2 * Copyright IBM, Corp. 2009
3 * Copyright (c) 2013, 2015 Red Hat Inc.
6 * Anthony Liguori <aliguori@us.ibm.com>
7 * Markus Armbruster <armbru@redhat.com>
9 * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
10 * See the COPYING.LIB file in the top-level directory.
14 #include "qemu/osdep.h"
16 #include "qapi/error.h"
17 #include "qapi/qmp/qbool.h"
18 #include "qapi/qmp/qjson.h"
19 #include "qapi/qmp/qlit.h"
20 #include "qapi/qmp/qnull.h"
21 #include "qapi/qmp/qnum.h"
22 #include "qapi/qmp/qstring.h"
23 #include "qemu-common.h"
25 static void escaped_string(void)
39 { "\"\\/\"", "/", .skip
= 1 },
42 { "\"hello world \\\"embedded string\\\"\"",
43 "hello world \"embedded string\"" },
44 { "\"hello world\\nwith new line\"", "hello world\nwith new line" },
45 { "\"single byte utf-8 \\u0020\"", "single byte utf-8 ", .skip
= 1 },
46 { "\"double byte utf-8 \\u00A2\"", "double byte utf-8 \xc2\xa2" },
47 { "\"triple byte utf-8 \\u20AC\"", "triple byte utf-8 \xe2\x82\xac" },
48 { "'\\b'", "\b", .skip
= 1 },
49 { "'\\f'", "\f", .skip
= 1 },
50 { "'\\n'", "\n", .skip
= 1 },
51 { "'\\r'", "\r", .skip
= 1 },
52 { "'\\t'", "\t", .skip
= 1 },
53 { "'\\/'", "/", .skip
= 1 },
54 { "'\\\\'", "\\", .skip
= 1 },
58 for (i
= 0; test_cases
[i
].encoded
; i
++) {
62 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
63 str
= qobject_to_qstring(obj
);
65 g_assert_cmpstr(qstring_get_str(str
), ==, test_cases
[i
].decoded
);
67 if (test_cases
[i
].skip
== 0) {
68 str
= qobject_to_json(obj
);
69 g_assert_cmpstr(qstring_get_str(str
), ==, test_cases
[i
].encoded
);
77 static void simple_string(void)
84 { "\"hello world\"", "hello world" },
85 { "\"the quick brown fox jumped over the fence\"",
86 "the quick brown fox jumped over the fence" },
90 for (i
= 0; test_cases
[i
].encoded
; i
++) {
94 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
95 str
= qobject_to_qstring(obj
);
97 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].decoded
) == 0);
99 str
= qobject_to_json(obj
);
100 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].encoded
) == 0);
108 static void single_quote_string(void)
115 { "'hello world'", "hello world" },
116 { "'the quick brown fox \\' jumped over the fence'",
117 "the quick brown fox ' jumped over the fence" },
121 for (i
= 0; test_cases
[i
].encoded
; i
++) {
125 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
126 str
= qobject_to_qstring(obj
);
128 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].decoded
) == 0);
134 static void utf8_string(void)
137 * FIXME Current behavior for invalid UTF-8 sequences is
138 * incorrect. This test expects current, incorrect results.
139 * They're all marked "bug:" below, and are to be replaced by
140 * correct ones as the bugs get fixed.
142 * The JSON parser rejects some invalid sequences, but accepts
143 * others without correcting the problem.
145 * We should either reject all invalid sequences, or minimize
146 * overlong sequences and replace all other invalid sequences by a
147 * suitable replacement character. A common choice for
148 * replacement is U+FFFD.
150 * Problem: we can't easily deal with embedded U+0000. Parsing
151 * the JSON string "this \\u0000" is fun" yields "this \0 is fun",
152 * which gets misinterpreted as NUL-terminated "this ". We should
153 * consider using overlong encoding \xC0\x80 for U+0000 ("modified
156 * Most test cases are scraped from Markus Kuhn's UTF-8 decoder
157 * capability and stress test at
158 * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
160 static const struct {
162 const char *utf8_out
;
163 const char *json_out
; /* defaults to @json_in */
164 const char *utf8_in
; /* defaults to @utf8_out */
167 * Bug markers used here:
168 * - bug: not corrected
169 * JSON parser fails to correct invalid sequence(s)
171 * JSON parser rejects invalid sequence(s)
172 * We may choose to define this as feature
174 * JSON parser produces incorrect result, this is the
175 * correct one, assuming replacement character U+FFFF
176 * We may choose to reject instead of replace
179 /* 1 Some correct UTF-8 text */
181 /* a bit of German */
182 "\"Falsches \xC3\x9C" "ben von Xylophonmusik qu\xC3\xA4lt"
183 " jeden gr\xC3\xB6\xC3\x9F" "eren Zwerg.\"",
184 "Falsches \xC3\x9C" "ben von Xylophonmusik qu\xC3\xA4lt"
185 " jeden gr\xC3\xB6\xC3\x9F" "eren Zwerg.",
186 "\"Falsches \\u00DCben von Xylophonmusik qu\\u00E4lt"
187 " jeden gr\\u00F6\\u00DFeren Zwerg.\"",
191 "\"\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5\"",
192 "\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5",
193 "\"\\u03BA\\u1F79\\u03C3\\u03BC\\u03B5\"",
195 /* 2 Boundary condition test cases */
196 /* 2.1 First possible sequence of a certain length */
197 /* 2.1.1 1 byte U+0000 */
200 "", /* bug: want overlong "\xC0\x80" */
204 /* 2.1.2 2 bytes U+0080 */
210 /* 2.1.3 3 bytes U+0800 */
216 /* 2.1.4 4 bytes U+10000 */
218 "\"\xF0\x90\x80\x80\"",
220 "\"\\uD800\\uDC00\"",
222 /* 2.1.5 5 bytes U+200000 */
224 "\"\xF8\x88\x80\x80\x80\"",
225 NULL
, /* bug: rejected */
227 "\xF8\x88\x80\x80\x80",
229 /* 2.1.6 6 bytes U+4000000 */
231 "\"\xFC\x84\x80\x80\x80\x80\"",
232 NULL
, /* bug: rejected */
234 "\xFC\x84\x80\x80\x80\x80",
236 /* 2.2 Last possible sequence of a certain length */
237 /* 2.2.1 1 byte U+007F */
243 /* 2.2.2 2 bytes U+07FF */
250 * 2.2.3 3 bytes U+FFFC
251 * The last possible sequence is actually U+FFFF. But that's
252 * a noncharacter, and already covered by its own test case
253 * under 5.3. Same for U+FFFE. U+FFFD is the last character
254 * in the BMP, and covered under 2.3. Because of U+FFFD's
255 * special role as replacement character, it's worth testing
263 /* 2.2.4 4 bytes U+1FFFFF */
265 "\"\xF7\xBF\xBF\xBF\"",
266 NULL
, /* bug: rejected */
270 /* 2.2.5 5 bytes U+3FFFFFF */
272 "\"\xFB\xBF\xBF\xBF\xBF\"",
273 NULL
, /* bug: rejected */
275 "\xFB\xBF\xBF\xBF\xBF",
277 /* 2.2.6 6 bytes U+7FFFFFFF */
279 "\"\xFD\xBF\xBF\xBF\xBF\xBF\"",
280 NULL
, /* bug: rejected */
282 "\xFD\xBF\xBF\xBF\xBF\xBF",
284 /* 2.3 Other boundary conditions */
286 /* last one before surrogate range: U+D7FF */
292 /* first one after surrogate range: U+E000 */
298 /* last one in BMP: U+FFFD */
304 /* last one in last plane: U+10FFFD */
305 "\"\xF4\x8F\xBF\xBD\"",
310 /* first one beyond Unicode range: U+110000 */
311 "\"\xF4\x90\x80\x80\"",
315 /* 3 Malformed sequences */
316 /* 3.1 Unexpected continuation bytes */
317 /* 3.1.1 First continuation byte */
320 "\x80", /* bug: not corrected */
323 /* 3.1.2 Last continuation byte */
326 "\xBF", /* bug: not corrected */
329 /* 3.1.3 2 continuation bytes */
332 "\x80\xBF", /* bug: not corrected */
333 "\"\\uFFFD\\uFFFD\"",
335 /* 3.1.4 3 continuation bytes */
338 "\x80\xBF\x80", /* bug: not corrected */
339 "\"\\uFFFD\\uFFFD\\uFFFD\"",
341 /* 3.1.5 4 continuation bytes */
343 "\"\x80\xBF\x80\xBF\"",
344 "\x80\xBF\x80\xBF", /* bug: not corrected */
345 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
347 /* 3.1.6 5 continuation bytes */
349 "\"\x80\xBF\x80\xBF\x80\"",
350 "\x80\xBF\x80\xBF\x80", /* bug: not corrected */
351 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
353 /* 3.1.7 6 continuation bytes */
355 "\"\x80\xBF\x80\xBF\x80\xBF\"",
356 "\x80\xBF\x80\xBF\x80\xBF", /* bug: not corrected */
357 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
359 /* 3.1.8 7 continuation bytes */
361 "\"\x80\xBF\x80\xBF\x80\xBF\x80\"",
362 "\x80\xBF\x80\xBF\x80\xBF\x80", /* bug: not corrected */
363 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
365 /* 3.1.9 Sequence of all 64 possible continuation bytes */
367 "\"\x80\x81\x82\x83\x84\x85\x86\x87"
368 "\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
369 "\x90\x91\x92\x93\x94\x95\x96\x97"
370 "\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
371 "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7"
372 "\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
373 "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
374 "\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF\"",
375 /* bug: not corrected */
376 "\x80\x81\x82\x83\x84\x85\x86\x87"
377 "\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
378 "\x90\x91\x92\x93\x94\x95\x96\x97"
379 "\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
380 "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7"
381 "\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
382 "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
383 "\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
384 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
385 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
386 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
387 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
388 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
389 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
390 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
391 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\""
393 /* 3.2 Lonely start characters */
394 /* 3.2.1 All 32 first bytes of 2-byte sequences, followed by space */
396 "\"\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 "
397 "\xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF "
398 "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
399 "\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \"",
400 NULL
, /* bug: rejected */
401 "\"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
402 "\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
403 "\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
404 "\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \"",
405 "\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 "
406 "\xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF "
407 "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
408 "\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF ",
410 /* 3.2.2 All 16 first bytes of 3-byte sequences, followed by space */
412 "\"\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
413 "\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF \"",
414 /* bug: not corrected */
415 "\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
416 "\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
417 "\"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
418 "\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \"",
420 /* 3.2.3 All 8 first bytes of 4-byte sequences, followed by space */
422 "\"\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 \"",
423 NULL
, /* bug: rejected */
424 "\"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \"",
425 "\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ",
427 /* 3.2.4 All 4 first bytes of 5-byte sequences, followed by space */
429 "\"\xF8 \xF9 \xFA \xFB \"",
430 NULL
, /* bug: rejected */
431 "\"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \"",
432 "\xF8 \xF9 \xFA \xFB ",
434 /* 3.2.5 All 2 first bytes of 6-byte sequences, followed by space */
437 NULL
, /* bug: rejected */
438 "\"\\uFFFD \\uFFFD \"",
441 /* 3.3 Sequences with last continuation byte missing */
442 /* 3.3.1 2-byte sequence with last byte missing (U+0000) */
445 NULL
, /* bug: rejected */
449 /* 3.3.2 3-byte sequence with last byte missing (U+0000) */
452 "\xE0\x80", /* bug: not corrected */
455 /* 3.3.3 4-byte sequence with last byte missing (U+0000) */
458 "\xF0\x80\x80", /* bug: not corrected */
461 /* 3.3.4 5-byte sequence with last byte missing (U+0000) */
463 "\"\xF8\x80\x80\x80\"",
464 NULL
, /* bug: rejected */
468 /* 3.3.5 6-byte sequence with last byte missing (U+0000) */
470 "\"\xFC\x80\x80\x80\x80\"",
471 NULL
, /* bug: rejected */
473 "\xFC\x80\x80\x80\x80",
475 /* 3.3.6 2-byte sequence with last byte missing (U+07FF) */
478 "\xDF", /* bug: not corrected */
481 /* 3.3.7 3-byte sequence with last byte missing (U+FFFF) */
484 "\xEF\xBF", /* bug: not corrected */
487 /* 3.3.8 4-byte sequence with last byte missing (U+1FFFFF) */
490 NULL
, /* bug: rejected */
494 /* 3.3.9 5-byte sequence with last byte missing (U+3FFFFFF) */
496 "\"\xFB\xBF\xBF\xBF\"",
497 NULL
, /* bug: rejected */
501 /* 3.3.10 6-byte sequence with last byte missing (U+7FFFFFFF) */
503 "\"\xFD\xBF\xBF\xBF\xBF\"",
504 NULL
, /* bug: rejected */
506 "\xFD\xBF\xBF\xBF\xBF",
508 /* 3.4 Concatenation of incomplete sequences */
510 "\"\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
511 "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF\"",
512 NULL
, /* bug: rejected */
513 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
514 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
515 "\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
516 "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF",
518 /* 3.5 Impossible bytes */
521 NULL
, /* bug: rejected */
527 NULL
, /* bug: rejected */
532 "\"\xFE\xFE\xFF\xFF\"",
533 NULL
, /* bug: rejected */
534 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
537 /* 4 Overlong sequences */
538 /* 4.1 Overlong '/' */
541 NULL
, /* bug: rejected */
547 "\xE0\x80\xAF", /* bug: not corrected */
551 "\"\xF0\x80\x80\xAF\"",
552 "\xF0\x80\x80\xAF", /* bug: not corrected */
556 "\"\xF8\x80\x80\x80\xAF\"",
557 NULL
, /* bug: rejected */
559 "\xF8\x80\x80\x80\xAF",
562 "\"\xFC\x80\x80\x80\x80\xAF\"",
563 NULL
, /* bug: rejected */
565 "\xFC\x80\x80\x80\x80\xAF",
568 * 4.2 Maximum overlong sequences
569 * Highest Unicode value that is still resulting in an
570 * overlong sequence if represented with the given number of
571 * bytes. This is a boundary test for safe UTF-8 decoders.
576 NULL
, /* bug: rejected */
583 "\xE0\x9F\xBF", /* bug: not corrected */
589 * The actual maximum would be U+FFFF, but that's a
590 * noncharacter. Testing U+FFFC seems more useful. See
593 "\"\xF0\x8F\xBF\xBC\"",
594 "\xF0\x8F\xBF\xBC", /* bug: not corrected */
599 "\"\xF8\x87\xBF\xBF\xBF\"",
600 NULL
, /* bug: rejected */
602 "\xF8\x87\xBF\xBF\xBF",
606 "\"\xFC\x83\xBF\xBF\xBF\xBF\"",
607 NULL
, /* bug: rejected */
609 "\xFC\x83\xBF\xBF\xBF\xBF",
611 /* 4.3 Overlong representation of the NUL character */
615 NULL
, /* bug: rejected */
622 "\xE0\x80\x80", /* bug: not corrected */
627 "\"\xF0\x80\x80\x80\"",
628 "\xF0\x80\x80\x80", /* bug: not corrected */
633 "\"\xF8\x80\x80\x80\x80\"",
634 NULL
, /* bug: rejected */
636 "\xF8\x80\x80\x80\x80",
640 "\"\xFC\x80\x80\x80\x80\x80\"",
641 NULL
, /* bug: rejected */
643 "\xFC\x80\x80\x80\x80\x80",
645 /* 5 Illegal code positions */
646 /* 5.1 Single UTF-16 surrogates */
650 "\xED\xA0\x80", /* bug: not corrected */
656 "\xED\xAD\xBF", /* bug: not corrected */
662 "\xED\xAE\x80", /* bug: not corrected */
668 "\xED\xAF\xBF", /* bug: not corrected */
674 "\xED\xB0\x80", /* bug: not corrected */
680 "\xED\xBE\x80", /* bug: not corrected */
686 "\xED\xBF\xBF", /* bug: not corrected */
689 /* 5.2 Paired UTF-16 surrogates */
692 "\"\xED\xA0\x80\xED\xB0\x80\"",
693 "\xED\xA0\x80\xED\xB0\x80", /* bug: not corrected */
694 "\"\\uFFFD\\uFFFD\"",
698 "\"\xED\xA0\x80\xED\xBF\xBF\"",
699 "\xED\xA0\x80\xED\xBF\xBF", /* bug: not corrected */
700 "\"\\uFFFD\\uFFFD\"",
704 "\"\xED\xAD\xBF\xED\xB0\x80\"",
705 "\xED\xAD\xBF\xED\xB0\x80", /* bug: not corrected */
706 "\"\\uFFFD\\uFFFD\"",
710 "\"\xED\xAD\xBF\xED\xBF\xBF\"",
711 "\xED\xAD\xBF\xED\xBF\xBF", /* bug: not corrected */
712 "\"\\uFFFD\\uFFFD\"",
716 "\"\xED\xAE\x80\xED\xB0\x80\"",
717 "\xED\xAE\x80\xED\xB0\x80", /* bug: not corrected */
718 "\"\\uFFFD\\uFFFD\"",
722 "\"\xED\xAE\x80\xED\xBF\xBF\"",
723 "\xED\xAE\x80\xED\xBF\xBF", /* bug: not corrected */
724 "\"\\uFFFD\\uFFFD\"",
728 "\"\xED\xAF\xBF\xED\xB0\x80\"",
729 "\xED\xAF\xBF\xED\xB0\x80", /* bug: not corrected */
730 "\"\\uFFFD\\uFFFD\"",
734 "\"\xED\xAF\xBF\xED\xBF\xBF\"",
735 "\xED\xAF\xBF\xED\xBF\xBF", /* bug: not corrected */
736 "\"\\uFFFD\\uFFFD\"",
738 /* 5.3 Other illegal code positions */
739 /* BMP noncharacters */
743 "\xEF\xBF\xBE", /* bug: not corrected */
749 "\xEF\xBF\xBF", /* bug: not corrected */
755 "\xEF\xB7\x90", /* bug: not corrected */
761 "\xEF\xB7\xAF", /* bug: not corrected */
764 /* Plane 1 .. 16 noncharacters */
766 /* U+1FFFE U+1FFFF U+2FFFE U+2FFFF ... U+10FFFE U+10FFFF */
767 "\"\xF0\x9F\xBF\xBE\xF0\x9F\xBF\xBF"
768 "\xF0\xAF\xBF\xBE\xF0\xAF\xBF\xBF"
769 "\xF0\xBF\xBF\xBE\xF0\xBF\xBF\xBF"
770 "\xF1\x8F\xBF\xBE\xF1\x8F\xBF\xBF"
771 "\xF1\x9F\xBF\xBE\xF1\x9F\xBF\xBF"
772 "\xF1\xAF\xBF\xBE\xF1\xAF\xBF\xBF"
773 "\xF1\xBF\xBF\xBE\xF1\xBF\xBF\xBF"
774 "\xF2\x8F\xBF\xBE\xF2\x8F\xBF\xBF"
775 "\xF2\x9F\xBF\xBE\xF2\x9F\xBF\xBF"
776 "\xF2\xAF\xBF\xBE\xF2\xAF\xBF\xBF"
777 "\xF2\xBF\xBF\xBE\xF2\xBF\xBF\xBF"
778 "\xF3\x8F\xBF\xBE\xF3\x8F\xBF\xBF"
779 "\xF3\x9F\xBF\xBE\xF3\x9F\xBF\xBF"
780 "\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
781 "\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
782 "\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF\"",
783 /* bug: not corrected */
784 "\xF0\x9F\xBF\xBE\xF0\x9F\xBF\xBF"
785 "\xF0\xAF\xBF\xBE\xF0\xAF\xBF\xBF"
786 "\xF0\xBF\xBF\xBE\xF0\xBF\xBF\xBF"
787 "\xF1\x8F\xBF\xBE\xF1\x8F\xBF\xBF"
788 "\xF1\x9F\xBF\xBE\xF1\x9F\xBF\xBF"
789 "\xF1\xAF\xBF\xBE\xF1\xAF\xBF\xBF"
790 "\xF1\xBF\xBF\xBE\xF1\xBF\xBF\xBF"
791 "\xF2\x8F\xBF\xBE\xF2\x8F\xBF\xBF"
792 "\xF2\x9F\xBF\xBE\xF2\x9F\xBF\xBF"
793 "\xF2\xAF\xBF\xBE\xF2\xAF\xBF\xBF"
794 "\xF2\xBF\xBF\xBE\xF2\xBF\xBF\xBF"
795 "\xF3\x8F\xBF\xBE\xF3\x8F\xBF\xBF"
796 "\xF3\x9F\xBF\xBE\xF3\x9F\xBF\xBF"
797 "\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
798 "\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
799 "\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF",
800 "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
801 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
802 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
803 "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
810 const char *json_in
, *utf8_out
, *utf8_in
, *json_out
;
812 for (i
= 0; test_cases
[i
].json_in
; i
++) {
813 json_in
= test_cases
[i
].json_in
;
814 utf8_out
= test_cases
[i
].utf8_out
;
815 utf8_in
= test_cases
[i
].utf8_in
?: test_cases
[i
].utf8_out
;
816 json_out
= test_cases
[i
].json_out
?: test_cases
[i
].json_in
;
818 obj
= qobject_from_json(json_in
, utf8_out
? &error_abort
: NULL
);
820 str
= qobject_to_qstring(obj
);
822 g_assert_cmpstr(qstring_get_str(str
), ==, utf8_out
);
828 obj
= QOBJECT(qstring_from_str(utf8_in
));
829 str
= qobject_to_json(obj
);
832 g_assert_cmpstr(qstring_get_str(str
), ==, json_out
);
840 * Disabled, because qobject_from_json() is buggy, and I can't
841 * be bothered to add the expected incorrect results.
842 * FIXME Enable once these bugs have been fixed.
844 if (0 && json_out
!= json_in
) {
845 obj
= qobject_from_json(json_out
, &error_abort
);
846 str
= qobject_to_qstring(obj
);
848 g_assert_cmpstr(qstring_get_str(str
), ==, utf8_out
);
853 static void vararg_string(void)
860 { "the quick brown fox jumped over the fence" },
864 for (i
= 0; test_cases
[i
].decoded
; i
++) {
867 str
= qobject_to_qstring(qobject_from_jsonf("%s",
868 test_cases
[i
].decoded
));
870 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].decoded
) == 0);
876 static void simple_number(void)
888 { "-0", 0, .skip
= 1 },
892 for (i
= 0; test_cases
[i
].encoded
; i
++) {
896 qnum
= qobject_to_qnum(qobject_from_json(test_cases
[i
].encoded
,
899 g_assert(qnum_get_try_int(qnum
, &val
));
900 g_assert_cmpint(val
, ==, test_cases
[i
].decoded
);
901 if (test_cases
[i
].skip
== 0) {
904 str
= qobject_to_json(QOBJECT(qnum
));
905 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].encoded
) == 0);
913 static void large_number(void)
915 const char *maxu64
= "18446744073709551615"; /* 2^64-1 */
916 const char *gtu64
= "18446744073709551616"; /* 2^64 */
917 const char *lti64
= "-9223372036854775809"; /* -2^63 - 1 */
923 qnum
= qobject_to_qnum(qobject_from_json(maxu64
, &error_abort
));
925 g_assert_cmpuint(qnum_get_uint(qnum
), ==, 18446744073709551615U);
926 g_assert(!qnum_get_try_int(qnum
, &ival
));
928 str
= qobject_to_json(QOBJECT(qnum
));
929 g_assert_cmpstr(qstring_get_str(str
), ==, maxu64
);
933 qnum
= qobject_to_qnum(qobject_from_json(gtu64
, &error_abort
));
935 g_assert_cmpfloat(qnum_get_double(qnum
), ==, 18446744073709552e3
);
936 g_assert(!qnum_get_try_uint(qnum
, &val
));
937 g_assert(!qnum_get_try_int(qnum
, &ival
));
939 str
= qobject_to_json(QOBJECT(qnum
));
940 g_assert_cmpstr(qstring_get_str(str
), ==, gtu64
);
944 qnum
= qobject_to_qnum(qobject_from_json(lti64
, &error_abort
));
946 g_assert_cmpfloat(qnum_get_double(qnum
), ==, -92233720368547758e2
);
947 g_assert(!qnum_get_try_uint(qnum
, &val
));
948 g_assert(!qnum_get_try_int(qnum
, &ival
));
950 str
= qobject_to_json(QOBJECT(qnum
));
951 g_assert_cmpstr(qstring_get_str(str
), ==, "-9223372036854775808");
956 static void float_number(void)
966 { "-32.12313", -32.12313 },
967 { "-32.20e-10", -32.20e-10, .skip
= 1 },
971 for (i
= 0; test_cases
[i
].encoded
; i
++) {
975 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
976 qnum
= qobject_to_qnum(obj
);
978 g_assert(qnum_get_double(qnum
) == test_cases
[i
].decoded
);
980 if (test_cases
[i
].skip
== 0) {
983 str
= qobject_to_json(obj
);
984 g_assert(strcmp(qstring_get_str(str
), test_cases
[i
].encoded
) == 0);
992 static void vararg_number(void)
996 long long value_ll
= 0x2342342343LL
;
997 double valuef
= 2.323423423;
1000 qnum
= qobject_to_qnum(qobject_from_jsonf("%d", value
));
1001 g_assert(qnum_get_try_int(qnum
, &val
));
1002 g_assert_cmpint(val
, ==, value
);
1005 qnum
= qobject_to_qnum(qobject_from_jsonf("%lld", value_ll
));
1006 g_assert(qnum_get_try_int(qnum
, &val
));
1007 g_assert_cmpint(val
, ==, value_ll
);
1010 qnum
= qobject_to_qnum(qobject_from_jsonf("%f", valuef
));
1011 g_assert(qnum_get_double(qnum
) == valuef
);
1015 static void keyword_literal(void)
1022 obj
= qobject_from_json("true", &error_abort
);
1023 qbool
= qobject_to_qbool(obj
);
1025 g_assert(qbool_get_bool(qbool
) == true);
1027 str
= qobject_to_json(obj
);
1028 g_assert(strcmp(qstring_get_str(str
), "true") == 0);
1033 obj
= qobject_from_json("false", &error_abort
);
1034 qbool
= qobject_to_qbool(obj
);
1036 g_assert(qbool_get_bool(qbool
) == false);
1038 str
= qobject_to_json(obj
);
1039 g_assert(strcmp(qstring_get_str(str
), "false") == 0);
1044 qbool
= qobject_to_qbool(qobject_from_jsonf("%i", false));
1046 g_assert(qbool_get_bool(qbool
) == false);
1049 /* Test that non-zero values other than 1 get collapsed to true */
1050 qbool
= qobject_to_qbool(qobject_from_jsonf("%i", 2));
1052 g_assert(qbool_get_bool(qbool
) == true);
1055 obj
= qobject_from_json("null", &error_abort
);
1056 g_assert(obj
!= NULL
);
1057 g_assert(qobject_type(obj
) == QTYPE_QNULL
);
1060 g_assert(QOBJECT(null
) == obj
);
1062 qobject_decref(obj
);
1066 static void simple_dict(void)
1070 const char *encoded
;
1074 .encoded
= "{\"foo\": 42, \"bar\": \"hello world\"}",
1075 .decoded
= QLIT_QDICT(((QLitDictEntry
[]){
1076 { "foo", QLIT_QNUM(42) },
1077 { "bar", QLIT_QSTR("hello world") },
1082 .decoded
= QLIT_QDICT(((QLitDictEntry
[]){
1086 .encoded
= "{\"foo\": 43}",
1087 .decoded
= QLIT_QDICT(((QLitDictEntry
[]){
1088 { "foo", QLIT_QNUM(43) },
1095 for (i
= 0; test_cases
[i
].encoded
; i
++) {
1099 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
1100 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1102 str
= qobject_to_json(obj
);
1103 qobject_decref(obj
);
1105 obj
= qobject_from_json(qstring_get_str(str
), &error_abort
);
1106 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1107 qobject_decref(obj
);
1113 * this generates json of the form:
1114 * a(0,m) = [0, 1, ..., m-1]
1119 * 'key(n-1)': a(n-1,m)
1122 static void gen_test_json(GString
*gstr
, int nest_level_max
,
1128 if (nest_level_max
== 0) {
1129 g_string_append(gstr
, "[");
1130 for (i
= 0; i
< elem_count
; i
++) {
1131 g_string_append_printf(gstr
, "%d", i
);
1132 if (i
< elem_count
- 1) {
1133 g_string_append_printf(gstr
, ", ");
1136 g_string_append(gstr
, "]");
1140 g_string_append(gstr
, "{");
1141 for (i
= 0; i
< nest_level_max
; i
++) {
1142 g_string_append_printf(gstr
, "'key%d': ", i
);
1143 gen_test_json(gstr
, i
, elem_count
);
1144 if (i
< nest_level_max
- 1) {
1145 g_string_append(gstr
, ",");
1148 g_string_append(gstr
, "}");
1151 static void large_dict(void)
1153 GString
*gstr
= g_string_new("");
1156 gen_test_json(gstr
, 10, 100);
1157 obj
= qobject_from_json(gstr
->str
, &error_abort
);
1158 g_assert(obj
!= NULL
);
1160 qobject_decref(obj
);
1161 g_string_free(gstr
, true);
1164 static void simple_list(void)
1168 const char *encoded
;
1172 .encoded
= "[43,42]",
1173 .decoded
= QLIT_QLIST(((QLitObject
[]){
1181 .decoded
= QLIT_QLIST(((QLitObject
[]){
1188 .decoded
= QLIT_QLIST(((QLitObject
[]){
1194 .decoded
= QLIT_QLIST(((QLitObject
[]){
1195 QLIT_QDICT(((QLitDictEntry
[]){
1204 for (i
= 0; test_cases
[i
].encoded
; i
++) {
1208 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
1209 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1211 str
= qobject_to_json(obj
);
1212 qobject_decref(obj
);
1214 obj
= qobject_from_json(qstring_get_str(str
), &error_abort
);
1215 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1216 qobject_decref(obj
);
1221 static void simple_whitespace(void)
1225 const char *encoded
;
1229 .encoded
= " [ 43 , 42 ]",
1230 .decoded
= QLIT_QLIST(((QLitObject
[]){
1237 .encoded
= " [ 43 , { 'h' : 'b' }, [ ], 42 ]",
1238 .decoded
= QLIT_QLIST(((QLitObject
[]){
1240 QLIT_QDICT(((QLitDictEntry
[]){
1241 { "h", QLIT_QSTR("b") },
1243 QLIT_QLIST(((QLitObject
[]){
1250 .encoded
= " [ 43 , { 'h' : 'b' , 'a' : 32 }, [ ], 42 ]",
1251 .decoded
= QLIT_QLIST(((QLitObject
[]){
1253 QLIT_QDICT(((QLitDictEntry
[]){
1254 { "h", QLIT_QSTR("b") },
1255 { "a", QLIT_QNUM(32) },
1257 QLIT_QLIST(((QLitObject
[]){
1266 for (i
= 0; test_cases
[i
].encoded
; i
++) {
1270 obj
= qobject_from_json(test_cases
[i
].encoded
, &error_abort
);
1271 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1273 str
= qobject_to_json(obj
);
1274 qobject_decref(obj
);
1276 obj
= qobject_from_json(qstring_get_str(str
), &error_abort
);
1277 g_assert(qlit_equal_qobject(&test_cases
[i
].decoded
, obj
));
1279 qobject_decref(obj
);
1284 static void simple_varargs(void)
1286 QObject
*embedded_obj
;
1288 QLitObject decoded
= QLIT_QLIST(((QLitObject
[]){
1291 QLIT_QLIST(((QLitObject
[]){
1297 embedded_obj
= qobject_from_json("[32, 42]", &error_abort
);
1298 g_assert(embedded_obj
!= NULL
);
1300 obj
= qobject_from_jsonf("[%d, 2, %p]", 1, embedded_obj
);
1301 g_assert(qlit_equal_qobject(&decoded
, obj
));
1303 qobject_decref(obj
);
1306 static void empty_input(void)
1308 const char *empty
= "";
1309 QObject
*obj
= qobject_from_json(empty
, &error_abort
);
1310 g_assert(obj
== NULL
);
1313 static void unterminated_string(void)
1316 QObject
*obj
= qobject_from_json("\"abc", &err
);
1317 g_assert(!err
); /* BUG */
1318 g_assert(obj
== NULL
);
1321 static void unterminated_sq_string(void)
1324 QObject
*obj
= qobject_from_json("'abc", &err
);
1325 g_assert(!err
); /* BUG */
1326 g_assert(obj
== NULL
);
1329 static void unterminated_escape(void)
1332 QObject
*obj
= qobject_from_json("\"abc\\\"", &err
);
1333 g_assert(!err
); /* BUG */
1334 g_assert(obj
== NULL
);
1337 static void unterminated_array(void)
1340 QObject
*obj
= qobject_from_json("[32", &err
);
1341 g_assert(!err
); /* BUG */
1342 g_assert(obj
== NULL
);
1345 static void unterminated_array_comma(void)
1348 QObject
*obj
= qobject_from_json("[32,", &err
);
1349 g_assert(!err
); /* BUG */
1350 g_assert(obj
== NULL
);
1353 static void invalid_array_comma(void)
1356 QObject
*obj
= qobject_from_json("[32,}", &err
);
1357 error_free_or_abort(&err
);
1358 g_assert(obj
== NULL
);
1361 static void unterminated_dict(void)
1364 QObject
*obj
= qobject_from_json("{'abc':32", &err
);
1365 g_assert(!err
); /* BUG */
1366 g_assert(obj
== NULL
);
1369 static void unterminated_dict_comma(void)
1372 QObject
*obj
= qobject_from_json("{'abc':32,", &err
);
1373 g_assert(!err
); /* BUG */
1374 g_assert(obj
== NULL
);
1377 static void invalid_dict_comma(void)
1380 QObject
*obj
= qobject_from_json("{'abc':32,}", &err
);
1381 error_free_or_abort(&err
);
1382 g_assert(obj
== NULL
);
1385 static void unterminated_literal(void)
1388 QObject
*obj
= qobject_from_json("nul", &err
);
1389 error_free_or_abort(&err
);
1390 g_assert(obj
== NULL
);
1393 static char *make_nest(char *buf
, size_t cnt
)
1395 memset(buf
, '[', cnt
- 1);
1398 memset(buf
+ cnt
+ 1, ']', cnt
- 1);
1403 static void limits_nesting(void)
1406 enum { max_nesting
= 1024 }; /* see qobject/json-streamer.c */
1407 char buf
[2 * (max_nesting
+ 1) + 1];
1410 obj
= qobject_from_json(make_nest(buf
, max_nesting
), &error_abort
);
1411 g_assert(obj
!= NULL
);
1412 qobject_decref(obj
);
1414 obj
= qobject_from_json(make_nest(buf
, max_nesting
+ 1), &err
);
1415 error_free_or_abort(&err
);
1416 g_assert(obj
== NULL
);
1419 int main(int argc
, char **argv
)
1421 g_test_init(&argc
, &argv
, NULL
);
1423 g_test_add_func("/literals/string/simple", simple_string
);
1424 g_test_add_func("/literals/string/escaped", escaped_string
);
1425 g_test_add_func("/literals/string/utf8", utf8_string
);
1426 g_test_add_func("/literals/string/single_quote", single_quote_string
);
1427 g_test_add_func("/literals/string/vararg", vararg_string
);
1429 g_test_add_func("/literals/number/simple", simple_number
);
1430 g_test_add_func("/literals/number/large", large_number
);
1431 g_test_add_func("/literals/number/float", float_number
);
1432 g_test_add_func("/literals/number/vararg", vararg_number
);
1434 g_test_add_func("/literals/keyword", keyword_literal
);
1436 g_test_add_func("/dicts/simple_dict", simple_dict
);
1437 g_test_add_func("/dicts/large_dict", large_dict
);
1438 g_test_add_func("/lists/simple_list", simple_list
);
1440 g_test_add_func("/whitespace/simple_whitespace", simple_whitespace
);
1442 g_test_add_func("/varargs/simple_varargs", simple_varargs
);
1444 g_test_add_func("/errors/empty_input", empty_input
);
1445 g_test_add_func("/errors/unterminated/string", unterminated_string
);
1446 g_test_add_func("/errors/unterminated/escape", unterminated_escape
);
1447 g_test_add_func("/errors/unterminated/sq_string", unterminated_sq_string
);
1448 g_test_add_func("/errors/unterminated/array", unterminated_array
);
1449 g_test_add_func("/errors/unterminated/array_comma", unterminated_array_comma
);
1450 g_test_add_func("/errors/unterminated/dict", unterminated_dict
);
1451 g_test_add_func("/errors/unterminated/dict_comma", unterminated_dict_comma
);
1452 g_test_add_func("/errors/invalid_array_comma", invalid_array_comma
);
1453 g_test_add_func("/errors/invalid_dict_comma", invalid_dict_comma
);
1454 g_test_add_func("/errors/unterminated/literal", unterminated_literal
);
1455 g_test_add_func("/errors/limits/nesting", limits_nesting
);
1457 return g_test_run();