserteq(' ', buf[8]);
129 ut_assert(!strncmp(buf, d4, 8));
130 ut_assert(!buf[14]);
131
132 /* Test handling of illegal utf-16 sequences */
133 memset(buf, 0xff, sizeof(buf));
134 sprintf(buf, "%ls", i1);
135 ut_asserteq_str("i1?l", buf);
136
137 memset(buf, 0xff, sizeof(buf));
138 sprintf(buf, "%ls", i2);
139 ut_asserteq_str("i2?l", buf);
140
141 memset(buf, 0xff, sizeof(buf));
142 sprintf(buf, "%ls", i3);
143 ut_asserteq_str("i3?", buf);
144
145 memset(buf, 0xff, sizeof(buf));
146 ret = snprintf(buf, 4, "%ls", c1);
147 ut_asserteq(6, ret);
148 ut_asserteq_str("U-B", buf);
149
150 memset(buf, 0xff, sizeof(buf));
151 ret = snprintf(buf, 6, "%ls", c2);
152 ut_asserteq_str("kafb", buf);
153 ut_asserteq(9, ret);
154
155 memset(buf, 0xff, sizeof(buf));
156 ret = snprintf(buf, 7, "%ls", c2);
157 ut_asserteq_str("kafb\xC3\xA1", buf);
158 ut_asserteq(9, ret);
159
160 memset(buf, 0xff, sizeof(buf));
161 ret = snprintf(buf, 8, "%ls", c3);
162 ut_asserteq_str("\xE6\xBD\x9C\xE6\xB0\xB4", buf);
163 ut_asserteq(9, ret);
164
165 memset(buf, 0xff, sizeof(buf));
166 ret = snprintf(buf, 11, "%ls", c4);
167 ut_asserteq_str("\xF0\x90\x92\x8D\xF0\x90\x92\x96", buf);
168 ut_asserteq(12, ret);
169
170 memset(buf, 0xff, sizeof(buf));
171 ret = snprintf(buf, 4, "%ls", c4);
172 ut_asserteq_str("", buf);
173 ut_asserteq(12, ret);
174
175 return 0;
176 }
177 UNICODE_TEST(unicode_test_string16);
178 #endif
179
180 static int unicode_test_utf8_get(struct unit_test_state *uts)
181 {
182 const char *s;
183 s32 code;
184 int i;
185
186 /* Check characters less than 0x800 */
187 s = d2;
188 for (i = 0; i < 8; ++i) {
189 code = utf8_get((const char **)&s);
190 /* c2 is the utf-8 encoding of d2 */
191 ut_asserteq(c2[i], code);
192 if (!code)
193 break;
194 }
195 ut_asserteq_ptr(s, d2 + 9)
196
197 /* Check characters less than 0x10000 */
198 s = d3;
199 for (i = 0; i < 4; ++i) {
200 code = utf8_get((const char **)&s);
201 /* c3 is the utf-8 encoding of d3 */
202 ut_asserteq(c3[i], code);
203 if (!code)
204 break;
205 }
206 ut_asserteq_ptr(s, d3 + 9)
207
208 /* Check character greater 0xffff */
209 s = d4;
210 code = utf8_get((const char **)&s);
211 ut_asserteq(0x0001048d, code);
212 ut_asserteq_ptr(s, d4 + 4);
213
214 /* Check illegal character */
215 s = j4;
216 code = utf8_get((const char **)&s);
217 ut_asserteq(-1, code);
218 ut_asserteq_ptr(j4 + 1, s);
219
220 return 0;
221 }
222 UNICODE_TEST(unicode_test_utf8_get);
223
224 static int unicode_test_utf8_put(struct unit_test_state *uts)
225 {
226 char buffer[8] = { 0, };
227 char *pos;
228
229 /* Commercial at, translates to one character */
230 pos = buffer;
231 ut_assert(!utf8_put('@', &pos))
232 ut_asserteq(1, pos - buffer);
233 ut_asserteq('@', buffer[0]);
234 ut_assert(!buffer[1]);
235
236 /* Latin letter G with acute, translates to two charactes */
237 pos = buffer;
238 ut_assert(!utf8_put(0x1f4, &pos));
239 ut_asserteq(2, pos - buffer);
240 ut_asserteq_str("\xc7\xb4", buffer);
241
242 /* Tagalog letter i, translates to three characters */
243 pos = buffer;
244 ut_assert(!utf8_put(0x1701, &pos));
245 ut_asserteq(3, pos - buffer);
246 ut_asserteq_str("\xe1\x9c\x81", buffer);
247
248 /* Hamster face, translates to four characters */
249 pos = buffer;
250 ut_assert(!utf8_put(0x1f439, &pos));
251 ut_asserteq(4, pos - buffer);
252 ut_asserteq_str("\xf0\x9f\x90\xb9", buffer);
253
254 /* Illegal code */
255 pos = buffer;
256 ut_asserteq(-1, utf8_put(0xd888, &pos));
257
258 return 0;
259 }
260 UNICODE_TEST(unicode_test_utf8_put);
261
262 static int unicode_test_utf8_utf16_strlen(struct unit_test_state *uts)
263 {
264 ut_asserteq(6, utf8_utf16_strlen(d1));
265 ut_asserteq(8, utf8_utf16_strlen(d2));
266 ut_asserteq(3, utf8_utf16_strlen(d3));
267 ut_asserteq(6, utf8_utf16_strlen(d4));
268
269 /* illegal utf-8 sequences */
270 ut_asserteq(4, utf8_utf16_strlen(j1));
271 ut_asserteq(4, utf8_utf16_strlen(j2));
272 ut_asserteq(3, utf8_utf16_strlen(j3));
273
274 return 0;
275 }
276 UNICODE_TEST(unicode_test_utf8_utf16_strlen);
277
278 static int unicode_test_utf8_utf16_strnlen(struct unit_test_state *uts)
279 {
280 ut_asserteq(3, utf8_utf16_strnlen(d1, 3));
281 ut_asserteq(6, utf8_utf16_strnlen(d1, 13));
282 ut_asserteq(6, utf8_utf16_strnlen(d2, 6));
283 ut_asserteq(2, utf8_utf16_strnlen(d3, 2));
284 ut_asserteq(4, utf8_utf16_strnlen(d4, 2));
285 ut_asserteq(6, utf8_utf16_strnlen(d4, 3));
286
287 /* illegal utf-8 sequences */
288 ut_asserteq(4, utf8_utf16_strnlen(j1, 16));
289 ut_asserteq(4, utf8_utf16_strnlen(j2, 16));
290 ut_asserteq(3, utf8_utf16_strnlen(j3, 16));
291
292 return 0;
293 }
294 UNICODE_TEST(unicode_test_utf8_utf16_strnlen);
295
296 /**
297 * ut_u16_strcmp() - Compare to u16 strings.
298 *
299 * @a1: first string
300 * @a2: second string
301 * @count: number of u16 to compare
302 * Return: -1 if a1 < a2, 0 if a1 == a2, 1 if a1 > a2
303 */
304 static int unicode_test_u16_strcmp(const u16 *a1, const u16 *a2, size_t count)
305 {
306 for (; (*a1 || *a2) && count; ++a1, ++a2, --count) {
307 if (*a1 < *a2)
308 return -1;
309 if (*a1 > *a2)
310 return 1;
311 }
312 return 0;
313 }
314
315 static int unicode_test_utf8_utf16_strcpy(struct unit_test_state *uts)
316 {
317 u16 buf[16];
318 u16 *pos;
319
320 pos = buf;
321 utf8_utf16_strcpy(&pos, d1);
322 ut_asserteq(6, pos - buf);
323 ut_assert(!unicode_test_u16_strcmp(buf, c1, SIZE_MAX));
324
325 pos = buf;
326 utf8_utf16_strcpy(&pos, d2);
327 ut_asserteq(8, pos - buf);
328 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
329
330 pos = buf;
331 utf8_utf16_strcpy(&pos, d3);
332 ut_asserteq(3, pos - buf);
333 ut_assert(!unicode_test_u16_strcmp(buf, c3, SIZE_MAX));
334
335 pos = buf;
336 utf8_utf16_strcpy(&pos, d4);
337 ut_asserteq(6, pos - buf);
338 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
339
340 /* Illegal utf-8 strings */
341 pos = buf;
342 utf8_utf16_strcpy(&pos, j1);
343 ut_asserteq(4, pos - buf);
344 ut_assert(!unicode_test_u16_strcmp(buf, u"j1?l", SIZE_MAX));
345
346 pos = buf;
347 utf8_utf16_strcpy(&pos, j2);
348 ut_asserteq(4, pos - buf);
349 ut_assert(!unicode_test_u16_strcmp(buf, u"j2?l", SIZE_MAX));
350
351 pos = buf;
352 utf8_utf16_strcpy(&pos, j3);
353 ut_asserteq(3, pos - buf);
354 ut_assert(!unicode_test_u16_strcmp(buf, u"j3?", SIZE_MAX));
355
356 return 0;
357 }
358 UNICODE_TEST(unicode_test_utf8_utf16_strcpy);
359
360 static int unicode_test_utf8_utf16_strncpy(struct unit_test_state *uts)
361 {
362 u16 buf[16];
363 u16 *pos;
364
365 pos = buf;
366 memset(buf, 0, sizeof(buf));
367 utf8_utf16_strncpy(&pos, d1, 4);
368 ut_asserteq(4, pos - buf);
369 ut_assert(!buf[4]);
370 ut_assert(!unicode_test_u16_strcmp(buf, c1, 4));
371
372 pos = buf;
373 memset(buf, 0, sizeof(buf));
374 utf8_utf16_strncpy(&pos, d2, 10);
375 ut_asserteq(8, pos - buf);
376 ut_assert(buf[4]);
377 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
378
379 pos = buf;
380 memset(buf, 0, sizeof(buf));
381 utf8_utf16_strncpy(&pos, d3, 2);
382 ut_asserteq(2, pos - buf);
383 ut_assert(!buf[2]);
384 ut_assert(!unicode_test_u16_strcmp(buf, c3, 2));
385
386 pos = buf;
387 memset(buf, 0, sizeof(buf));
388 utf8_utf16_strncpy(&pos, d4, 2);
389 ut_asserteq(4, pos - buf);
390 ut_assert(!buf[4]);
391 ut_assert(!unicode_test_u16_strcmp(buf, c4, 4));
392
393 pos = buf;
394 memset(buf, 0, sizeof(buf));
395 utf8_utf16_strncpy(&pos, d4, 10);
396 ut_asserteq(6, pos - buf);
397 ut_assert(buf[5]);
398 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
399
400 return 0;
401 }
402 UNICODE_TEST(unicode_test_utf8_utf16_strncpy);
403
404 static int unicode_test_utf16_get(struct unit_test_state *uts)
405 {
406 const u16 *s;
407 s32 code;
408 int i;
409
410 /* Check characters less than 0x10000 */
411 s = c2;
412 for (i = 0; i < 9; ++i) {
413 code = utf16_get((const u16 **)&s);
414 ut_asserteq(c2[i], code);
415 if (!code)
416 break;
417 }
418 ut_asserteq_ptr(c2 + 8, s);
419
420 /* Check character greater 0xffff */
421 s = c4;
422 code = utf16_get((const u16 **)&s);
423 ut_asserteq(0x0001048d, code);
424 ut_asserteq_ptr(c4 + 2, s);
425
426 return 0;
427 }
428 UNICODE_TEST(unicode_test_utf16_get);
429
430 static int unicode_test_utf16_put(struct unit_test_state *uts)
431 {
432 u16 buffer[4] = { 0, };
433 u16 *pos;
434
435 /* Commercial at, translates to one word */
436 pos = buffer;
437 ut_assert(!utf16_put('@', &pos));
438 ut_asserteq(1, pos - buffer);
439 ut_asserteq((u16)'@', buffer[0]);
440 ut_assert(!buffer[1]);
441
442 /* Hamster face, translates to two words */
443 pos = buffer;
444 ut_assert(!utf16_put(0x1f439, &pos));
445 ut_asserteq(2, pos - buffer);
446 ut_asserteq((u16)0xd83d, buffer[0]);
447 ut_asserteq((u16)0xdc39, buffer[1]);
448 ut_assert(!buffer[2]);
449
450 /* Illegal code */
451 pos = buffer;
452 ut_asserteq(-1, utf16_put(0xd888, &pos));
453
454 return 0;
455 }
456 UNICODE_TEST(unicode_test_utf16_put);
457
458 static int unicode_test_utf16_strnlen(struct unit_test_state *uts)
459 {
460 ut_asserteq(3, utf16_strnlen(c1, 3));
461 ut_asserteq(6, utf16_strnlen(c1, 13));
462 ut_asserteq(6, utf16_strnlen(c2, 6));
463 ut_asserteq(2, utf16_strnlen(c3, 2));
464 ut_asserteq(2, utf16_strnlen(c4, 2));
465 ut_asserteq(3, utf16_strnlen(c4, 3));
466
467 /* illegal utf-16 word sequences */
468 ut_asserteq(4, utf16_strnlen(i1, 16));
469 ut_asserteq(4, utf16_strnlen(i2, 16));
470 ut_asserteq(3, utf16_strnlen(i3, 16));
471
472 return 0;
473 }
474 UNICODE_TEST(unicode_test_utf16_strnlen);
475
476 static int unicode_test_utf16_utf8_strlen(struct unit_test_state *uts)
477 {
478 ut_asserteq(6, utf16_utf8_strlen(c1));
479 ut_asserteq(9, utf16_utf8_strlen(c2));
480 ut_asserteq(9, utf16_utf8_strlen(c3));
481 ut_asserteq(12, utf16_utf8_strlen(c4));
482
483 /* illegal utf-16 word sequences */
484 ut_asserteq(4, utf16_utf8_strlen(i1));
485 ut_asserteq(4, utf16_utf8_strlen(i2));
486 ut_asserteq(3, utf16_utf8_strlen(i3));
487
488 return 0;
489 }
490 UNICODE_TEST(unicode_test_utf16_utf8_strlen);
491
492 static int unicode_test_utf16_utf8_strnlen(struct unit_test_state *uts)
493 {
494 ut_asserteq(3, utf16_utf8_strnlen(c1, 3));
495 ut_asserteq(6, utf16_utf8_strnlen(c1, 13));
496 ut_asserteq(7, utf16_utf8_strnlen(c2, 6));
497 ut_asserteq(6, utf16_utf8_strnlen(c3, 2));
498 ut_asserteq(8, utf16_utf8_strnlen(c4, 2));
499 ut_asserteq(12, utf16_utf8_strnlen(c4, 3));
500 return 0;
501 }
502 UNICODE_TEST(unicode_test_utf16_utf8_strnlen);
503
504 static int unicode_test_utf16_utf8_strcpy(struct unit_test_state *uts)
505 {
506 char buf[16];
507 char *pos;
508
509 pos = buf;
510 utf16_utf8_strcpy(&pos, c1);
511 ut_asserteq(6, pos - buf);
512 ut_asserteq_str(d1, buf);
513
514 pos = buf;
515 utf16_utf8_strcpy(&pos, c2);
516 ut_asserteq(9, pos - buf);
517 ut_asserteq_str(d2, buf);
518
519 pos = buf;
520 utf16_utf8_strcpy(&pos, c3);
521 ut_asserteq(9, pos - buf);
522 ut_asserteq_str(d3, buf);
523
524 pos = buf;
525 utf16_utf8_strcpy(&pos, c4);
526 ut_asserteq(12, pos - buf);
527 ut_asserteq_str(d4, buf);
528
529 /* Illegal utf-16 strings */
530 pos = buf;
531 utf16_utf8_strcpy(&pos, i1);
532 ut_asserteq(4, pos - buf);
533 ut_asserteq_str("i1?l", buf);
534
535 pos = buf;
536 utf16_utf8_strcpy(&pos, i2);
537 ut_asserteq(4, pos - buf);
538 ut_asserteq_str("i2?l", buf);
539
540 pos = buf;
541 utf16_utf8_strcpy(&pos, i3);
542 ut_asserteq(3, pos - buf);
543 ut_asserteq_str("i3?", buf);
544
545 return 0;
546 }
547 UNICODE_TEST(unicode_test_utf16_utf8_strcpy);
548
549 static int unicode_test_utf16_utf8_strncpy(struct unit_test_state *uts)
550 {
551 char buf[16];
552 char *pos;
553
554 pos = buf;
555 memset(buf, 0, sizeof(buf));
556 utf16_utf8_strncpy(&pos, c1, 4);
557 ut_asserteq(4, pos - buf);
558 ut_assert(!buf[4]);
559 ut_assert(!strncmp(buf, d1, 4));
560
561 pos = buf;
562 memset(buf, 0, sizeof(buf));
563 utf16_utf8_strncpy(&pos, c2, 10);
564 ut_asserteq(9, pos - buf);
565 ut_assert(buf[4]);
566 ut_assert(!strncmp(buf, d2, SIZE_MAX));
567
568 pos = buf;
569 memset(buf, 0, sizeof(buf));
570 utf16_utf8_strncpy(&pos, c3, 2);
571 ut_asserteq(6, pos - buf);
572 ut_assert(!buf[6]);
573 ut_assert(!strncmp(buf, d3, 6));
574
575 pos = buf;
576 memset(buf, 0, sizeof(buf));
577 utf16_utf8_strncpy(&pos, c4, 2);
578 ut_asserteq(8, pos - buf);
579 ut_assert(!buf[8]);
580 ut_assert(!strncmp(buf, d4, 8));
581
582 pos = buf;
583 memset(buf, 0, sizeof(buf));
584 utf16_utf8_strncpy(&pos, c4, 10);
585 ut_asserteq(12, pos - buf);
586 ut_assert(buf[5]);
587 ut_assert(!strncmp(buf, d4, SIZE_MAX));
588
589 return 0;
590 }
591 UNICODE_TEST(unicode_test_utf16_utf8_strncpy);
592
593 static int unicode_test_utf_to_lower(struct unit_test_state *uts)
594 {
595 ut_asserteq('@', utf_to_lower('@'));
596 ut_asserteq('a', utf_to_lower('A'));
597 ut_asserteq('z', utf_to_lower('Z'));
598 ut_asserteq('[', utf_to_lower('['));
599 ut_asserteq('m', utf_to_lower('m'));
600 /* Latin letter O with diaresis (umlaut) */
601 ut_asserteq(0x00f6, utf_to_lower(0x00d6));
602 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
603 /* Cyrillic letter I*/
604 ut_asserteq(0x0438, utf_to_lower(0x0418));
605 #endif
606 return 0;
607 }
608 UNICODE_TEST(unicode_test_utf_to_lower);
609
610 static int unicode_test_utf_to_upper(struct unit_test_state *uts)
611 {
612 ut_asserteq('`', utf_to_upper('`'));
613 ut_asserteq('A', utf_to_upper('a'));
614 ut_asserteq('Z', utf_to_upper('z'));
615 ut_asserteq('{', utf_to_upper('{'));
616 ut_asserteq('M', utf_to_upper('M'));
617 /* Latin letter O with diaresis (umlaut) */
618 ut_asserteq(0x00d6, utf_to_upper(0x00f6));
619 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
620 /* Cyrillic letter I */
621 ut_asserteq(0x0418, utf_to_upper(0x0438));
622 #endif
623 return 0;
624 }
625 UNICODE_TEST(unicode_test_utf_to_upper);
626
627 static int unicode_test_u16_strncmp(struct unit_test_state *uts)
628 {
629 ut_assert(u16_strncmp(u"abc", u"abc", 3) == 0);
630 ut_assert(u16_strncmp(u"abcdef", u"abcghi", 3) == 0);
631 ut_assert(u16_strncmp(u"abcdef", u"abcghi", 6) < 0);
632 ut_assert(u16_strncmp(u"abcghi", u"abcdef", 6) > 0);
633 ut_assert(u16_strcmp(u"abc", u"abc") == 0);
634 ut_assert(u16_strcmp(u"abcdef", u"deghi") < 0);
635 ut_assert(u16_strcmp(u"deghi", u"abcdef") > 0);
636 return 0;
637 }
638 UNICODE_TEST(unicode_test_u16_strncmp);
639
640 static int unicode_test_u16_strsize(struct unit_test_state *uts)
641 {
642 ut_asserteq_64(u16_strsize(c1), 14);
643 ut_asserteq_64(u16_strsize(c2), 18);
644 ut_asserteq_64(u16_strsize(c3), 8);
645 ut_asserteq_64(u16_strsize(c4), 14);
646 return 0;
647 }
648 UNICODE_TEST(unicode_test_u16_strsize);
649
650 static int unicode_test_utf_to_cp(struct unit_test_state *uts)
651 {
652 int ret;
653 s32 c;
654
655 c = '\n';
656 ret = utf_to_cp(&c, codepage_437);
657 ut_asserteq(0, ret);
658 ut_asserteq('\n', c);
659
660 c = 'a';
661 ret = utf_to_cp(&c, codepage_437);
662 ut_asserteq(0, ret);
663 ut_asserteq('a', c);
664
665 c = 0x03c4; /* Greek small letter tau */
666 ret = utf_to_cp(&c, codepage_437);
667 ut_asserteq(0, ret);
668 ut_asserteq(0xe7, c);
669
670 c = 0x03a4; /* Greek capital letter tau */
671 ret = utf_to_cp(&c, codepage_437);
672 ut_asserteq(-ENOENT, ret);
673 ut_asserteq('?', c);
674
675 return 0;
676 }
677 UNICODE_TEST(unicode_test_utf_to_cp);
678
679 static void utf8_to_cp437_stream_helper(const char *in, char *out)
680 {
681 char buffer[5];
682 int ret;
683
684 *buffer = 0;
685 for (; *in; ++in) {
686 ret = utf8_to_cp437_stream(*in, buffer);
687 if (ret)
688 *out++ = ret;
689 }
690 *out = 0;
691 }
692
693 static int unicode_test_utf8_to_cp437_stream(struct unit_test_state *uts)
694 {
695 char buf[16];
696
697 utf8_to_cp437_stream_helper(d1, buf);
698 ut_asserteq_str("U-Boot", buf);
699 utf8_to_cp437_stream_helper(d2, buf);
700 ut_asserteq_str("kafb\xa0tur", buf);
701 utf8_to_cp437_stream_helper(d5, buf);
702 ut_asserteq_str("? is not B", buf);
703 utf8_to_cp437_stream_helper(j2, buf);
704 ut_asserteq_str("j2l", buf);
705
706 return 0;
707 }
708 UNICODE_TEST(unicode_test_utf8_to_cp437_stream);
709
710 static void utf8_to_utf32_stream_helper(const char *in, s32 *out)
711 {
712 char buffer[5];
713 int ret;
714
715 *buffer = 0;
716 for (; *in; ++in) {
717 ret = utf8_to_utf32_stream(*in, buffer);
718 if (ret)
719 *out++ = ret;
720 }
721 *out = 0;
722 }
723
724 static int unicode_test_utf8_to_utf32_stream(struct unit_test_state *uts)
725 {
726 s32 buf[16];
727
728 const u32 u1[] = {0x55, 0x2D, 0x42, 0x6F, 0x6F, 0x74, 0x0000};
729 const u32 u2[] = {0x6B, 0x61, 0x66, 0x62, 0xE1, 0x74, 0x75, 0x72, 0x00};
730 const u32 u3[] = {0x0392, 0x20, 0x69, 0x73, 0x20, 0x6E, 0x6F, 0x74,
731 0x20, 0x42, 0x00};
732 const u32 u4[] = {0x6A, 0x32, 0x6C, 0x00};
733
734 memset(buf, 0, sizeof(buf));
735 utf8_to_utf32_stream_helper(d1, buf);
736 ut_asserteq_mem(u1, buf, sizeof(u1));
737
738 memset(buf, 0, sizeof(buf));
739 utf8_to_utf32_stream_helper(d2, buf);
740 ut_asserteq_mem(u2, buf, sizeof(u2));
741
742 memset(buf, 0, sizeof(buf));
743 utf8_to_utf32_stream_helper(d5, buf);
744 ut_asserteq_mem(u3, buf, sizeof(u3));
745
746 memset(buf, 0, sizeof(buf));
747 utf8_to_utf32_stream_helper(j2, buf);
748 ut_asserteq_mem(u4, buf, sizeof(u4));
749
750 return 0;
751 }
752 UNICODE_TEST(unicode_test_utf8_to_utf32_stream);
753
754 #ifdef CONFIG_EFI_LOADER
755 static int unicode_test_efi_create_indexed_name(struct unit_test_state *uts)
756 {
757 u16 buf[16];
758 u16 const expected[] = u"Capsule0AF9";
759 u16 *pos;
760
761 memset(buf, 0xeb, sizeof(buf));
762 pos = efi_create_indexed_name(buf, sizeof(buf), "Capsule", 0x0af9);
763
764 ut_asserteq_mem(expected, buf, sizeof(expected));
765 ut_asserteq(pos - buf, u16_strnlen(buf, SIZE_MAX));
766
767 return 0;
768 }
769 UNICODE_TEST(unicode_test_efi_create_indexed_name);
770 #endif
771
772 static int unicode_test_u16_strlcat(struct unit_test_state *uts)
773 {
774 u16 buf[40];
775 u16 dest[] = {0x3053, 0x3093, 0x306b, 0x3061, 0x306f, 0};
776 u16 src[] = {0x03B1, 0x2172, 0x6F5C, 0x8247, 0};
777 u16 concat_str[] = {0x3053, 0x3093, 0x306b, 0x3061, 0x306f,
778 0x03B1, 0x2172, 0x6F5C, 0x8247, 0};
779 u16 null_src = u'\0';
780 size_t ret, expected;
781 int i;
782
783 /* dest and src are empty string */
784 memset(buf, 0, sizeof(buf));
785 ret = u16_strlcat(buf, &null_src, sizeof(buf));
786 ut_asserteq(1, ret);
787
788 /* dest is empty string */
789 memset(buf, 0, sizeof(buf));
790 ret = u16_strlcat(buf, src, sizeof(buf));
791 ut_asserteq(5, ret);
792 ut_assert(!unicode_test_u16_strcmp(buf, src, 40));
793
794 /* src is empty string */
795 memset(buf, 0xCD, (sizeof(buf) - sizeof(u16)));
796 buf[39] = 0;
797 memcpy(buf, dest, sizeof(dest));
798 ret = u16_strlcat(buf, &null_src, sizeof(buf));
799 ut_asserteq(6, ret);
800 ut_assert(!unicode_test_u16_strcmp(buf, dest, 40));
801
802 for (i = 0; i <= 40; i++) {
803 memset(buf, 0xCD, (sizeof(buf) - sizeof(u16)));
804 buf[39] = 0;
805 memcpy(buf, dest, sizeof(dest));
806 expected = 10;
807 ret = u16_strlcat(buf, src, i);
808 ut_asserteq(expected, ret);
809 if (i <= 6) {
810 ut_assert(!unicode_test_u16_strcmp(buf, dest, 40));
811 } else if (i < 10) {
812 ut_assert(!unicode_test_u16_strcmp(buf, concat_str, i - 1));
813 } else {
814 ut_assert(!unicode_test_u16_strcmp(buf, concat_str, 40));
815 }
816 }
817
818 return 0;
819 }
820 UNICODE_TEST(unicode_test_u16_strlcat);
821
822 int do_ut_unicode(struct cmd_tbl *cmdtp, int flag, int argc, char *const argv[])
823 {
824 struct unit_test *tests = UNIT_TEST_SUITE_START(unicode_test);
825 const int n_ents = UNIT_TEST_SUITE_COUNT(unicode_test);
826
827 return cmd_ut_category("Unicode", "unicode_test_",
828 tests, n_ents, argc, argv);
829 }