#include "qapi/qmp/qnull.h"
#include "qapi/qmp/qnum.h"
#include "qapi/qmp/qstring.h"
+#include "qemu/unicode.h"
#include "qemu-common.h"
static QString *from_json_str(const char *jstr, bool single, Error **errp)
{ "double byte utf-8 \\u00A2", "double byte utf-8 \xc2\xa2" },
{ "triple byte utf-8 \\u20AC", "triple byte utf-8 \xe2\x82\xac" },
{ "quadruple byte utf-8 \\uD834\\uDD1E", /* U+1D11E */
- /* bug: want \xF0\x9D\x84\x9E */
- "quadruple byte utf-8 \xED\xA0\xB4\xED\xB4\x9E", .skip = 1 },
+ "quadruple byte utf-8 \xF0\x9D\x84\x9E" },
{ "\\", NULL },
{ "\\z", NULL },
{ "\\ux", NULL },
{ "\\u12x", NULL },
{ "\\u123x", NULL },
{ "\\u12345", "\341\210\2645" },
- { "\\u0000x", "x", .skip = 1}, /* bug: want \xC0\x80x */
- { "unpaired leading surrogate \\uD800",
- /* bug: not rejected */
- "unpaired leading surrogate \355\240\200", .skip = 1 },
- { "unpaired leading surrogate \\uD800\\uCAFE",
- /* bug: not rejected */
- "unpaired leading surrogate \355\240\200\354\253\276", .skip = 1 },
- { "unpaired leading surrogate \\uD800\\uD801\\uDC02",
- /* bug: not rejected */
- "unpaired leading surrogate \355\240\200\355\240\201\355\260\202",
- .skip = 1 },
- { "unpaired trailing surrogate \\uDC00",
- /* bug: not rejected */
- "unpaired trailing surrogate \355\260\200", .skip = 1},
- { "backward surrogate pair \\uDC00\\uD800",
- /* bug: not rejected */
- "backward surrogate pair \355\260\200\355\240\200", .skip = 1},
- { "noncharacter U+FDD0 \\uFDD0",
- /* bug: not rejected */
- "noncharacter U+FDD0 \xEF\xB7\x90", .skip = 1},
- { "noncharacter U+FDEF \\uFDEF",
- /* bug: not rejected */
- "noncharacter U+FDEF \xEF\xB7\xAF", .skip = 1},
- { "noncharacter U+1FFFE \\uD87F\\uDFFE",
- /* bug: not rejected */
- "noncharacter U+1FFFE \xED\xA1\xBF\xED\xBF\xBE", .skip = 1},
- { "noncharacter U+10FFFF \\uDC3F\\uDFFF",
- /* bug: not rejected */
- "noncharacter U+10FFFF \xED\xB0\xBF\xED\xBF\xBF", .skip = 1},
+ { "\\u0000x", "\xC0\x80x" },
+ { "unpaired leading surrogate \\uD800", NULL },
+ { "unpaired leading surrogate \\uD800\\uCAFE", NULL },
+ { "unpaired leading surrogate \\uD800\\uD801\\uDC02", NULL },
+ { "unpaired trailing surrogate \\uDC00", NULL },
+ { "backward surrogate pair \\uDC00\\uD800", NULL },
+ { "noncharacter U+FDD0 \\uFDD0", NULL },
+ { "noncharacter U+FDEF \\uFDEF", NULL },
+ { "noncharacter U+1FFFE \\uD87F\\uDFFE", NULL },
+ { "noncharacter U+10FFFF \\uDC3F\\uDFFF", NULL },
{}
};
int i, j;
static void utf8_string(void)
{
/*
- * FIXME Current behavior for invalid UTF-8 sequences is
- * incorrect. This test expects current, incorrect results.
- * They're all marked "bug:" below, and are to be replaced by
- * correct ones as the bugs get fixed.
- *
- * The JSON parser rejects some invalid sequences, but accepts
- * others without correcting the problem.
- *
- * We should either reject all invalid sequences, or minimize
- * overlong sequences and replace all other invalid sequences by a
- * suitable replacement character. A common choice for
- * replacement is U+FFFD.
- *
- * Problem: we can't easily deal with embedded U+0000. Parsing
- * the JSON string "this \\u0000" is fun" yields "this \0 is fun",
- * which gets misinterpreted as NUL-terminated "this ". We should
- * consider using overlong encoding \xC0\x80 for U+0000 ("modified
- * UTF-8").
- *
* Most test cases are scraped from Markus Kuhn's UTF-8 decoder
* capability and stress test at
* http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
const char *utf8_out;
/* Expected unparse output, defaults to @json_in */
const char *json_out;
- /* Expected parse output for @json_out, defaults to @utf8_out */
- const char *utf8_in;
} test_cases[] = {
- /*
- * Bug markers used here:
- * - bug: not corrected
- * JSON parser fails to correct invalid sequence(s)
- * - bug: rejected
- * JSON parser rejects invalid sequence(s)
- * We may choose to define this as feature
- * - bug: want "..."
- * JSON parser produces incorrect result, this is the
- * correct one, assuming replacement character U+FFFF
- * We may choose to reject instead of replace
- */
-
+ /* 0 Control characters */
+ {
+ /*
+ * Note: \x00 is impossible, other representations of
+ * U+0000 are covered under 4.3
+ */
+ "\x01\x02\x03\x04\x05\x06\x07"
+ "\x08\x09\x0A\x0B\x0C\x0D\x0E\x0F"
+ "\x10\x11\x12\x13\x14\x15\x16\x17"
+ "\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F",
+ NULL,
+ "\\u0001\\u0002\\u0003\\u0004\\u0005\\u0006\\u0007"
+ "\\b\\t\\n\\u000B\\f\\r\\u000E\\u000F"
+ "\\u0010\\u0011\\u0012\\u0013\\u0014\\u0015\\u0016\\u0017"
+ "\\u0018\\u0019\\u001A\\u001B\\u001C\\u001D\\u001E\\u001F",
+ },
/* 1 Some correct UTF-8 text */
{
/* a bit of German */
"\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5",
"\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5",
"\\u03BA\\u1F79\\u03C3\\u03BC\\u03B5",
+ },
+ /* '%' character when not interpolating */
+ {
+ "100%",
+ "100%",
},
/* 2 Boundary condition test cases */
/* 2.1 First possible sequence of a certain length */
- /* 2.1.1 1 byte U+0000 */
+ /*
+ * 2.1.1 1 byte U+0020
+ * Control characters are already covered by their own test
+ * case under 0. Test the first 1 byte non-control character
+ * here.
+ */
{
- "\\u0000",
- "", /* bug: want overlong "\xC0\x80" */
- "\\u0000",
- "\xC0\x80",
+ " ",
+ " ",
},
/* 2.1.2 2 bytes U+0080 */
{
/* 2.1.5 5 bytes U+200000 */
{
"\xF8\x88\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF8\x88\x80\x80\x80",
},
/* 2.1.6 6 bytes U+4000000 */
{
"\xFC\x84\x80\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFC\x84\x80\x80\x80\x80",
},
/* 2.2 Last possible sequence of a certain length */
/* 2.2.1 1 byte U+007F */
/* 2.2.4 4 bytes U+1FFFFF */
{
"\xF7\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF7\xBF\xBF\xBF",
},
/* 2.2.5 5 bytes U+3FFFFFF */
{
"\xFB\xBF\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFB\xBF\xBF\xBF\xBF",
},
/* 2.2.6 6 bytes U+7FFFFFFF */
{
"\xFD\xBF\xBF\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFD\xBF\xBF\xBF\xBF\xBF",
},
/* 2.3 Other boundary conditions */
{
{
/* first one beyond Unicode range: U+110000 */
"\xF4\x90\x80\x80",
- "\xF4\x90\x80\x80",
+ NULL,
"\\uFFFD",
},
/* 3 Malformed sequences */
/* 3.1.1 First continuation byte */
{
"\x80",
- "\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.1.2 Last continuation byte */
{
"\xBF",
- "\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.1.3 2 continuation bytes */
{
"\x80\xBF",
- "\x80\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
/* 3.1.4 3 continuation bytes */
{
"\x80\xBF\x80",
- "\x80\xBF\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.1.5 4 continuation bytes */
{
"\x80\xBF\x80\xBF",
- "\x80\xBF\x80\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.1.6 5 continuation bytes */
{
"\x80\xBF\x80\xBF\x80",
- "\x80\xBF\x80\xBF\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.1.7 6 continuation bytes */
{
"\x80\xBF\x80\xBF\x80\xBF",
- "\x80\xBF\x80\xBF\x80\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.1.8 7 continuation bytes */
{
"\x80\xBF\x80\xBF\x80\xBF\x80",
- "\x80\xBF\x80\xBF\x80\xBF\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.1.9 Sequence of all 64 possible continuation bytes */
"\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
"\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
"\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
- /* bug: not corrected */
- "\x80\x81\x82\x83\x84\x85\x86\x87"
- "\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
- "\x90\x91\x92\x93\x94\x95\x96\x97"
- "\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
- "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7"
- "\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
- "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
- "\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
- "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
+ "\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
},
/* 3.2 Lonely start characters */
/* 3.2.1 All 32 first bytes of 2-byte sequences, followed by space */
"\xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF "
"\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
"\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF ",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
- "\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 "
- "\xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF "
- "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
- "\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF ",
},
/* 3.2.2 All 16 first bytes of 3-byte sequences, followed by space */
{
"\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
"\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
- /* bug: not corrected */
- "\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
- "\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
+ NULL,
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
},
/* 3.2.3 All 8 first bytes of 4-byte sequences, followed by space */
{
"\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
- "\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ",
},
/* 3.2.4 All 4 first bytes of 5-byte sequences, followed by space */
{
"\xF8 \xF9 \xFA \xFB ",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
- "\xF8 \xF9 \xFA \xFB ",
},
/* 3.2.5 All 2 first bytes of 6-byte sequences, followed by space */
{
"\xFC \xFD ",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD \\uFFFD ",
- "\xFC \xFD ",
},
/* 3.3 Sequences with last continuation byte missing */
/* 3.3.1 2-byte sequence with last byte missing (U+0000) */
{
"\xC0",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xC0",
},
/* 3.3.2 3-byte sequence with last byte missing (U+0000) */
{
"\xE0\x80",
- "\xE0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.3.3 4-byte sequence with last byte missing (U+0000) */
{
"\xF0\x80\x80",
- "\xF0\x80\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.3.4 5-byte sequence with last byte missing (U+0000) */
{
"\xF8\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF8\x80\x80\x80",
},
/* 3.3.5 6-byte sequence with last byte missing (U+0000) */
{
"\xFC\x80\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFC\x80\x80\x80\x80",
},
/* 3.3.6 2-byte sequence with last byte missing (U+07FF) */
{
"\xDF",
- "\xDF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.3.7 3-byte sequence with last byte missing (U+FFFF) */
{
"\xEF\xBF",
- "\xEF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 3.3.8 4-byte sequence with last byte missing (U+1FFFFF) */
{
"\xF7\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF7\xBF\xBF",
},
/* 3.3.9 5-byte sequence with last byte missing (U+3FFFFFF) */
{
"\xFB\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFB\xBF\xBF\xBF",
},
/* 3.3.10 6-byte sequence with last byte missing (U+7FFFFFFF) */
{
"\xFD\xBF\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFD\xBF\xBF\xBF\xBF",
},
/* 3.4 Concatenation of incomplete sequences */
{
"\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
"\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
- "\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
- "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF",
},
/* 3.5 Impossible bytes */
{
"\xFE",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFE",
},
{
"\xFF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFF",
},
{
"\xFE\xFE\xFF\xFF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
- "\xFE\xFE\xFF\xFF",
},
/* 4 Overlong sequences */
/* 4.1 Overlong '/' */
{
"\xC0\xAF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xC0\xAF",
},
{
"\xE0\x80\xAF",
- "\xE0\x80\xAF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
"\xF0\x80\x80\xAF",
- "\xF0\x80\x80\xAF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
"\xF8\x80\x80\x80\xAF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF8\x80\x80\x80\xAF",
},
{
"\xFC\x80\x80\x80\x80\xAF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFC\x80\x80\x80\x80\xAF",
},
/*
* 4.2 Maximum overlong sequences
{
/* \U+007F */
"\xC1\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xC1\xBF",
},
{
/* \U+07FF */
"\xE0\x9F\xBF",
- "\xE0\x9F\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
* also 2.2.3
*/
"\xF0\x8F\xBF\xBC",
- "\xF0\x8F\xBF\xBC", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+1FFFFF */
"\xF8\x87\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF8\x87\xBF\xBF\xBF",
},
{
/* \U+3FFFFFF */
"\xFC\x83\xBF\xBF\xBF\xBF",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFC\x83\xBF\xBF\xBF\xBF",
},
/* 4.3 Overlong representation of the NUL character */
{
/* \U+0000 */
"\xC0\x80",
- NULL, /* bug: rejected */
- "\\u0000",
"\xC0\x80",
+ "\\u0000",
},
{
/* \U+0000 */
"\xE0\x80\x80",
- "\xE0\x80\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+0000 */
"\xF0\x80\x80\x80",
- "\xF0\x80\x80\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+0000 */
"\xF8\x80\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xF8\x80\x80\x80\x80",
},
{
/* \U+0000 */
"\xFC\x80\x80\x80\x80\x80",
- NULL, /* bug: rejected */
+ NULL,
"\\uFFFD",
- "\xFC\x80\x80\x80\x80\x80",
},
/* 5 Illegal code positions */
/* 5.1 Single UTF-16 surrogates */
{
/* \U+D800 */
"\xED\xA0\x80",
- "\xED\xA0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DB7F */
"\xED\xAD\xBF",
- "\xED\xAD\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DB80 */
"\xED\xAE\x80",
- "\xED\xAE\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DBFF */
"\xED\xAF\xBF",
- "\xED\xAF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DC00 */
"\xED\xB0\x80",
- "\xED\xB0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DF80 */
"\xED\xBE\x80",
- "\xED\xBE\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+DFFF */
"\xED\xBF\xBF",
- "\xED\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* 5.2 Paired UTF-16 surrogates */
{
/* \U+D800\U+DC00 */
"\xED\xA0\x80\xED\xB0\x80",
- "\xED\xA0\x80\xED\xB0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+D800\U+DFFF */
"\xED\xA0\x80\xED\xBF\xBF",
- "\xED\xA0\x80\xED\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DB7F\U+DC00 */
"\xED\xAD\xBF\xED\xB0\x80",
- "\xED\xAD\xBF\xED\xB0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DB7F\U+DFFF */
"\xED\xAD\xBF\xED\xBF\xBF",
- "\xED\xAD\xBF\xED\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DB80\U+DC00 */
"\xED\xAE\x80\xED\xB0\x80",
- "\xED\xAE\x80\xED\xB0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DB80\U+DFFF */
"\xED\xAE\x80\xED\xBF\xBF",
- "\xED\xAE\x80\xED\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DBFF\U+DC00 */
"\xED\xAF\xBF\xED\xB0\x80",
- "\xED\xAF\xBF\xED\xB0\x80", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
{
/* \U+DBFF\U+DFFF */
"\xED\xAF\xBF\xED\xBF\xBF",
- "\xED\xAF\xBF\xED\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD\\uFFFD",
},
/* 5.3 Other illegal code positions */
{
/* \U+FFFE */
"\xEF\xBF\xBE",
- "\xEF\xBF\xBE", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* \U+FFFF */
"\xEF\xBF\xBF",
- "\xEF\xBF\xBF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* U+FDD0 */
"\xEF\xB7\x90",
- "\xEF\xB7\x90", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
{
/* U+FDEF */
"\xEF\xB7\xAF",
- "\xEF\xB7\xAF", /* bug: not corrected */
+ NULL,
"\\uFFFD",
},
/* Plane 1 .. 16 noncharacters */
"\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
"\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
"\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF",
- /* bug: not corrected */
- "\xF0\x9F\xBF\xBE\xF0\x9F\xBF\xBF"
- "\xF0\xAF\xBF\xBE\xF0\xAF\xBF\xBF"
- "\xF0\xBF\xBF\xBE\xF0\xBF\xBF\xBF"
- "\xF1\x8F\xBF\xBE\xF1\x8F\xBF\xBF"
- "\xF1\x9F\xBF\xBE\xF1\x9F\xBF\xBF"
- "\xF1\xAF\xBF\xBE\xF1\xAF\xBF\xBF"
- "\xF1\xBF\xBF\xBE\xF1\xBF\xBF\xBF"
- "\xF2\x8F\xBF\xBE\xF2\x8F\xBF\xBF"
- "\xF2\x9F\xBF\xBE\xF2\x9F\xBF\xBF"
- "\xF2\xAF\xBF\xBE\xF2\xAF\xBF\xBF"
- "\xF2\xBF\xBF\xBE\xF2\xBF\xBF\xBF"
- "\xF3\x8F\xBF\xBE\xF3\x8F\xBF\xBF"
- "\xF3\x9F\xBF\xBE\xF3\x9F\xBF\xBF"
- "\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
- "\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
- "\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF",
+ NULL,
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
};
int i, j;
QString *str;
- const char *json_in, *utf8_out, *utf8_in, *json_out;
- char *jstr;
+ const char *json_in, *utf8_out, *utf8_in, *json_out, *tail;
+ char *end, *in, *jstr;
for (i = 0; test_cases[i].json_in; i++) {
for (j = 0; j < 2; j++) {
json_in = test_cases[i].json_in;
utf8_out = test_cases[i].utf8_out;
- utf8_in = test_cases[i].utf8_in ?: test_cases[i].utf8_out;
+ utf8_in = test_cases[i].utf8_out ?: test_cases[i].json_in;
json_out = test_cases[i].json_out ?: test_cases[i].json_in;
/* Parse @json_in, expect @utf8_out */
} else {
str = from_json_str(json_in, j, NULL);
g_assert(!str);
+ /*
+ * Failure may be due to any sequence, but *all* sequences
+ * are expected to fail. Test each one in isolation.
+ */
+ for (tail = json_in; *tail; tail = end) {
+ mod_utf8_codepoint(tail, 6, &end);
+ if (*end == ' ') {
+ end++;
+ }
+ in = g_strndup(tail, end - tail);
+ str = from_json_str(in, j, NULL);
+ g_assert(!str);
+ g_free(in);
+ }
}
/* Unparse @utf8_in, expect @json_out */
qobject_unref(str);
g_free(jstr);
- /*
- * Parse @json_out right back
- * Disabled, because qobject_from_json() is buggy, and I can't
- * be bothered to add the expected incorrect results.
- * FIXME Enable once these bugs have been fixed.
- */
- if (0 && json_out != json_in) {
+ /* Parse @json_out right back, unless it has replacements */
+ if (!strstr(json_out, "\\uFFFD")) {
str = from_json_str(json_out, j, &error_abort);
- g_assert_cmpstr(qstring_get_try_str(str), ==, utf8_out);
+ g_assert_cmpstr(qstring_get_try_str(str), ==, utf8_in);
+ qobject_unref(str);
}
}
}
}
-static void vararg_string(void)
-{
- int i;
- struct {
- const char *decoded;
- } test_cases[] = {
- { "hello world" },
- { "the quick brown fox jumped over the fence" },
- {}
- };
-
- for (i = 0; test_cases[i].decoded; i++) {
- QString *str;
-
- str = qobject_to(QString,
- qobject_from_jsonf_nofail("%s",
- test_cases[i].decoded));
- g_assert(str);
- g_assert(strcmp(qstring_get_str(str), test_cases[i].decoded) == 0);
-
- qobject_unref(str);
- }
-}
-
static void simple_number(void)
{
int i;
}
}
-static void vararg_number(void)
-{
- QNum *qnum;
- int value = 0x2342;
- long long value_ll = 0x2342342343LL;
- double valuef = 2.323423423;
- int64_t val;
-
- qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%d", value));
- g_assert(qnum_get_try_int(qnum, &val));
- g_assert_cmpint(val, ==, value);
- qobject_unref(qnum);
-
- qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%lld", value_ll));
- g_assert(qnum_get_try_int(qnum, &val));
- g_assert_cmpint(val, ==, value_ll);
- qobject_unref(qnum);
-
- qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%f", valuef));
- g_assert(qnum_get_double(qnum) == valuef);
- qobject_unref(qnum);
-}
-
static void keyword_literal(void)
{
QObject *obj;
qobject_unref(qbool);
+ obj = qobject_from_json("null", &error_abort);
+ g_assert(obj != NULL);
+ g_assert(qobject_type(obj) == QTYPE_QNULL);
+
+ null = qnull();
+ g_assert(QOBJECT(null) == obj);
+
+ qobject_unref(obj);
+ qobject_unref(null);
+}
+
+static void interpolation_valid(void)
+{
+ long long value_lld = 0x123456789abcdefLL;
+ int64_t value_d64 = value_lld;
+ long value_ld = (long)value_lld;
+ int value_d = (int)value_lld;
+ unsigned long long value_llu = 0xfedcba9876543210ULL;
+ uint64_t value_u64 = value_llu;
+ unsigned long value_lu = (unsigned long)value_llu;
+ unsigned value_u = (unsigned)value_llu;
+ double value_f = 2.323423423;
+ const char *value_s = "hello world";
+ QObject *value_p = QOBJECT(qnull());
+ QBool *qbool;
+ QNum *qnum;
+ QString *qstr;
+ QObject *qobj;
+
+ /* bool */
+
qbool = qobject_to(QBool, qobject_from_jsonf_nofail("%i", false));
g_assert(qbool);
g_assert(qbool_get_bool(qbool) == false);
g_assert(qbool_get_bool(qbool) == true);
qobject_unref(qbool);
- obj = qobject_from_json("null", &error_abort);
- g_assert(obj != NULL);
- g_assert(qobject_type(obj) == QTYPE_QNULL);
+ /* number */
- null = qnull();
- g_assert(QOBJECT(null) == obj);
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%d", value_d));
+ g_assert_cmpint(qnum_get_int(qnum), ==, value_d);
+ qobject_unref(qnum);
- qobject_unref(obj);
- qobject_unref(null);
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%ld", value_ld));
+ g_assert_cmpint(qnum_get_int(qnum), ==, value_ld);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%lld", value_lld));
+ g_assert_cmpint(qnum_get_int(qnum), ==, value_lld);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%" PRId64, value_d64));
+ g_assert_cmpint(qnum_get_int(qnum), ==, value_lld);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%u", value_u));
+ g_assert_cmpuint(qnum_get_uint(qnum), ==, value_u);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%lu", value_lu));
+ g_assert_cmpuint(qnum_get_uint(qnum), ==, value_lu);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%llu", value_llu));
+ g_assert_cmpuint(qnum_get_uint(qnum), ==, value_llu);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%" PRIu64, value_u64));
+ g_assert_cmpuint(qnum_get_uint(qnum), ==, value_llu);
+ qobject_unref(qnum);
+
+ qnum = qobject_to(QNum, qobject_from_jsonf_nofail("%f", value_f));
+ g_assert(qnum_get_double(qnum) == value_f);
+ qobject_unref(qnum);
+
+ /* string */
+
+ qstr = qobject_to(QString,
+ qobject_from_jsonf_nofail("%s", value_s));
+ g_assert_cmpstr(qstring_get_try_str(qstr), ==, value_s);
+ qobject_unref(qstr);
+
+ /* object */
+
+ qobj = qobject_from_jsonf_nofail("%p", value_p);
+ g_assert(qobj == value_p);
+}
+
+static void interpolation_unknown(void)
+{
+ if (g_test_subprocess()) {
+ qobject_from_jsonf_nofail("%x", 666);
+ }
+ g_test_trap_subprocess(NULL, 0, 0);
+ g_test_trap_assert_failed();
+ g_test_trap_assert_stderr("*Unexpected error*"
+ "invalid interpolation '%x'*");
+}
+
+static void interpolation_string(void)
+{
+ if (g_test_subprocess()) {
+ qobject_from_jsonf_nofail("['%s', %s]", "eins", "zwei");
+ }
+ g_test_trap_subprocess(NULL, 0, 0);
+ g_test_trap_assert_failed();
+ g_test_trap_assert_stderr("*Unexpected error*"
+ "can't interpolate into string*");
}
static void simple_dict(void)
}
}
-static void simple_varargs(void)
+static void simple_interpolation(void)
{
QObject *embedded_obj;
QObject *obj;
QLitObject decoded = QLIT_QLIST(((QLitObject[]){
QLIT_QNUM(1),
- QLIT_QNUM(2),
+ QLIT_QSTR("100%"),
QLIT_QLIST(((QLitObject[]){
QLIT_QNUM(32),
QLIT_QNUM(42),
embedded_obj = qobject_from_json("[32, 42]", &error_abort);
g_assert(embedded_obj != NULL);
- obj = qobject_from_jsonf_nofail("[%d, 2, %p]", 1, embedded_obj);
+ obj = qobject_from_jsonf_nofail("[%d, '100%%', %p]", 1, embedded_obj);
g_assert(qlit_equal_qobject(&decoded, obj));
qobject_unref(obj);
static void empty_input(void)
{
- QObject *obj = qobject_from_json("", &error_abort);
+ Error *err = NULL;
+ QObject *obj;
+
+ obj = qobject_from_json("", &err);
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
static void blank_input(void)
{
- QObject *obj = qobject_from_json("\n ", &error_abort);
+ Error *err = NULL;
+ QObject *obj;
+
+ obj = qobject_from_json("\n ", &err);
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
QObject *obj;
obj = qobject_from_json("@", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
+ g_assert(obj == NULL);
+
+ obj = qobject_from_json("{\x01", &err);
+ error_free_or_abort(&err);
g_assert(obj == NULL);
obj = qobject_from_json("[0\xFF]", &err);
g_assert(obj == NULL);
obj = qobject_from_json("00", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
obj = qobject_from_json("[1e", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
obj = qobject_from_json("truer", &err);
{
Error *err = NULL;
QObject *obj = qobject_from_json("\"abc", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("'abc", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("\"abc\\\"", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("[32", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("[32,", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("{'abc':32", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
{
Error *err = NULL;
QObject *obj = qobject_from_json("{'abc':32,", &err);
- g_assert(!err); /* BUG */
+ error_free_or_abort(&err);
g_assert(obj == NULL);
}
Error *err = NULL;
QObject *obj;
- /* BUG this leaks the syntax tree for "false" */
obj = qobject_from_json("false true", &err);
- g_assert(qbool_get_bool(qobject_to(QBool, obj)));
- g_assert(!err);
- qobject_unref(obj);
+ error_free_or_abort(&err);
+ g_assert(obj == NULL);
- /* BUG simultaneously succeeds and fails */
- /* BUG calls json_parser_parse() with errp pointing to non-null */
obj = qobject_from_json("} true", &err);
- g_assert(qbool_get_bool(qobject_to(QBool, obj)));
error_free_or_abort(&err);
- qobject_unref(obj);
+ g_assert(obj == NULL);
}
int main(int argc, char **argv)
g_test_add_func("/literals/string/escaped", escaped_string);
g_test_add_func("/literals/string/quotes", string_with_quotes);
g_test_add_func("/literals/string/utf8", utf8_string);
- g_test_add_func("/literals/string/vararg", vararg_string);
g_test_add_func("/literals/number/simple", simple_number);
g_test_add_func("/literals/number/large", large_number);
g_test_add_func("/literals/number/float", float_number);
- g_test_add_func("/literals/number/vararg", vararg_number);
g_test_add_func("/literals/keyword", keyword_literal);
+ g_test_add_func("/literals/interpolation/valid", interpolation_valid);
+ g_test_add_func("/literals/interpolation/unkown", interpolation_unknown);
+ g_test_add_func("/literals/interpolation/string", interpolation_string);
+
g_test_add_func("/dicts/simple_dict", simple_dict);
g_test_add_func("/dicts/large_dict", large_dict);
g_test_add_func("/lists/simple_list", simple_list);
- g_test_add_func("/whitespace/simple_whitespace", simple_whitespace);
-
- g_test_add_func("/varargs/simple_varargs", simple_varargs);
+ g_test_add_func("/mixed/simple_whitespace", simple_whitespace);
+ g_test_add_func("/mixed/interpolation", simple_interpolation);
g_test_add_func("/errors/empty", empty_input);
g_test_add_func("/errors/blank", blank_input);
projects / mirror_qemu.git / blobdiff