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
]);
199 g_assert (error
!= NULL
);
200 g_assert (result
== NULL
);
201 g_assert (items_read
== error_pos
);
202 g_error_free (error
);
204 g_assert (error3
!= NULL
);
205 g_assert (result3
== NULL
);
206 g_error_free (error3
);
210 g_assert_no_error (error
);
211 g_assert (items_read
== utf8_len
);
212 g_assert (items_written
== ucs4_len
);
214 for (i
= 0; i
<= items_written
; i
++)
215 g_assert (result
[i
] == ucs4
[i
]);
217 g_assert_no_error (error3
);
219 for (i
= 0; i
<= ucs4_len
; i
++)
220 g_assert (result3
[i
] == ucs4
[i
]);
228 check_ucs4_to_utf8 (const gunichar
*ucs4
,
234 gchar
*result
, *result2
, *result3
;
235 glong items_read
, items_read2
;
236 glong items_written
, items_written2
;
237 GError
*error
, *error2
, *error3
;
240 result
= g_ucs4_to_utf8 (ucs4
, ucs4_len
, &items_read
, &items_written
, &error
);
242 if (ucs4
[ucs4_len
] == 0)
244 /* check that len == -1 yields identical results */
246 result2
= g_ucs4_to_utf8 (ucs4
, -1, &items_read2
, &items_written2
, &error2
);
248 g_assert (error
|| items_read2
== items_read
);
249 g_assert (error
|| items_written2
== items_written
);
250 g_assert (!!result
== !!result2
);
251 g_assert (!!error
== !!error2
);
253 g_assert (strcmp (result
, result2
) == 0);
257 g_error_free (error2
);
261 result3
= g_ucs4_to_utf8 (ucs4
, ucs4_len
, NULL
, NULL
, &error3
);
265 g_assert (error
!= NULL
);
266 g_assert (result
== NULL
);
267 g_assert (items_read
== error_pos
);
268 g_error_free (error
);
270 g_assert (error3
!= NULL
);
271 g_assert (result3
== NULL
);
272 g_error_free (error3
);
276 g_assert_no_error (error
);
277 g_assert (items_read
== ucs4_len
);
278 g_assert (items_written
== utf8_len
);
280 g_assert (strcmp (result
, utf8
) == 0);
282 g_assert_no_error (error3
);
284 g_assert (strcmp (result3
, utf8
) == 0);
292 check_utf8_to_utf16 (const char *utf8
,
294 const gunichar2
*utf16
,
298 gunichar2
*result
, *result2
, *result3
;
299 glong items_read
, items_read2
;
300 glong items_written
, items_written2
;
301 GError
*error
, *error2
, *error3
;
305 result
= g_utf8_to_utf16 (utf8
, utf8_len
, &items_read
, &items_written
, &error
);
307 if (utf8_len
== strlen (utf8
))
309 /* check that len == -1 yields identical results */
311 result2
= g_utf8_to_utf16 (utf8
, -1, &items_read2
, &items_written2
, &error2
);
312 g_assert (error
|| items_read2
== items_read
);
313 g_assert (error
|| items_written2
== items_written2
);
314 g_assert (!!result
== !!result2
);
315 g_assert (!!error
== !!error2
);
317 for (i
= 0; i
<= items_written
; i
++)
318 g_assert (result
[i
] == result2
[i
]);
322 g_error_free (error2
);
326 result3
= g_utf8_to_utf16 (utf8
, utf8_len
, NULL
, NULL
, &error3
);
328 if (error3
&& error3
->code
== G_CONVERT_ERROR_PARTIAL_INPUT
)
330 g_assert_no_error (error
);
331 g_assert (items_read
== error_pos
);
332 g_assert (items_written
== utf16_len
);
334 for (i
= 0; i
<= items_written
; i
++)
335 g_assert (result
[i
] == utf16
[i
]);
339 g_assert (error
!= NULL
);
340 g_assert (result
== NULL
);
341 g_assert (items_read
== error_pos
);
342 g_error_free (error
);
344 g_assert (error3
!= NULL
);
345 g_assert (result3
== NULL
);
346 g_error_free (error3
);
350 g_assert_no_error (error
);
351 g_assert (items_read
== utf8_len
);
352 g_assert (items_written
== utf16_len
);
354 for (i
= 0; i
<= items_written
; i
++)
355 g_assert (result
[i
] == utf16
[i
]);
357 g_assert_no_error (error3
);
359 for (i
= 0; i
<= utf16_len
; i
++)
360 g_assert (result3
[i
] == utf16
[i
]);
368 check_utf16_to_utf8 (const gunichar2
*utf16
,
374 gchar
*result
, *result2
, *result3
;
375 glong items_read
, items_read2
;
376 glong items_written
, items_written2
;
377 GError
*error
, *error2
, *error3
;
380 result
= g_utf16_to_utf8 (utf16
, utf16_len
, &items_read
, &items_written
, &error
);
381 if (utf16
[utf16_len
] == 0)
383 /* check that len == -1 yields identical results */
385 result2
= g_utf16_to_utf8 (utf16
, -1, &items_read2
, &items_written2
, &error2
);
387 g_assert (error
|| items_read2
== items_read
);
388 g_assert (error
|| items_written2
== items_written
);
389 g_assert (!!result
== !!result2
);
390 g_assert (!!error
== !!error2
);
392 g_assert (strcmp (result
, result2
) == 0);
396 g_error_free (error2
);
400 result3
= g_utf16_to_utf8 (utf16
, utf16_len
, NULL
, NULL
, &error3
);
402 if (error3
&& error3
->code
== G_CONVERT_ERROR_PARTIAL_INPUT
)
404 g_assert_no_error (error
);
405 g_assert (items_read
== error_pos
);
406 g_assert (items_read
+ 1 == utf16_len
);
407 g_assert (items_written
== utf8_len
);
409 g_assert (strcmp (result
, utf8
) == 0);
413 g_assert (error
!= NULL
);
414 g_assert (result
== NULL
);
415 g_assert (items_read
== error_pos
);
416 g_error_free (error
);
418 g_assert (error3
!= NULL
);
419 g_assert (result3
== NULL
);
420 g_error_free (error3
);
424 g_assert_no_error (error
);
425 g_assert (items_read
== utf16_len
);
426 g_assert (items_written
== utf8_len
);
428 g_assert (strcmp (result
, utf8
) == 0);
430 g_assert_no_error (error3
);
432 g_assert (strcmp (result3
, utf8
) == 0);
440 check_ucs4_to_utf16 (const gunichar
*ucs4
,
442 const gunichar2
*utf16
,
446 gunichar2
*result
, *result2
, *result3
;
447 glong items_read
, items_read2
;
448 glong items_written
, items_written2
;
449 GError
*error
, *error2
, *error3
;
453 result
= g_ucs4_to_utf16 (ucs4
, ucs4_len
, &items_read
, &items_written
, &error
);
455 if (ucs4
[ucs4_len
] == 0)
457 /* check that len == -1 yields identical results */
459 result2
= g_ucs4_to_utf16 (ucs4
, -1, &items_read2
, &items_written2
, &error2
);
461 g_assert (error
|| items_read2
== items_read
);
462 g_assert (error
|| items_written2
== items_written
);
463 g_assert (!!result
== !!result2
);
464 g_assert (!!error
== !!error2
);
466 for (i
= 0; i
<= utf16_len
; i
++)
467 g_assert (result
[i
] == result2
[i
]);
471 g_error_free (error2
);
475 result3
= g_ucs4_to_utf16 (ucs4
, -1, NULL
, NULL
, &error3
);
479 g_assert (error
!= NULL
);
480 g_assert (result
== NULL
);
481 g_assert (items_read
== error_pos
);
482 g_error_free (error
);
484 g_assert (error3
!= NULL
);
485 g_assert (result3
== NULL
);
486 g_error_free (error3
);
490 g_assert_no_error (error
);
491 g_assert (items_read
== ucs4_len
);
492 g_assert (items_written
== utf16_len
);
494 for (i
= 0; i
<= utf16_len
; i
++)
495 g_assert (result
[i
] == utf16
[i
]);
497 g_assert_no_error (error3
);
499 for (i
= 0; i
<= utf16_len
; i
++)
500 g_assert (result3
[i
] == utf16
[i
]);
508 check_utf16_to_ucs4 (const gunichar2
*utf16
,
510 const gunichar
*ucs4
,
514 gunichar
*result
, *result2
, *result3
;
515 glong items_read
, items_read2
;
516 glong items_written
, items_written2
;
517 GError
*error
, *error2
, *error3
;
521 result
= g_utf16_to_ucs4 (utf16
, utf16_len
, &items_read
, &items_written
, &error
);
522 if (utf16
[utf16_len
] == 0)
524 /* check that len == -1 yields identical results */
526 result2
= g_utf16_to_ucs4 (utf16
, -1, &items_read2
, &items_written2
, &error2
);
527 g_assert (error
|| items_read2
== items_read
);
528 g_assert (error
|| items_written2
== items_written2
);
529 g_assert (!!result
== !!result2
);
530 g_assert (!!error
== !!error2
);
532 for (i
= 0; i
<= items_written
; i
++)
533 g_assert (result
[i
] == result2
[i
]);
537 g_error_free (error2
);
541 result3
= g_utf16_to_ucs4 (utf16
, utf16_len
, NULL
, NULL
, &error3
);
543 if (error3
&& error3
->code
== G_CONVERT_ERROR_PARTIAL_INPUT
)
545 g_assert_no_error (error
);
546 g_assert (items_read
== error_pos
);
547 g_assert (items_read
+ 1 == utf16_len
);
548 g_assert (items_written
== ucs4_len
);
550 for (i
= 0; i
<= items_written
; i
++)
551 g_assert (result
[i
] == ucs4
[i
]);
555 g_assert (error
!= NULL
);
556 g_assert (result
== NULL
);
557 g_assert (items_read
== error_pos
);
558 g_error_free (error
);
560 g_assert (error3
!= NULL
);
561 g_assert (result3
== NULL
);
562 g_error_free (error3
);
566 g_assert_no_error (error
);
567 g_assert (items_read
== utf16_len
);
568 g_assert (items_written
== ucs4_len
);
570 for (i
= 0; i
<= ucs4_len
; i
++)
571 g_assert (result
[i
] == ucs4
[i
]);
573 g_assert_no_error (error3
);
575 for (i
= 0; i
<= ucs4_len
; i
++)
576 g_assert (result3
[i
] == ucs4
[i
]);
584 test_unicode_conversions (void)
588 gunichar2 utf16
[100];
591 ucs4
[0] = 0x61; ucs4
[1] = 0x62; ucs4
[2] = 0x63; ucs4
[3] = 0;
592 utf16
[0] = 0x61; utf16
[1] = 0x62; utf16
[2] = 0x63; utf16
[3] = 0;
594 check_utf8_to_ucs4 (utf8
, 3, ucs4
, 3, 0);
595 check_ucs4_to_utf8 (ucs4
, 3, utf8
, 3, 0);
596 check_utf8_to_utf16 (utf8
, 3, utf16
, 3, 0);
597 check_utf16_to_utf8 (utf16
, 3, utf8
, 3, 0);
598 check_ucs4_to_utf16 (ucs4
, 3, utf16
, 3, 0);
599 check_utf16_to_ucs4 (utf16
, 3, ucs4
, 3, 0);
601 utf8
= "\316\261\316\262\316\263";
602 ucs4
[0] = 0x03b1; ucs4
[1] = 0x03b2; ucs4
[2] = 0x03b3; ucs4
[3] = 0;
603 utf16
[0] = 0x03b1; utf16
[1] = 0x03b2; utf16
[2] = 0x03b3; utf16
[3] = 0;
605 check_utf8_to_ucs4 (utf8
, 6, ucs4
, 3, 0);
606 check_ucs4_to_utf8 (ucs4
, 3, utf8
, 6, 0);
607 check_utf8_to_utf16 (utf8
, 6, utf16
, 3, 0);
608 check_utf16_to_utf8 (utf16
, 3, utf8
, 6, 0);
609 check_ucs4_to_utf16 (ucs4
, 3, utf16
, 3, 0);
610 check_utf16_to_ucs4 (utf16
, 3, ucs4
, 3, 0);
612 /* partial utf8 character */
614 ucs4
[0] = 0x61; ucs4
[1] = 0x62; ucs4
[2] = 0x63; ucs4
[3] = 0;
615 utf16
[0] = 0x61; utf16
[1] = 0x62; utf16
[2] = 0x63; utf16
[3] = 0;
617 check_utf8_to_ucs4 (utf8
, 4, ucs4
, 3, 3);
618 check_utf8_to_utf16 (utf8
, 4, utf16
, 3, 3);
621 utf8
= "abc\316\316";
625 check_utf8_to_ucs4 (utf8
, 5, ucs4
, 0, 3);
626 check_utf8_to_utf16 (utf8
, 5, utf16
, 0, 3);
628 /* partial utf16 character */
630 ucs4
[0] = 0x61; ucs4
[1] = 0x62; ucs4
[2] = 0;
631 utf16
[0] = 0x61; utf16
[1] = 0x62; utf16
[2] = 0xd801; utf16
[3] = 0;
633 check_utf16_to_utf8 (utf16
, 3, utf8
, 2, 2);
634 check_utf16_to_ucs4 (utf16
, 3, ucs4
, 2, 2);
639 utf16
[0] = 0x61; utf16
[1] = 0x62; utf16
[2] = 0xdc01; utf16
[3] = 0;
641 check_utf16_to_utf8 (utf16
, 3, utf8
, 0, 2);
642 check_utf16_to_ucs4 (utf16
, 3, ucs4
, 0, 2);
646 ucs4
[0] = 0x61; ucs4
[1] = 0x62; ucs4
[2] = 0x80000000; ucs4
[3] = 0;
649 check_ucs4_to_utf8 (ucs4
, 3, utf8
, 0, 2);
650 check_ucs4_to_utf16 (ucs4
, 3, utf16
, 0, 2);
654 main (int argc
, char *argv
[])
659 test_unicode_conversions ();