1 /* GLIB - Library of useful routines for C programming
2 * Copyright (C) 1995-1997 Peter Mattis, Spencer Kimball and Josh MacDonald
4 * This library is free software; you can redistribute it and/or
5 * modify it under the terms of the GNU Lesser General Public
6 * License as published by the Free Software Foundation; either
7 * version 2 of the License, or (at your option) any later version.
9 * This library is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
12 * Lesser General Public License for more details.
14 * You should have received a copy of the GNU Lesser General Public
15 * License along with this library; if not, write to the
16 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
17 * Boston, MA 02111-1307, USA.
21 * Modified by the GLib Team and others 1997-2000. See the AUTHORS
22 * file for a list of people on the GLib Team. See the ChangeLog
23 * files for a list of changes. These files are distributed with
24 * GLib at ftp://ftp.gtk.org/pub/gtk/.
27 #undef G_DISABLE_ASSERT
36 test_iconv_state (void)
38 gchar *in = "\xf4\xe5\xf8\xe5\xed";
39 gchar *expected = "\xd7\xa4\xd7\x95\xd7\xa8\xd7\x95\xd7\x9d";
42 gsize bytes_written = 0;
45 out = g_convert (in, -1, "UTF-8", "CP1255",
46 &bytes_read, &bytes_written, &error);
48 if (error && error->code == G_CONVERT_ERROR_NO_CONVERSION)
49 return; /* silently skip if CP1255 is not supported, see bug 467707 */
51 g_assert_no_error (error);
52 g_assert (bytes_read == 5);
53 g_assert (bytes_written == 10);
54 g_assert (strcmp (out, expected) == 0);
58 /* some tests involving "vulgar fraction one half" */
62 gchar *in = "\xc2\xbd";
65 gsize bytes_written = 0;
68 out = g_convert (in, -1,
69 "ISO-8859-1", "UTF-8",
70 &bytes_read, &bytes_written,
73 g_assert_no_error (error);
74 g_assert (bytes_read == 2);
75 g_assert (bytes_written == 1);
76 g_assert (strcmp (out, "\xbd") == 0);
79 out = g_convert (in, -1,
80 "ISO-8859-15", "UTF-8",
81 &bytes_read, &bytes_written,
84 g_assert_error (error, G_CONVERT_ERROR, G_CONVERT_ERROR_ILLEGAL_SEQUENCE);
85 g_assert (bytes_read == 0);
86 g_assert (bytes_written == 0);
87 g_assert (out == NULL);
88 g_clear_error (&error);
91 out = g_convert_with_fallback (in, -1,
92 "ISO8859-15", "UTF-8",
94 &bytes_read, &bytes_written,
97 g_assert_no_error (error);
98 g_assert (bytes_read == 2);
99 g_assert (bytes_written == 1);
100 g_assert (strcmp (out, "a") == 0);
105 test_byte_order (void)
107 gchar in_be[4] = { 0xfe, 0xff, 0x03, 0x93}; /* capital gamma */
108 gchar in_le[4] = { 0xff, 0xfe, 0x93, 0x03};
109 gchar *expected = "\xce\x93";
111 gsize bytes_read = 0;
112 gsize bytes_written = 0;
113 GError *error = NULL;
115 out = g_convert (in_be, sizeof (in_be),
117 &bytes_read, &bytes_written,
120 g_assert_no_error (error);
121 g_assert (bytes_read == 4);
122 g_assert (bytes_written == 2);
123 g_assert (strcmp (out, expected) == 0);
126 out = g_convert (in_le, sizeof (in_le),
128 &bytes_read, &bytes_written,
131 g_assert_no_error (error);
132 g_assert (bytes_read == 4);
133 g_assert (bytes_written == 2);
134 g_assert (strcmp (out, expected) == 0);
139 check_utf8_to_ucs4 (const char *utf8,
141 const gunichar *ucs4,
145 gunichar *result, *result2, *result3;
146 glong items_read, items_read2;
147 glong items_written, items_written2;
148 GError *error, *error2, *error3;
153 /* check the fast conversion */
154 result = g_utf8_to_ucs4_fast (utf8, utf8_len, &items_written);
156 g_assert (items_written == ucs4_len);
158 for (i = 0; i <= items_written; i++)
159 g_assert (result[i] == ucs4[i]);
165 result = g_utf8_to_ucs4 (utf8, utf8_len, &items_read, &items_written, &error);
167 if (utf8_len == strlen (utf8))
169 /* check that len == -1 yields identical results */
171 result2 = g_utf8_to_ucs4 (utf8, -1, &items_read2, &items_written2, &error2);
172 g_assert (error || items_read2 == items_read);
173 g_assert (error || items_written2 == items_written2);
174 g_assert (!!result == !!result2);
175 g_assert (!!error == !!error2);
177 for (i = 0; i <= items_written; i++)
178 g_assert (result[i] == result2[i]);
182 g_error_free (error2);
186 result3 = g_utf8_to_ucs4 (utf8, utf8_len, NULL, NULL, &error3);
188 if (error3 && error3->code == G_CONVERT_ERROR_PARTIAL_INPUT)
190 g_assert_no_error (error);
191 g_assert (items_read == error_pos);
192 g_assert (items_written == ucs4_len);
194 for (i = 0; i <= items_written; i++)
195 g_assert (result[i] == ucs4[i]);
196 g_error_free (error3);
200 g_assert (error != NULL);
201 g_assert (result == NULL);
202 g_assert (items_read == error_pos);
203 g_error_free (error);
205 g_assert (error3 != NULL);
206 g_assert (result3 == NULL);
207 g_error_free (error3);
211 g_assert_no_error (error);
212 g_assert (items_read == utf8_len);
213 g_assert (items_written == ucs4_len);
215 for (i = 0; i <= items_written; i++)
216 g_assert (result[i] == ucs4[i]);
218 g_assert_no_error (error3);
220 for (i = 0; i <= ucs4_len; i++)
221 g_assert (result3[i] == ucs4[i]);
229 check_ucs4_to_utf8 (const gunichar *ucs4,
235 gchar *result, *result2, *result3;
236 glong items_read, items_read2;
237 glong items_written, items_written2;
238 GError *error, *error2, *error3;
241 result = g_ucs4_to_utf8 (ucs4, ucs4_len, &items_read, &items_written, &error);
243 if (ucs4[ucs4_len] == 0)
245 /* check that len == -1 yields identical results */
247 result2 = g_ucs4_to_utf8 (ucs4, -1, &items_read2, &items_written2, &error2);
249 g_assert (error || items_read2 == items_read);
250 g_assert (error || items_written2 == items_written);
251 g_assert (!!result == !!result2);
252 g_assert (!!error == !!error2);
254 g_assert (strcmp (result, result2) == 0);
258 g_error_free (error2);
262 result3 = g_ucs4_to_utf8 (ucs4, ucs4_len, NULL, NULL, &error3);
266 g_assert (error != NULL);
267 g_assert (result == NULL);
268 g_assert (items_read == error_pos);
269 g_error_free (error);
271 g_assert (error3 != NULL);
272 g_assert (result3 == NULL);
273 g_error_free (error3);
277 g_assert_no_error (error);
278 g_assert (items_read == ucs4_len);
279 g_assert (items_written == utf8_len);
281 g_assert (strcmp (result, utf8) == 0);
283 g_assert_no_error (error3);
285 g_assert (strcmp (result3, utf8) == 0);
293 check_utf8_to_utf16 (const char *utf8,
295 const gunichar2 *utf16,
299 gunichar2 *result, *result2, *result3;
300 glong items_read, items_read2;
301 glong items_written, items_written2;
302 GError *error, *error2, *error3;
306 result = g_utf8_to_utf16 (utf8, utf8_len, &items_read, &items_written, &error);
308 if (utf8_len == strlen (utf8))
310 /* check that len == -1 yields identical results */
312 result2 = g_utf8_to_utf16 (utf8, -1, &items_read2, &items_written2, &error2);
313 g_assert (error || items_read2 == items_read);
314 g_assert (error || items_written2 == items_written2);
315 g_assert (!!result == !!result2);
316 g_assert (!!error == !!error2);
318 for (i = 0; i <= items_written; i++)
319 g_assert (result[i] == result2[i]);
323 g_error_free (error2);
327 result3 = g_utf8_to_utf16 (utf8, utf8_len, NULL, NULL, &error3);
329 if (error3 && error3->code == G_CONVERT_ERROR_PARTIAL_INPUT)
331 g_assert_no_error (error);
332 g_assert (items_read == error_pos);
333 g_assert (items_written == utf16_len);
335 for (i = 0; i <= items_written; i++)
336 g_assert (result[i] == utf16[i]);
337 g_error_free (error3);
341 g_assert (error != NULL);
342 g_assert (result == NULL);
343 g_assert (items_read == error_pos);
344 g_error_free (error);
346 g_assert (error3 != NULL);
347 g_assert (result3 == NULL);
348 g_error_free (error3);
352 g_assert_no_error (error);
353 g_assert (items_read == utf8_len);
354 g_assert (items_written == utf16_len);
356 for (i = 0; i <= items_written; i++)
357 g_assert (result[i] == utf16[i]);
359 g_assert_no_error (error3);
361 for (i = 0; i <= utf16_len; i++)
362 g_assert (result3[i] == utf16[i]);
370 check_utf16_to_utf8 (const gunichar2 *utf16,
376 gchar *result, *result2, *result3;
377 glong items_read, items_read2;
378 glong items_written, items_written2;
379 GError *error, *error2, *error3;
382 result = g_utf16_to_utf8 (utf16, utf16_len, &items_read, &items_written, &error);
383 if (utf16[utf16_len] == 0)
385 /* check that len == -1 yields identical results */
387 result2 = g_utf16_to_utf8 (utf16, -1, &items_read2, &items_written2, &error2);
389 g_assert (error || items_read2 == items_read);
390 g_assert (error || items_written2 == items_written);
391 g_assert (!!result == !!result2);
392 g_assert (!!error == !!error2);
394 g_assert (strcmp (result, result2) == 0);
398 g_error_free (error2);
402 result3 = g_utf16_to_utf8 (utf16, utf16_len, NULL, NULL, &error3);
404 if (error3 && error3->code == G_CONVERT_ERROR_PARTIAL_INPUT)
406 g_assert_no_error (error);
407 g_assert (items_read == error_pos);
408 g_assert (items_read + 1 == utf16_len);
409 g_assert (items_written == utf8_len);
411 g_assert (strcmp (result, utf8) == 0);
412 g_error_free (error3);
416 g_assert (error != NULL);
417 g_assert (result == NULL);
418 g_assert (items_read == error_pos);
419 g_error_free (error);
421 g_assert (error3 != NULL);
422 g_assert (result3 == NULL);
423 g_error_free (error3);
427 g_assert_no_error (error);
428 g_assert (items_read == utf16_len);
429 g_assert (items_written == utf8_len);
431 g_assert (strcmp (result, utf8) == 0);
433 g_assert_no_error (error3);
435 g_assert (strcmp (result3, utf8) == 0);
443 check_ucs4_to_utf16 (const gunichar *ucs4,
445 const gunichar2 *utf16,
449 gunichar2 *result, *result2, *result3;
450 glong items_read, items_read2;
451 glong items_written, items_written2;
452 GError *error, *error2, *error3;
456 result = g_ucs4_to_utf16 (ucs4, ucs4_len, &items_read, &items_written, &error);
458 if (ucs4[ucs4_len] == 0)
460 /* check that len == -1 yields identical results */
462 result2 = g_ucs4_to_utf16 (ucs4, -1, &items_read2, &items_written2, &error2);
464 g_assert (error || items_read2 == items_read);
465 g_assert (error || items_written2 == items_written);
466 g_assert (!!result == !!result2);
467 g_assert (!!error == !!error2);
469 for (i = 0; i <= utf16_len; i++)
470 g_assert (result[i] == result2[i]);
474 g_error_free (error2);
478 result3 = g_ucs4_to_utf16 (ucs4, -1, NULL, NULL, &error3);
482 g_assert (error != NULL);
483 g_assert (result == NULL);
484 g_assert (items_read == error_pos);
485 g_error_free (error);
487 g_assert (error3 != NULL);
488 g_assert (result3 == NULL);
489 g_error_free (error3);
493 g_assert_no_error (error);
494 g_assert (items_read == ucs4_len);
495 g_assert (items_written == utf16_len);
497 for (i = 0; i <= utf16_len; i++)
498 g_assert (result[i] == utf16[i]);
500 g_assert_no_error (error3);
502 for (i = 0; i <= utf16_len; i++)
503 g_assert (result3[i] == utf16[i]);
511 check_utf16_to_ucs4 (const gunichar2 *utf16,
513 const gunichar *ucs4,
517 gunichar *result, *result2, *result3;
518 glong items_read, items_read2;
519 glong items_written, items_written2;
520 GError *error, *error2, *error3;
524 result = g_utf16_to_ucs4 (utf16, utf16_len, &items_read, &items_written, &error);
525 if (utf16[utf16_len] == 0)
527 /* check that len == -1 yields identical results */
529 result2 = g_utf16_to_ucs4 (utf16, -1, &items_read2, &items_written2, &error2);
530 g_assert (error || items_read2 == items_read);
531 g_assert (error || items_written2 == items_written2);
532 g_assert (!!result == !!result2);
533 g_assert (!!error == !!error2);
535 for (i = 0; i <= items_written; i++)
536 g_assert (result[i] == result2[i]);
540 g_error_free (error2);
544 result3 = g_utf16_to_ucs4 (utf16, utf16_len, NULL, NULL, &error3);
546 if (error3 && error3->code == G_CONVERT_ERROR_PARTIAL_INPUT)
548 g_assert_no_error (error);
549 g_assert (items_read == error_pos);
550 g_assert (items_read + 1 == utf16_len);
551 g_assert (items_written == ucs4_len);
553 for (i = 0; i <= items_written; i++)
554 g_assert (result[i] == ucs4[i]);
555 g_error_free (error3);
559 g_assert (error != NULL);
560 g_assert (result == NULL);
561 g_assert (items_read == error_pos);
562 g_error_free (error);
564 g_assert (error3 != NULL);
565 g_assert (result3 == NULL);
566 g_error_free (error3);
570 g_assert_no_error (error);
571 g_assert (items_read == utf16_len);
572 g_assert (items_written == ucs4_len);
574 for (i = 0; i <= ucs4_len; i++)
575 g_assert (result[i] == ucs4[i]);
577 g_assert_no_error (error3);
579 for (i = 0; i <= ucs4_len; i++)
580 g_assert (result3[i] == ucs4[i]);
588 test_unicode_conversions (void)
592 gunichar2 utf16[100];
595 ucs4[0] = 0x61; ucs4[1] = 0x62; ucs4[2] = 0x63; ucs4[3] = 0;
596 utf16[0] = 0x61; utf16[1] = 0x62; utf16[2] = 0x63; utf16[3] = 0;
598 check_utf8_to_ucs4 (utf8, 3, ucs4, 3, 0);
599 check_ucs4_to_utf8 (ucs4, 3, utf8, 3, 0);
600 check_utf8_to_utf16 (utf8, 3, utf16, 3, 0);
601 check_utf16_to_utf8 (utf16, 3, utf8, 3, 0);
602 check_ucs4_to_utf16 (ucs4, 3, utf16, 3, 0);
603 check_utf16_to_ucs4 (utf16, 3, ucs4, 3, 0);
605 utf8 = "\316\261\316\262\316\263";
606 ucs4[0] = 0x03b1; ucs4[1] = 0x03b2; ucs4[2] = 0x03b3; ucs4[3] = 0;
607 utf16[0] = 0x03b1; utf16[1] = 0x03b2; utf16[2] = 0x03b3; utf16[3] = 0;
609 check_utf8_to_ucs4 (utf8, 6, ucs4, 3, 0);
610 check_ucs4_to_utf8 (ucs4, 3, utf8, 6, 0);
611 check_utf8_to_utf16 (utf8, 6, utf16, 3, 0);
612 check_utf16_to_utf8 (utf16, 3, utf8, 6, 0);
613 check_ucs4_to_utf16 (ucs4, 3, utf16, 3, 0);
614 check_utf16_to_ucs4 (utf16, 3, ucs4, 3, 0);
616 /* partial utf8 character */
618 ucs4[0] = 0x61; ucs4[1] = 0x62; ucs4[2] = 0x63; ucs4[3] = 0;
619 utf16[0] = 0x61; utf16[1] = 0x62; utf16[2] = 0x63; utf16[3] = 0;
621 check_utf8_to_ucs4 (utf8, 4, ucs4, 3, 3);
622 check_utf8_to_utf16 (utf8, 4, utf16, 3, 3);
625 utf8 = "abc\316\316";
629 check_utf8_to_ucs4 (utf8, 5, ucs4, 0, 3);
630 check_utf8_to_utf16 (utf8, 5, utf16, 0, 3);
632 /* partial utf16 character */
634 ucs4[0] = 0x61; ucs4[1] = 0x62; ucs4[2] = 0;
635 utf16[0] = 0x61; utf16[1] = 0x62; utf16[2] = 0xd801; utf16[3] = 0;
637 check_utf16_to_utf8 (utf16, 3, utf8, 2, 2);
638 check_utf16_to_ucs4 (utf16, 3, ucs4, 2, 2);
643 utf16[0] = 0x61; utf16[1] = 0x62; utf16[2] = 0xdc01; utf16[3] = 0;
645 check_utf16_to_utf8 (utf16, 3, utf8, 0, 2);
646 check_utf16_to_ucs4 (utf16, 3, ucs4, 0, 2);
650 ucs4[0] = 0x61; ucs4[1] = 0x62; ucs4[2] = 0x80000000; ucs4[3] = 0;
653 check_ucs4_to_utf8 (ucs4, 3, utf8, 0, 2);
654 check_ucs4_to_utf16 (ucs4, 3, utf16, 0, 2);
658 test_filename_utf8 (void)
660 const gchar *filename = "/my/path/to/foo";
666 utf8 = g_filename_to_utf8 (filename, -1, NULL, NULL, &error);
667 g_assert_no_error (error);
668 back = g_filename_from_utf8 (utf8, -1, NULL, NULL, &error);
669 g_assert_no_error (error);
670 g_assert_cmpstr (back, ==, filename);
677 test_filename_display (void)
679 const gchar *filename = "/my/path/to/foo";
682 display = g_filename_display_basename (filename);
683 g_assert_cmpstr (display, ==, "foo");
689 main (int argc, char *argv[])
691 g_test_init (&argc, &argv, NULL);
693 g_test_add_func ("/conversion/iconv-state", test_iconv_state);
694 g_test_add_func ("/conversion/illegal-sequence", test_one_half);
695 g_test_add_func ("/conversion/byte-order", test_byte_order);
696 g_test_add_func ("/conversion/unicode", test_unicode_conversions);
697 g_test_add_func ("/conversion/filename-utf8", test_filename_utf8);
698 g_test_add_func ("/conversion/filename-display", test_filename_display);
700 return g_test_run ();