1 // SPDX-License-Identifier: GPL-2.0+
3 * Unit tests for Unicode functions
14 #include <test/test.h>
15 #include <test/suites.h>
18 /* Linker list entry for a Unicode test */
19 #define UNICODE_TEST(_name) UNIT_TEST(_name, 0, unicode_test)
21 /* Constants c1-c4 and d1-d4 encode the same letters */
23 /* Six characters translating to one utf-8 byte each. */
24 static const u16 c1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
25 /* One character translating to two utf-8 bytes */
26 static const u16 c2[] = {0x6b, 0x61, 0x66, 0x62, 0xe1, 0x74, 0x75, 0x72, 0x00};
27 /* Three characters translating to three utf-8 bytes each */
28 static const u16 c3[] = {0x6f5c, 0x6c34, 0x8266, 0x00};
29 /* Three letters translating to four utf-8 bytes each */
30 static const u16 c4[] = {0xd801, 0xdc8d, 0xd801, 0xdc96, 0xd801, 0xdc87,
33 /* Illegal utf-16 strings */
34 static const u16 i1[] = {0x69, 0x31, 0xdc87, 0x6c, 0x00};
35 static const u16 i2[] = {0x69, 0x32, 0xd801, 0xd801, 0x6c, 0x00};
36 static const u16 i3[] = {0x69, 0x33, 0xd801, 0x00};
38 /* Six characters translating to one utf-16 word each. */
39 static const char d1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
40 /* Eight characters translating to one utf-16 word each */
41 static const char d2[] = {0x6b, 0x61, 0x66, 0x62, 0xc3, 0xa1, 0x74, 0x75,
43 /* Three characters translating to one utf-16 word each */
44 static const char d3[] = {0xe6, 0xbd, 0x9c, 0xe6, 0xb0, 0xb4, 0xe8, 0x89,
46 /* Three letters translating to two utf-16 word each */
47 static const char d4[] = {0xf0, 0x90, 0x92, 0x8d, 0xf0, 0x90, 0x92, 0x96,
48 0xf0, 0x90, 0x92, 0x87, 0x00};
50 /* Illegal utf-8 strings */
51 static const char j1[] = {0x6a, 0x31, 0xa1, 0x6c, 0x00};
52 static const char j2[] = {0x6a, 0x32, 0xc3, 0xc3, 0x6c, 0x00};
53 static const char j3[] = {0x6a, 0x33, 0xf0, 0x90, 0xf0, 0x00};
55 static int unicode_test_u16_strlen(struct unit_test_state *uts)
57 ut_asserteq(6, u16_strlen(c1));
58 ut_asserteq(8, u16_strlen(c2));
59 ut_asserteq(3, u16_strlen(c3));
60 ut_asserteq(6, u16_strlen(c4));
63 UNICODE_TEST(unicode_test_u16_strlen);
65 static int unicode_test_u16_strdup(struct unit_test_state *uts)
67 u16 *copy = u16_strdup(c4);
69 ut_assert(copy != c4);
70 ut_assert(!memcmp(copy, c4, sizeof(c4)));
74 UNICODE_TEST(unicode_test_u16_strdup);
76 static int unicode_test_u16_strcpy(struct unit_test_state *uts)
81 r = u16_strcpy(copy, c1);
83 ut_assert(!memcmp(copy, c1, sizeof(c1)));
86 UNICODE_TEST(unicode_test_u16_strcpy);
88 /* U-Boot uses UTF-16 strings in the EFI context only. */
89 #if CONFIG_IS_ENABLED(EFI_LOADER) && !defined(API_BUILD)
90 static int unicode_test_string16(struct unit_test_state *uts)
94 /* Test length and precision */
95 memset(buf, 0xff, sizeof(buf));
96 sprintf(buf, "%8.6ls", c2);
97 ut_asserteq(' ', buf[1]);
98 ut_assert(!strncmp(&buf[2], d2, 7));
101 memset(buf, 0xff, sizeof(buf));
102 sprintf(buf, "%8.6ls", c4);
103 ut_asserteq(' ', buf[4]);
104 ut_assert(!strncmp(&buf[5], d4, 12));
107 memset(buf, 0xff, sizeof(buf));
108 sprintf(buf, "%-8.2ls", c4);
109 ut_asserteq(' ', buf[8]);
110 ut_assert(!strncmp(buf, d4, 8));
113 /* Test handling of illegal utf-16 sequences */
114 memset(buf, 0xff, sizeof(buf));
115 sprintf(buf, "%ls", i1);
116 ut_asserteq_str("i1?l", buf);
118 memset(buf, 0xff, sizeof(buf));
119 sprintf(buf, "%ls", i2);
120 ut_asserteq_str("i2?l", buf);
122 memset(buf, 0xff, sizeof(buf));
123 sprintf(buf, "%ls", i3);
124 ut_asserteq_str("i3?", buf);
128 UNICODE_TEST(unicode_test_string16);
131 static int unicode_test_utf8_get(struct unit_test_state *uts)
137 /* Check characters less than 0x800 */
139 for (i = 0; i < 8; ++i) {
140 code = utf8_get((const char **)&s);
141 /* c2 is the utf-8 encoding of d2 */
142 ut_asserteq(c2[i], code);
146 ut_asserteq_ptr(s, d2 + 9)
148 /* Check characters less than 0x10000 */
150 for (i = 0; i < 4; ++i) {
151 code = utf8_get((const char **)&s);
152 /* c3 is the utf-8 encoding of d3 */
153 ut_asserteq(c3[i], code);
157 ut_asserteq_ptr(s, d3 + 9)
159 /* Check character greater 0xffff */
161 code = utf8_get((const char **)&s);
162 ut_asserteq(0x0001048d, code);
163 ut_asserteq_ptr(s, d4 + 4);
167 UNICODE_TEST(unicode_test_utf8_get);
169 static int unicode_test_utf8_put(struct unit_test_state *uts)
171 char buffer[8] = { 0, };
174 /* Commercial at, translates to one character */
176 ut_assert(!utf8_put('@', &pos))
177 ut_asserteq(1, pos - buffer);
178 ut_asserteq('@', buffer[0]);
179 ut_assert(!buffer[1]);
181 /* Latin letter G with acute, translates to two charactes */
183 ut_assert(!utf8_put(0x1f4, &pos));
184 ut_asserteq(2, pos - buffer);
185 ut_asserteq_str("\xc7\xb4", buffer);
187 /* Tagalog letter i, translates to three characters */
189 ut_assert(!utf8_put(0x1701, &pos));
190 ut_asserteq(3, pos - buffer);
191 ut_asserteq_str("\xe1\x9c\x81", buffer);
193 /* Hamster face, translates to four characters */
195 ut_assert(!utf8_put(0x1f439, &pos));
196 ut_asserteq(4, pos - buffer);
197 ut_asserteq_str("\xf0\x9f\x90\xb9", buffer);
201 ut_asserteq(-1, utf8_put(0xd888, &pos));
205 UNICODE_TEST(unicode_test_utf8_put);
207 static int unicode_test_utf8_utf16_strlen(struct unit_test_state *uts)
209 ut_asserteq(6, utf8_utf16_strlen(d1));
210 ut_asserteq(8, utf8_utf16_strlen(d2));
211 ut_asserteq(3, utf8_utf16_strlen(d3));
212 ut_asserteq(6, utf8_utf16_strlen(d4));
214 /* illegal utf-8 sequences */
215 ut_asserteq(4, utf8_utf16_strlen(j1));
216 ut_asserteq(4, utf8_utf16_strlen(j2));
217 ut_asserteq(3, utf8_utf16_strlen(j3));
221 UNICODE_TEST(unicode_test_utf8_utf16_strlen);
223 static int unicode_test_utf8_utf16_strnlen(struct unit_test_state *uts)
225 ut_asserteq(3, utf8_utf16_strnlen(d1, 3));
226 ut_asserteq(6, utf8_utf16_strnlen(d1, 13));
227 ut_asserteq(6, utf8_utf16_strnlen(d2, 6));
228 ut_asserteq(2, utf8_utf16_strnlen(d3, 2));
229 ut_asserteq(4, utf8_utf16_strnlen(d4, 2));
230 ut_asserteq(6, utf8_utf16_strnlen(d4, 3));
232 /* illegal utf-8 sequences */
233 ut_asserteq(4, utf8_utf16_strnlen(j1, 16));
234 ut_asserteq(4, utf8_utf16_strnlen(j2, 16));
235 ut_asserteq(3, utf8_utf16_strnlen(j3, 16));
239 UNICODE_TEST(unicode_test_utf8_utf16_strnlen);
242 * ut_u16_strcmp() - Compare to u16 strings.
246 * @count: number of u16 to compare
247 * Return: -1 if a1 < a2, 0 if a1 == a2, 1 if a1 > a2
249 static int unicode_test_u16_strcmp(const u16 *a1, const u16 *a2, size_t count)
251 for (; (*a1 || *a2) && count; ++a1, ++a2, --count) {
260 static int unicode_test_utf8_utf16_strcpy(struct unit_test_state *uts)
266 utf8_utf16_strcpy(&pos, d1);
267 ut_asserteq(6, pos - buf);
268 ut_assert(!unicode_test_u16_strcmp(buf, c1, SIZE_MAX));
271 utf8_utf16_strcpy(&pos, d2);
272 ut_asserteq(8, pos - buf);
273 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
276 utf8_utf16_strcpy(&pos, d3);
277 ut_asserteq(3, pos - buf);
278 ut_assert(!unicode_test_u16_strcmp(buf, c3, SIZE_MAX));
281 utf8_utf16_strcpy(&pos, d4);
282 ut_asserteq(6, pos - buf);
283 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
285 /* Illegal utf-8 strings */
287 utf8_utf16_strcpy(&pos, j1);
288 ut_asserteq(4, pos - buf);
289 ut_assert(!unicode_test_u16_strcmp(buf, L"j1?l", SIZE_MAX));
292 utf8_utf16_strcpy(&pos, j2);
293 ut_asserteq(4, pos - buf);
294 ut_assert(!unicode_test_u16_strcmp(buf, L"j2?l", SIZE_MAX));
297 utf8_utf16_strcpy(&pos, j3);
298 ut_asserteq(3, pos - buf);
299 ut_assert(!unicode_test_u16_strcmp(buf, L"j3?", SIZE_MAX));
303 UNICODE_TEST(unicode_test_utf8_utf16_strcpy);
305 static int unicode_test_utf8_utf16_strncpy(struct unit_test_state *uts)
311 memset(buf, 0, sizeof(buf));
312 utf8_utf16_strncpy(&pos, d1, 4);
313 ut_asserteq(4, pos - buf);
315 ut_assert(!unicode_test_u16_strcmp(buf, c1, 4));
318 memset(buf, 0, sizeof(buf));
319 utf8_utf16_strncpy(&pos, d2, 10);
320 ut_asserteq(8, pos - buf);
322 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
325 memset(buf, 0, sizeof(buf));
326 utf8_utf16_strncpy(&pos, d3, 2);
327 ut_asserteq(2, pos - buf);
329 ut_assert(!unicode_test_u16_strcmp(buf, c3, 2));
332 memset(buf, 0, sizeof(buf));
333 utf8_utf16_strncpy(&pos, d4, 2);
334 ut_asserteq(4, pos - buf);
336 ut_assert(!unicode_test_u16_strcmp(buf, c4, 4));
339 memset(buf, 0, sizeof(buf));
340 utf8_utf16_strncpy(&pos, d4, 10);
341 ut_asserteq(6, pos - buf);
343 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
347 UNICODE_TEST(unicode_test_utf8_utf16_strncpy);
349 static int unicode_test_utf16_get(struct unit_test_state *uts)
355 /* Check characters less than 0x10000 */
357 for (i = 0; i < 9; ++i) {
358 code = utf16_get((const u16 **)&s);
359 ut_asserteq(c2[i], code);
363 ut_asserteq_ptr(c2 + 8, s);
365 /* Check character greater 0xffff */
367 code = utf16_get((const u16 **)&s);
368 ut_asserteq(0x0001048d, code);
369 ut_asserteq_ptr(c4 + 2, s);
373 UNICODE_TEST(unicode_test_utf16_get);
375 static int unicode_test_utf16_put(struct unit_test_state *uts)
377 u16 buffer[4] = { 0, };
380 /* Commercial at, translates to one word */
382 ut_assert(!utf16_put('@', &pos));
383 ut_asserteq(1, pos - buffer);
384 ut_asserteq((u16)'@', buffer[0]);
385 ut_assert(!buffer[1]);
387 /* Hamster face, translates to two words */
389 ut_assert(!utf16_put(0x1f439, &pos));
390 ut_asserteq(2, pos - buffer);
391 ut_asserteq((u16)0xd83d, buffer[0]);
392 ut_asserteq((u16)0xdc39, buffer[1]);
393 ut_assert(!buffer[2]);
397 ut_asserteq(-1, utf16_put(0xd888, &pos));
401 UNICODE_TEST(unicode_test_utf16_put);
403 static int unicode_test_utf16_strnlen(struct unit_test_state *uts)
405 ut_asserteq(3, utf16_strnlen(c1, 3));
406 ut_asserteq(6, utf16_strnlen(c1, 13));
407 ut_asserteq(6, utf16_strnlen(c2, 6));
408 ut_asserteq(2, utf16_strnlen(c3, 2));
409 ut_asserteq(2, utf16_strnlen(c4, 2));
410 ut_asserteq(3, utf16_strnlen(c4, 3));
412 /* illegal utf-16 word sequences */
413 ut_asserteq(4, utf16_strnlen(i1, 16));
414 ut_asserteq(4, utf16_strnlen(i2, 16));
415 ut_asserteq(3, utf16_strnlen(i3, 16));
419 UNICODE_TEST(unicode_test_utf16_strnlen);
421 static int unicode_test_utf16_utf8_strlen(struct unit_test_state *uts)
423 ut_asserteq(6, utf16_utf8_strlen(c1));
424 ut_asserteq(9, utf16_utf8_strlen(c2));
425 ut_asserteq(9, utf16_utf8_strlen(c3));
426 ut_asserteq(12, utf16_utf8_strlen(c4));
428 /* illegal utf-16 word sequences */
429 ut_asserteq(4, utf16_utf8_strlen(i1));
430 ut_asserteq(4, utf16_utf8_strlen(i2));
431 ut_asserteq(3, utf16_utf8_strlen(i3));
435 UNICODE_TEST(unicode_test_utf16_utf8_strlen);
437 static int unicode_test_utf16_utf8_strnlen(struct unit_test_state *uts)
439 ut_asserteq(3, utf16_utf8_strnlen(c1, 3));
440 ut_asserteq(6, utf16_utf8_strnlen(c1, 13));
441 ut_asserteq(7, utf16_utf8_strnlen(c2, 6));
442 ut_asserteq(6, utf16_utf8_strnlen(c3, 2));
443 ut_asserteq(8, utf16_utf8_strnlen(c4, 2));
444 ut_asserteq(12, utf16_utf8_strnlen(c4, 3));
447 UNICODE_TEST(unicode_test_utf16_utf8_strnlen);
449 static int unicode_test_utf16_utf8_strcpy(struct unit_test_state *uts)
455 utf16_utf8_strcpy(&pos, c1);
456 ut_asserteq(6, pos - buf);
457 ut_asserteq_str(d1, buf);
460 utf16_utf8_strcpy(&pos, c2);
461 ut_asserteq(9, pos - buf);
462 ut_asserteq_str(d2, buf);
465 utf16_utf8_strcpy(&pos, c3);
466 ut_asserteq(9, pos - buf);
467 ut_asserteq_str(d3, buf);
470 utf16_utf8_strcpy(&pos, c4);
471 ut_asserteq(12, pos - buf);
472 ut_asserteq_str(d4, buf);
474 /* Illegal utf-16 strings */
476 utf16_utf8_strcpy(&pos, i1);
477 ut_asserteq(4, pos - buf);
478 ut_asserteq_str("i1?l", buf);
481 utf16_utf8_strcpy(&pos, i2);
482 ut_asserteq(4, pos - buf);
483 ut_asserteq_str("i2?l", buf);
486 utf16_utf8_strcpy(&pos, i3);
487 ut_asserteq(3, pos - buf);
488 ut_asserteq_str("i3?", buf);
492 UNICODE_TEST(unicode_test_utf16_utf8_strcpy);
494 static int unicode_test_utf16_utf8_strncpy(struct unit_test_state *uts)
500 memset(buf, 0, sizeof(buf));
501 utf16_utf8_strncpy(&pos, c1, 4);
502 ut_asserteq(4, pos - buf);
504 ut_assert(!strncmp(buf, d1, 4));
507 memset(buf, 0, sizeof(buf));
508 utf16_utf8_strncpy(&pos, c2, 10);
509 ut_asserteq(9, pos - buf);
511 ut_assert(!strncmp(buf, d2, SIZE_MAX));
514 memset(buf, 0, sizeof(buf));
515 utf16_utf8_strncpy(&pos, c3, 2);
516 ut_asserteq(6, pos - buf);
518 ut_assert(!strncmp(buf, d3, 6));
521 memset(buf, 0, sizeof(buf));
522 utf16_utf8_strncpy(&pos, c4, 2);
523 ut_asserteq(8, pos - buf);
525 ut_assert(!strncmp(buf, d4, 8));
528 memset(buf, 0, sizeof(buf));
529 utf16_utf8_strncpy(&pos, c4, 10);
530 ut_asserteq(12, pos - buf);
532 ut_assert(!strncmp(buf, d4, SIZE_MAX));
536 UNICODE_TEST(unicode_test_utf16_utf8_strncpy);
538 static int unicode_test_utf_to_lower(struct unit_test_state *uts)
540 ut_asserteq('@', utf_to_lower('@'));
541 ut_asserteq('a', utf_to_lower('A'));
542 ut_asserteq('z', utf_to_lower('Z'));
543 ut_asserteq('[', utf_to_lower('['));
544 ut_asserteq('m', utf_to_lower('m'));
545 /* Latin letter O with diaresis (umlaut) */
546 ut_asserteq(0x00f6, utf_to_lower(0x00d6));
547 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
548 /* Cyrillic letter I*/
549 ut_asserteq(0x0438, utf_to_lower(0x0418));
553 UNICODE_TEST(unicode_test_utf_to_lower);
555 static int unicode_test_utf_to_upper(struct unit_test_state *uts)
557 ut_asserteq('`', utf_to_upper('`'));
558 ut_asserteq('A', utf_to_upper('a'));
559 ut_asserteq('Z', utf_to_upper('z'));
560 ut_asserteq('{', utf_to_upper('{'));
561 ut_asserteq('M', utf_to_upper('M'));
562 /* Latin letter O with diaresis (umlaut) */
563 ut_asserteq(0x00d6, utf_to_upper(0x00f6));
564 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
565 /* Cyrillic letter I */
566 ut_asserteq(0x0418, utf_to_upper(0x0438));
570 UNICODE_TEST(unicode_test_utf_to_upper);
572 static int unicode_test_u16_strncmp(struct unit_test_state *uts)
574 ut_assert(u16_strncmp(L"abc", L"abc", 3) == 0);
575 ut_assert(u16_strncmp(L"abcdef", L"abcghi", 3) == 0);
576 ut_assert(u16_strncmp(L"abcdef", L"abcghi", 6) < 0);
577 ut_assert(u16_strncmp(L"abcghi", L"abcdef", 6) > 0);
578 ut_assert(u16_strcmp(L"abc", L"abc") == 0);
579 ut_assert(u16_strcmp(L"abcdef", L"deghi") < 0);
580 ut_assert(u16_strcmp(L"deghi", L"abcdef") > 0);
583 UNICODE_TEST(unicode_test_u16_strncmp);
585 static int unicode_test_u16_strsize(struct unit_test_state *uts)
587 ut_asserteq_64(u16_strsize(c1), 14);
588 ut_asserteq_64(u16_strsize(c2), 18);
589 ut_asserteq_64(u16_strsize(c3), 8);
590 ut_asserteq_64(u16_strsize(c4), 14);
593 UNICODE_TEST(unicode_test_u16_strsize);
595 int do_ut_unicode(struct cmd_tbl *cmdtp, int flag, int argc, char *const argv[])
597 struct unit_test *tests = ll_entry_start(struct unit_test, unicode_test);
598 const int n_ents = ll_entry_count(struct unit_test, unicode_test);
600 return cmd_ut_category("Unicode", "unicode_test_",
601 tests, n_ents, argc, argv);