1 // SPDX-License-Identifier: GPL-2.0+
3 * Unit tests for Unicode functions
5 * Copyright (c) 2018 Heinrich Schuchardt <xypron.glpk@gmx.de>
12 #include <test/test.h>
13 #include <test/suites.h>
16 /* Linker list entry for a Unicode test */
17 #define UNICODE_TEST(_name) UNIT_TEST(_name, 0, unicode_test)
19 /* Constants c1-c4 and d1-d4 encode the same letters */
21 /* Six characters translating to one utf-8 byte each. */
22 static const u16 c1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
23 /* One character translating to two utf-8 bytes */
24 static const u16 c2[] = {0x6b, 0x61, 0x66, 0x62, 0xe1, 0x74, 0x75, 0x72, 0x00};
25 /* Three characters translating to three utf-8 bytes each */
26 static const u16 c3[] = {0x6f5c, 0x6c34, 0x8266, 0x00};
27 /* Three letters translating to four utf-8 bytes each */
28 static const u16 c4[] = {0xd801, 0xdc8d, 0xd801, 0xdc96, 0xd801, 0xdc87,
31 /* Illegal utf-16 strings */
32 static const u16 i1[] = {0x69, 0x31, 0xdc87, 0x6c, 0x00};
33 static const u16 i2[] = {0x69, 0x32, 0xd801, 0xd801, 0x6c, 0x00};
34 static const u16 i3[] = {0x69, 0x33, 0xd801, 0x00};
36 /* Six characters translating to one utf-16 word each. */
37 static const char d1[] = {0x55, 0x2d, 0x42, 0x6f, 0x6f, 0x74, 0x00};
38 /* Eight characters translating to one utf-16 word each */
39 static const char d2[] = {0x6b, 0x61, 0x66, 0x62, 0xc3, 0xa1, 0x74, 0x75,
41 /* Three characters translating to one utf-16 word each */
42 static const char d3[] = {0xe6, 0xbd, 0x9c, 0xe6, 0xb0, 0xb4, 0xe8, 0x89,
44 /* Three letters translating to two utf-16 word each */
45 static const char d4[] = {0xf0, 0x90, 0x92, 0x8d, 0xf0, 0x90, 0x92, 0x96,
46 0xf0, 0x90, 0x92, 0x87, 0x00};
48 /* Illegal utf-8 strings */
49 static const char j1[] = {0x6a, 0x31, 0xa1, 0x6c, 0x00};
50 static const char j2[] = {0x6a, 0x32, 0xc3, 0xc3, 0x6c, 0x00};
51 static const char j3[] = {0x6a, 0x33, 0xf0, 0x90, 0xf0, 0x00};
53 static int unicode_test_u16_strlen(struct unit_test_state *uts)
55 ut_asserteq(6, u16_strlen(c1));
56 ut_asserteq(8, u16_strlen(c2));
57 ut_asserteq(3, u16_strlen(c3));
58 ut_asserteq(6, u16_strlen(c4));
61 UNICODE_TEST(unicode_test_u16_strlen);
63 static int unicode_test_u16_strdup(struct unit_test_state *uts)
65 u16 *copy = u16_strdup(c4);
67 ut_assert(copy != c4);
68 ut_assert(!memcmp(copy, c4, sizeof(c4)));
72 UNICODE_TEST(unicode_test_u16_strdup);
74 static int unicode_test_u16_strcpy(struct unit_test_state *uts)
79 r = u16_strcpy(copy, c1);
81 ut_assert(!memcmp(copy, c1, sizeof(c1)));
84 UNICODE_TEST(unicode_test_u16_strcpy);
86 /* U-Boot uses UTF-16 strings in the EFI context only. */
87 #if CONFIG_IS_ENABLED(EFI_LOADER) && !defined(API_BUILD)
88 static int unicode_test_string16(struct unit_test_state *uts)
92 /* Test length and precision */
93 memset(buf, 0xff, sizeof(buf));
94 sprintf(buf, "%8.6ls", c2);
95 ut_asserteq(' ', buf[1]);
96 ut_assert(!strncmp(&buf[2], d2, 7));
99 memset(buf, 0xff, sizeof(buf));
100 sprintf(buf, "%8.6ls", c4);
101 ut_asserteq(' ', buf[4]);
102 ut_assert(!strncmp(&buf[5], d4, 12));
105 memset(buf, 0xff, sizeof(buf));
106 sprintf(buf, "%-8.2ls", c4);
107 ut_asserteq(' ', buf[8]);
108 ut_assert(!strncmp(buf, d4, 8));
111 /* Test handling of illegal utf-16 sequences */
112 memset(buf, 0xff, sizeof(buf));
113 sprintf(buf, "%ls", i1);
114 ut_asserteq_str("i1?l", buf);
116 memset(buf, 0xff, sizeof(buf));
117 sprintf(buf, "%ls", i2);
118 ut_asserteq_str("i2?l", buf);
120 memset(buf, 0xff, sizeof(buf));
121 sprintf(buf, "%ls", i3);
122 ut_asserteq_str("i3?", buf);
126 UNICODE_TEST(unicode_test_string16);
129 static int unicode_test_utf8_get(struct unit_test_state *uts)
135 /* Check characters less than 0x800 */
137 for (i = 0; i < 8; ++i) {
138 code = utf8_get((const char **)&s);
139 /* c2 is the utf-8 encoding of d2 */
140 ut_asserteq(c2[i], code);
144 ut_asserteq_ptr(s, d2 + 9)
146 /* Check characters less than 0x10000 */
148 for (i = 0; i < 4; ++i) {
149 code = utf8_get((const char **)&s);
150 /* c3 is the utf-8 encoding of d3 */
151 ut_asserteq(c3[i], code);
155 ut_asserteq_ptr(s, d3 + 9)
157 /* Check character greater 0xffff */
159 code = utf8_get((const char **)&s);
160 ut_asserteq(0x0001048d, code);
161 ut_asserteq_ptr(s, d4 + 4);
165 UNICODE_TEST(unicode_test_utf8_get);
167 static int unicode_test_utf8_put(struct unit_test_state *uts)
169 char buffer[8] = { 0, };
172 /* Commercial at, translates to one character */
174 ut_assert(!utf8_put('@', &pos))
175 ut_asserteq(1, pos - buffer);
176 ut_asserteq('@', buffer[0]);
177 ut_assert(!buffer[1]);
179 /* Latin letter G with acute, translates to two charactes */
181 ut_assert(!utf8_put(0x1f4, &pos));
182 ut_asserteq(2, pos - buffer);
183 ut_asserteq_str("\xc7\xb4", buffer);
185 /* Tagalog letter i, translates to three characters */
187 ut_assert(!utf8_put(0x1701, &pos));
188 ut_asserteq(3, pos - buffer);
189 ut_asserteq_str("\xe1\x9c\x81", buffer);
191 /* Hamster face, translates to four characters */
193 ut_assert(!utf8_put(0x1f439, &pos));
194 ut_asserteq(4, pos - buffer);
195 ut_asserteq_str("\xf0\x9f\x90\xb9", buffer);
199 ut_asserteq(-1, utf8_put(0xd888, &pos));
203 UNICODE_TEST(unicode_test_utf8_put);
205 static int unicode_test_utf8_utf16_strlen(struct unit_test_state *uts)
207 ut_asserteq(6, utf8_utf16_strlen(d1));
208 ut_asserteq(8, utf8_utf16_strlen(d2));
209 ut_asserteq(3, utf8_utf16_strlen(d3));
210 ut_asserteq(6, utf8_utf16_strlen(d4));
212 /* illegal utf-8 sequences */
213 ut_asserteq(4, utf8_utf16_strlen(j1));
214 ut_asserteq(4, utf8_utf16_strlen(j2));
215 ut_asserteq(3, utf8_utf16_strlen(j3));
219 UNICODE_TEST(unicode_test_utf8_utf16_strlen);
221 static int unicode_test_utf8_utf16_strnlen(struct unit_test_state *uts)
223 ut_asserteq(3, utf8_utf16_strnlen(d1, 3));
224 ut_asserteq(6, utf8_utf16_strnlen(d1, 13));
225 ut_asserteq(6, utf8_utf16_strnlen(d2, 6));
226 ut_asserteq(2, utf8_utf16_strnlen(d3, 2));
227 ut_asserteq(4, utf8_utf16_strnlen(d4, 2));
228 ut_asserteq(6, utf8_utf16_strnlen(d4, 3));
230 /* illegal utf-8 sequences */
231 ut_asserteq(4, utf8_utf16_strnlen(j1, 16));
232 ut_asserteq(4, utf8_utf16_strnlen(j2, 16));
233 ut_asserteq(3, utf8_utf16_strnlen(j3, 16));
237 UNICODE_TEST(unicode_test_utf8_utf16_strnlen);
240 * ut_u16_strcmp() - Compare to u16 strings.
244 * @count: number of u16 to compare
245 * Return: -1 if a1 < a2, 0 if a1 == a2, 1 if a1 > a2
247 static int unicode_test_u16_strcmp(const u16 *a1, const u16 *a2, size_t count)
249 for (; (*a1 || *a2) && count; ++a1, ++a2, --count) {
258 static int unicode_test_utf8_utf16_strcpy(struct unit_test_state *uts)
264 utf8_utf16_strcpy(&pos, d1);
265 ut_asserteq(6, pos - buf);
266 ut_assert(!unicode_test_u16_strcmp(buf, c1, SIZE_MAX));
269 utf8_utf16_strcpy(&pos, d2);
270 ut_asserteq(8, pos - buf);
271 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
274 utf8_utf16_strcpy(&pos, d3);
275 ut_asserteq(3, pos - buf);
276 ut_assert(!unicode_test_u16_strcmp(buf, c3, SIZE_MAX));
279 utf8_utf16_strcpy(&pos, d4);
280 ut_asserteq(6, pos - buf);
281 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
283 /* Illegal utf-8 strings */
285 utf8_utf16_strcpy(&pos, j1);
286 ut_asserteq(4, pos - buf);
287 ut_assert(!unicode_test_u16_strcmp(buf, L"j1?l", SIZE_MAX));
290 utf8_utf16_strcpy(&pos, j2);
291 ut_asserteq(4, pos - buf);
292 ut_assert(!unicode_test_u16_strcmp(buf, L"j2?l", SIZE_MAX));
295 utf8_utf16_strcpy(&pos, j3);
296 ut_asserteq(3, pos - buf);
297 ut_assert(!unicode_test_u16_strcmp(buf, L"j3?", SIZE_MAX));
301 UNICODE_TEST(unicode_test_utf8_utf16_strcpy);
303 static int unicode_test_utf8_utf16_strncpy(struct unit_test_state *uts)
309 memset(buf, 0, sizeof(buf));
310 utf8_utf16_strncpy(&pos, d1, 4);
311 ut_asserteq(4, pos - buf);
313 ut_assert(!unicode_test_u16_strcmp(buf, c1, 4));
316 memset(buf, 0, sizeof(buf));
317 utf8_utf16_strncpy(&pos, d2, 10);
318 ut_asserteq(8, pos - buf);
320 ut_assert(!unicode_test_u16_strcmp(buf, c2, SIZE_MAX));
323 memset(buf, 0, sizeof(buf));
324 utf8_utf16_strncpy(&pos, d3, 2);
325 ut_asserteq(2, pos - buf);
327 ut_assert(!unicode_test_u16_strcmp(buf, c3, 2));
330 memset(buf, 0, sizeof(buf));
331 utf8_utf16_strncpy(&pos, d4, 2);
332 ut_asserteq(4, pos - buf);
334 ut_assert(!unicode_test_u16_strcmp(buf, c4, 4));
337 memset(buf, 0, sizeof(buf));
338 utf8_utf16_strncpy(&pos, d4, 10);
339 ut_asserteq(6, pos - buf);
341 ut_assert(!unicode_test_u16_strcmp(buf, c4, SIZE_MAX));
345 UNICODE_TEST(unicode_test_utf8_utf16_strncpy);
347 static int unicode_test_utf16_get(struct unit_test_state *uts)
353 /* Check characters less than 0x10000 */
355 for (i = 0; i < 9; ++i) {
356 code = utf16_get((const u16 **)&s);
357 ut_asserteq(c2[i], code);
361 ut_asserteq_ptr(c2 + 8, s);
363 /* Check character greater 0xffff */
365 code = utf16_get((const u16 **)&s);
366 ut_asserteq(0x0001048d, code);
367 ut_asserteq_ptr(c4 + 2, s);
371 UNICODE_TEST(unicode_test_utf16_get);
373 static int unicode_test_utf16_put(struct unit_test_state *uts)
375 u16 buffer[4] = { 0, };
378 /* Commercial at, translates to one word */
380 ut_assert(!utf16_put('@', &pos));
381 ut_asserteq(1, pos - buffer);
382 ut_asserteq((u16)'@', buffer[0]);
383 ut_assert(!buffer[1]);
385 /* Hamster face, translates to two words */
387 ut_assert(!utf16_put(0x1f439, &pos));
388 ut_asserteq(2, pos - buffer);
389 ut_asserteq((u16)0xd83d, buffer[0]);
390 ut_asserteq((u16)0xdc39, buffer[1]);
391 ut_assert(!buffer[2]);
395 ut_asserteq(-1, utf16_put(0xd888, &pos));
399 UNICODE_TEST(unicode_test_utf16_put);
401 static int unicode_test_utf16_strnlen(struct unit_test_state *uts)
403 ut_asserteq(3, utf16_strnlen(c1, 3));
404 ut_asserteq(6, utf16_strnlen(c1, 13));
405 ut_asserteq(6, utf16_strnlen(c2, 6));
406 ut_asserteq(2, utf16_strnlen(c3, 2));
407 ut_asserteq(2, utf16_strnlen(c4, 2));
408 ut_asserteq(3, utf16_strnlen(c4, 3));
410 /* illegal utf-16 word sequences */
411 ut_asserteq(4, utf16_strnlen(i1, 16));
412 ut_asserteq(4, utf16_strnlen(i2, 16));
413 ut_asserteq(3, utf16_strnlen(i3, 16));
417 UNICODE_TEST(unicode_test_utf16_strnlen);
419 static int unicode_test_utf16_utf8_strlen(struct unit_test_state *uts)
421 ut_asserteq(6, utf16_utf8_strlen(c1));
422 ut_asserteq(9, utf16_utf8_strlen(c2));
423 ut_asserteq(9, utf16_utf8_strlen(c3));
424 ut_asserteq(12, utf16_utf8_strlen(c4));
426 /* illegal utf-16 word sequences */
427 ut_asserteq(4, utf16_utf8_strlen(i1));
428 ut_asserteq(4, utf16_utf8_strlen(i2));
429 ut_asserteq(3, utf16_utf8_strlen(i3));
433 UNICODE_TEST(unicode_test_utf16_utf8_strlen);
435 static int unicode_test_utf16_utf8_strnlen(struct unit_test_state *uts)
437 ut_asserteq(3, utf16_utf8_strnlen(c1, 3));
438 ut_asserteq(6, utf16_utf8_strnlen(c1, 13));
439 ut_asserteq(7, utf16_utf8_strnlen(c2, 6));
440 ut_asserteq(6, utf16_utf8_strnlen(c3, 2));
441 ut_asserteq(8, utf16_utf8_strnlen(c4, 2));
442 ut_asserteq(12, utf16_utf8_strnlen(c4, 3));
445 UNICODE_TEST(unicode_test_utf16_utf8_strnlen);
447 static int unicode_test_utf16_utf8_strcpy(struct unit_test_state *uts)
453 utf16_utf8_strcpy(&pos, c1);
454 ut_asserteq(6, pos - buf);
455 ut_asserteq_str(d1, buf);
458 utf16_utf8_strcpy(&pos, c2);
459 ut_asserteq(9, pos - buf);
460 ut_asserteq_str(d2, buf);
463 utf16_utf8_strcpy(&pos, c3);
464 ut_asserteq(9, pos - buf);
465 ut_asserteq_str(d3, buf);
468 utf16_utf8_strcpy(&pos, c4);
469 ut_asserteq(12, pos - buf);
470 ut_asserteq_str(d4, buf);
472 /* Illegal utf-16 strings */
474 utf16_utf8_strcpy(&pos, i1);
475 ut_asserteq(4, pos - buf);
476 ut_asserteq_str("i1?l", buf);
479 utf16_utf8_strcpy(&pos, i2);
480 ut_asserteq(4, pos - buf);
481 ut_asserteq_str("i2?l", buf);
484 utf16_utf8_strcpy(&pos, i3);
485 ut_asserteq(3, pos - buf);
486 ut_asserteq_str("i3?", buf);
490 UNICODE_TEST(unicode_test_utf16_utf8_strcpy);
492 static int unicode_test_utf16_utf8_strncpy(struct unit_test_state *uts)
498 memset(buf, 0, sizeof(buf));
499 utf16_utf8_strncpy(&pos, c1, 4);
500 ut_asserteq(4, pos - buf);
502 ut_assert(!strncmp(buf, d1, 4));
505 memset(buf, 0, sizeof(buf));
506 utf16_utf8_strncpy(&pos, c2, 10);
507 ut_asserteq(9, pos - buf);
509 ut_assert(!strncmp(buf, d2, SIZE_MAX));
512 memset(buf, 0, sizeof(buf));
513 utf16_utf8_strncpy(&pos, c3, 2);
514 ut_asserteq(6, pos - buf);
516 ut_assert(!strncmp(buf, d3, 6));
519 memset(buf, 0, sizeof(buf));
520 utf16_utf8_strncpy(&pos, c4, 2);
521 ut_asserteq(8, pos - buf);
523 ut_assert(!strncmp(buf, d4, 8));
526 memset(buf, 0, sizeof(buf));
527 utf16_utf8_strncpy(&pos, c4, 10);
528 ut_asserteq(12, pos - buf);
530 ut_assert(!strncmp(buf, d4, SIZE_MAX));
534 UNICODE_TEST(unicode_test_utf16_utf8_strncpy);
536 static int unicode_test_utf_to_lower(struct unit_test_state *uts)
538 ut_asserteq('@', utf_to_lower('@'));
539 ut_asserteq('a', utf_to_lower('A'));
540 ut_asserteq('z', utf_to_lower('Z'));
541 ut_asserteq('[', utf_to_lower('['));
542 ut_asserteq('m', utf_to_lower('m'));
543 /* Latin letter O with diaresis (umlaut) */
544 ut_asserteq(0x00f6, utf_to_lower(0x00d6));
545 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
546 /* Cyrillic letter I*/
547 ut_asserteq(0x0438, utf_to_lower(0x0418));
551 UNICODE_TEST(unicode_test_utf_to_lower);
553 static int unicode_test_utf_to_upper(struct unit_test_state *uts)
555 ut_asserteq('`', utf_to_upper('`'));
556 ut_asserteq('A', utf_to_upper('a'));
557 ut_asserteq('Z', utf_to_upper('z'));
558 ut_asserteq('{', utf_to_upper('{'));
559 ut_asserteq('M', utf_to_upper('M'));
560 /* Latin letter O with diaresis (umlaut) */
561 ut_asserteq(0x00d6, utf_to_upper(0x00f6));
562 #ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
563 /* Cyrillic letter I */
564 ut_asserteq(0x0418, utf_to_upper(0x0438));
568 UNICODE_TEST(unicode_test_utf_to_upper);
570 int do_ut_unicode(cmd_tbl_t *cmdtp, int flag, int argc, char * const argv[])
572 struct unit_test *tests = ll_entry_start(struct unit_test, unicode_test);
573 const int n_ents = ll_entry_count(struct unit_test, unicode_test);
575 return cmd_ut_category("Unicode", tests, n_ents, argc, argv);