Known bugs in to_json():
* A start byte for a three-byte sequence followed by less than two
continuation bytes is split into one-byte sequences.
* Start bytes for sequences longer than three bytes get misinterpreted
as start bytes for three-byte sequences. Continuation bytes beyond
byte three become one-byte sequences.
This means all characters outside the BMP are decoded incorrectly.
* One-byte sequences with the MSB are put into the JSON string
verbatim when char is unsigned, producing invalid UTF-8. When char
is signed, they're replaced by "\\uFFFF" instead.
This includes \xFE, \xFF, and stray continuation bytes.
* Overlong sequences are happily accepted, unless screwed up by the
bugs above.
* Likewise, sequences encoding surrogate code points or noncharacters.
* Unlike other control characters, ASCII DEL is not escaped. Except
in overlong encodings.
My rewrite fixes them as follows:
* Malformed UTF-8 sequences are replaced.
Except the overlong encoding \xC0\x80 of U+0000 is still accepted.
Permits embedding NUL characters in C strings. This trick is known
as "Modified UTF-8".
* Sequences encoding code points beyond Unicode range are replaced.
* Sequences encoding code points beyond the BMP produce a surrogate
pair.
* Sequences encoding surrogate code points are replaced.
* Sequences encoding noncharacters are replaced.
* ASCII DEL is now always escaped.
The replacement character is U+FFFD.
Signed-off-by: Markus Armbruster <arm...@redhat.com>
---
qobject/qjson.c | 102 +++++++++++--------------
tests/check-qjson.c | 216 ++++++++++++++++++++++++----------------------------
2 files changed, 145 insertions(+), 173 deletions(-)
diff --git a/qobject/qjson.c b/qobject/qjson.c
index 83a6b4f..19085a1 100644
--- a/qobject/qjson.c
+++ b/qobject/qjson.c
@@ -136,68 +136,56 @@ static void to_json(const QObject *obj, QString *str, int
pretty, int indent)
case QTYPE_QSTRING: {
QString *val = qobject_to_qstring(obj);
const char *ptr;
+ int cp;
+ char buf[16];
+ char *end;
ptr = qstring_get_str(val);
qstring_append(str, "\"");
- while (*ptr) {
- if ((ptr[0] & 0xE0) == 0xE0 &&
- (ptr[1] & 0x80) && (ptr[2] & 0x80)) {
- uint16_t wchar;
- char escape[7];
-
- wchar = (ptr[0] & 0x0F) << 12;
- wchar |= (ptr[1] & 0x3F) << 6;
- wchar |= (ptr[2] & 0x3F);
- ptr += 2;
-
- snprintf(escape, sizeof(escape), "\\u%04X", wchar);
- qstring_append(str, escape);
- } else if ((ptr[0] & 0xE0) == 0xC0 && (ptr[1] & 0x80)) {
- uint16_t wchar;
- char escape[7];
-
- wchar = (ptr[0] & 0x1F) << 6;
- wchar |= (ptr[1] & 0x3F);
- ptr++;
-
- snprintf(escape, sizeof(escape), "\\u%04X", wchar);
- qstring_append(str, escape);
- } else switch (ptr[0]) {
- case '\"':
- qstring_append(str, "\\\"");
- break;
- case '\\':
- qstring_append(str, "\\\\");
- break;
- case '\b':
- qstring_append(str, "\\b");
- break;
- case '\f':
- qstring_append(str, "\\f");
- break;
- case '\n':
- qstring_append(str, "\\n");
- break;
- case '\r':
- qstring_append(str, "\\r");
- break;
- case '\t':
- qstring_append(str, "\\t");
- break;
- default: {
- if (ptr[0] <= 0x1F) {
- char escape[7];
- snprintf(escape, sizeof(escape), "\\u%04X", ptr[0]);
- qstring_append(str, escape);
- } else {
- char buf[2] = { ptr[0], 0 };
- qstring_append(str, buf);
- }
- break;
+
+ for (; *ptr; ptr = end) {
+ cp = mod_utf8_codepoint(ptr, 6, &end);
+ switch (cp) {
+ case '\"':
+ qstring_append(str, "\\\"");
+ break;
+ case '\\':
+ qstring_append(str, "\\\\");
+ break;
+ case '\b':
+ qstring_append(str, "\\b");
+ break;
+ case '\f':
+ qstring_append(str, "\\f");
+ break;
+ case '\n':
+ qstring_append(str, "\\n");
+ break;
+ case '\r':
+ qstring_append(str, "\\r");
+ break;
+ case '\t':
+ qstring_append(str, "\\t");
+ break;
+ default:
+ if (cp < 0) {
+ cp = 0xFFFD; /* replacement character */
}
+ if (cp > 0xFFFF) {
+ /* beyond BMP; need a surrogate pair */
+ snprintf(buf, sizeof(buf), "\\u%04X\\u%04X",
+ 0xD800 + ((cp - 0x10000) >> 10),
+ 0xDC00 + ((cp - 0x10000) & 0x3FF));
+ } else if (cp < 0x20 || cp >= 0x7F) {
+ snprintf(buf, sizeof(buf), "\\u%04X", cp);
+ } else {
+ buf[0] = cp;
+ buf[1] = 0;
}
- ptr++;
- }
+ qstring_append(str, buf);
+ }
+ };
+
qstring_append(str, "\"");
break;
}
diff --git a/tests/check-qjson.c b/tests/check-qjson.c
index efec1b2..595ddc0 100644
--- a/tests/check-qjson.c
+++ b/tests/check-qjson.c
@@ -144,13 +144,10 @@ static void utf8_string(void)
* The JSON parser rejects some invalid sequences, but accepts
* others without correcting the problem.
*
- * The JSON formatter replaces some invalid sequences by U+FFFF (a
- * noncharacter), and goes wonky for others.
- *
- * For both directions, 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.
+ * 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",
@@ -175,16 +172,10 @@ static void utf8_string(void)
* - bug: rejected
* JSON parser rejects invalid sequence(s)
* We may choose to define this as feature
- * - bug: want "\"...\""
- * JSON formatter produces incorrect result, this is the
- * correct one, assuming replacement character U+FFFF
- * - bug: want "..." (no \")
+ * - 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
- * Not marked explicitly, but trivial to find:
- * - JSON formatter replacing invalid sequence by \\uFFFF is a
- * bug if we want it to fail for invalid sequences.
*/
/* 1 Some correct UTF-8 text */
@@ -209,7 +200,8 @@ static void utf8_string(void)
{
"\"\\u0000\"",
"", /* bug: want overlong "\xC0\x80" */
- "\"\"", /* bug: want "\"\\u0000\"" */
+ "\"\\u0000\"",
+ "\xC0\x80",
},
/* 2.1.2 2 bytes U+0080 */
{
@@ -227,20 +219,20 @@ static void utf8_string(void)
{
"\"\xF0\x90\x80\x80\"",
"\xF0\x90\x80\x80",
- "\"\\u0400\\uFFFF\"", /* bug: want "\"\\uD800\\uDC00\"" */
+ "\"\\uD800\\uDC00\"",
},
/* 2.1.5 5 bytes U+200000 */
{
"\"\xF8\x88\x80\x80\x80\"",
- NULL, /* bug: rejected */
- "\"\\u8200\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ NULL, /* bug: rejected */
+ "\"\\uFFFD\"",
"\xF8\x88\x80\x80\x80",
},
/* 2.1.6 6 bytes U+4000000 */
{
"\"\xFC\x84\x80\x80\x80\x80\"",
- NULL, /* bug: rejected */
- "\"\\uC100\\uFFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ NULL, /* bug: rejected */
+ "\"\\uFFFD\"",
"\xFC\x84\x80\x80\x80\x80",
},
/* 2.2 Last possible sequence of a certain length */
@@ -248,7 +240,7 @@ static void utf8_string(void)
{
"\"\x7F\"",
"\x7F",
- "\"\177\"",
+ "\"\\u007F\"",
},
/* 2.2.2 2 bytes U+07FF */
{
@@ -265,22 +257,22 @@ static void utf8_string(void)
/* 2.2.4 4 bytes U+1FFFFF */
{
"\"\xF7\xBF\xBF\xBF\"",
- NULL, /* bug: rejected */
- "\"\\u7FFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ NULL, /* bug: rejected */
+ "\"\\uFFFD\"",
"\xF7\xBF\xBF\xBF",
},
/* 2.2.5 5 bytes U+3FFFFFF */
{
"\"\xFB\xBF\xBF\xBF\xBF\"",
- NULL, /* bug: rejected */
- "\"\\uBFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ NULL, /* bug: rejected */
+ "\"\\uFFFD\"",
"\xFB\xBF\xBF\xBF\xBF",
},
/* 2.2.6 6 bytes U+7FFFFFFF */
{
"\"\xFD\xBF\xBF\xBF\xBF\xBF\"",
- NULL, /* bug: rejected */
- "\"\\uDFFF\\uFFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ NULL, /* bug: rejected */
+ "\"\\uFFFD\"",
"\xFD\xBF\xBF\xBF\xBF\xBF",
},
/* 2.3 Other boundary conditions */
@@ -306,13 +298,13 @@ static void utf8_string(void)
/* U+10FFFD */
"\"\xF4\x8F\xBF\xBD\"",
"\xF4\x8F\xBF\xBD",
- "\"\\u43FF\\uFFFF\"", /* bug: want "\"\\uDBFF\\uDFFD\"" */
+ "\"\\uDBFF\\uDFFD\""
},
{
/* U+110000 */
"\"\xF4\x90\x80\x80\"",
"\xF4\x90\x80\x80",
- "\"\\u4400\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
/* 3 Malformed sequences */
/* 3.1 Unexpected continuation bytes */
@@ -320,49 +312,49 @@ static void utf8_string(void)
{
"\"\x80\"",
"\x80", /* bug: not corrected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
},
/* 3.1.2 Last continuation byte */
{
"\"\xBF\"",
"\xBF", /* bug: not corrected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
},
/* 3.1.3 2 continuation bytes */
{
"\"\x80\xBF\"",
"\x80\xBF", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\"",
+ "\"\\uFFFD\\uFFFD\"",
},
/* 3.1.4 3 continuation bytes */
{
"\"\x80\xBF\x80\"",
"\x80\xBF\x80", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\\uFFFF\"",
+ "\"\\uFFFD\\uFFFD\\uFFFD\"",
},
/* 3.1.5 4 continuation bytes */
{
"\"\x80\xBF\x80\xBF\"",
"\x80\xBF\x80\xBF", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"",
+ "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
},
/* 3.1.6 5 continuation bytes */
{
"\"\x80\xBF\x80\xBF\x80\"",
"\x80\xBF\x80\xBF\x80", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"",
+ "\"\\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 */
- "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"",
+ "\"\\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 */
- "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"",
+ "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
},
/* 3.1.9 Sequence of all 64 possible continuation bytes */
{
@@ -383,14 +375,14 @@ static void utf8_string(void)
"\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
"\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
"\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
- "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\""
+ "\"\\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"
+ "\\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 */
@@ -400,10 +392,10 @@ static void utf8_string(void)
"\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
"\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF \"",
NULL, /* bug: rejected */
- "\"\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF
"
- "\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF "
- "\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF "
- "\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF
\"",
+ "\"\\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 "
@@ -416,28 +408,28 @@ static void utf8_string(void)
/* bug: not corrected */
"\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
"\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
- "\"\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF
"
- "\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF
\"",
+ "\"\\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 */
- "\"\\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF \\uFFFF
\"",
+ "\"\\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 */
- "\"\\uFFFF \\uFFFF \\uFFFF \\uFFFF \"",
+ "\"\\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 */
- "\"\\uFFFF \\uFFFF \"",
+ "\"\\uFFFD \\uFFFD \"",
"\xFC \xFD ",
},
/* 3.3 Sequences with last continuation byte missing */
@@ -445,66 +437,66 @@ static void utf8_string(void)
{
"\"\xC0\"",
NULL, /* bug: rejected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
"\xC0",
},
/* 3.3.2 3-byte sequence with last byte missing (U+0000) */
{
"\"\xE0\x80\"",
"\xE0\x80", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
/* 3.3.3 4-byte sequence with last byte missing (U+0000) */
{
"\"\xF0\x80\x80\"",
"\xF0\x80\x80", /* bug: not corrected */
- "\"\\u0000\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
/* 3.3.4 5-byte sequence with last byte missing (U+0000) */
{
"\"\xF8\x80\x80\x80\"",
NULL, /* bug: rejected */
- "\"\\u8000\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\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 */
- "\"\\uC000\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
"\xFC\x80\x80\x80\x80",
},
/* 3.3.6 2-byte sequence with last byte missing (U+07FF) */
{
"\"\xDF\"",
"\xDF", /* bug: not corrected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
},
/* 3.3.7 3-byte sequence with last byte missing (U+FFFF) */
{
"\"\xEF\xBF\"",
"\xEF\xBF", /* bug: not corrected */
- "\"\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
/* 3.3.8 4-byte sequence with last byte missing (U+1FFFFF) */
{
"\"\xF7\xBF\xBF\"",
NULL, /* bug: rejected */
- "\"\\u7FFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
"\xF7\xBF\xBF",
},
/* 3.3.9 5-byte sequence with last byte missing (U+3FFFFFF) */
{
"\"\xFB\xBF\xBF\xBF\"",
NULL, /* bug: rejected */
- "\"\\uBFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\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 */
- "\"\\uDFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"", */
+ "\"\\uFFFD\"",
"\xFD\xBF\xBF\xBF\xBF",
},
/* 3.4 Concatenation of incomplete sequences */
@@ -512,10 +504,8 @@ static void utf8_string(void)
"\"\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 */
- /* bug: want "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF"
- "\\uFFFF\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"" */
- "\"\\u0020\\uFFFF\\u0000\\u8000\\uFFFF\\uC000\\uFFFF\\uFFFF"
- "\\u07EF\\uFFFF\\u7FFF\\uBFFF\\uFFFF\\uDFFF\\uFFFF\\uFFFF\"",
+ "\"\\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",
},
@@ -523,20 +513,19 @@ static void utf8_string(void)
{
"\"\xFE\"",
NULL, /* bug: rejected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
"\xFE",
},
{
"\"\xFF\"",
NULL, /* bug: rejected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
"\xFF",
},
{
"\"\xFE\xFE\xFF\xFF\"",
NULL, /* bug: rejected */
- /* bug: want "\"\\uFFFF\\uFFFF\\uFFFF\\uFFFF\"" */
- "\"\\uEFBF\\uFFFF\"",
+ "\"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\"",
"\xFE\xFE\xFF\xFF",
},
/* 4 Overlong sequences */
@@ -544,29 +533,29 @@ static void utf8_string(void)
{
"\"\xC0\xAF\"",
NULL, /* bug: rejected */
- "\"\\u002F\"", /* bug: want "\"/\"" */
+ "\"\\uFFFD\"",
"\xC0\xAF",
},
{
"\"\xE0\x80\xAF\"",
"\xE0\x80\xAF", /* bug: not corrected */
- "\"\\u002F\"", /* bug: want "\"/\"" */
+ "\"\\uFFFD\"",
},
{
"\"\xF0\x80\x80\xAF\"",
"\xF0\x80\x80\xAF", /* bug: not corrected */
- "\"\\u0000\\uFFFF\"" /* bug: want "\"/\"" */
+ "\"\\uFFFD\"",
},
{
"\"\xF8\x80\x80\x80\xAF\"",
NULL, /* bug: rejected */
- "\"\\u8000\\uFFFF\\uFFFF\"", /* bug: want "\"/\"" */
+ "\"\\uFFFD\"",
"\xF8\x80\x80\x80\xAF",
},
{
"\"\xFC\x80\x80\x80\x80\xAF\"",
NULL, /* bug: rejected */
- "\"\\uC000\\uFFFF\\uFFFF\\uFFFF\"", /* bug: want "\"/\"" */
+ "\"\\uFFFD\"",
"\xFC\x80\x80\x80\x80\xAF",
},
/* 4.2 Maximum overlong sequences */
@@ -574,33 +563,33 @@ static void utf8_string(void)
/* \U+007F */
"\"\xC1\xBF\"",
NULL, /* bug: rejected */
- "\"\\u007F\"", /* bug: want "\"\177\"" */
+ "\"\\uFFFD\"",
"\xC1\xBF",
},
{
/* \U+07FF */
"\"\xE0\x9F\xBF\"",
"\xE0\x9F\xBF", /* bug: not corrected */
- "\"\\u07FF\"",
+ "\"\\uFFFD\"",
},
{
/* \U+FFFD */
"\"\xF0\x8F\xBF\xBD\"",
"\xF0\x8F\xBF\xBD", /* bug: not corrected */
- "\"\\u03FF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+1FFFFF */
"\"\xF8\x87\xBF\xBF\xBF\"",
NULL, /* bug: rejected */
- "\"\\u81FF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
"\xF8\x87\xBF\xBF\xBF",
},
{
/* \U+3FFFFFF */
"\"\xFC\x83\xBF\xBF\xBF\xBF\"",
NULL, /* bug: rejected */
- "\"\\uC0FF\\uFFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
"\xFC\x83\xBF\xBF\xBF\xBF",
},
/* 4.3 Overlong representation of the NUL character */
@@ -615,26 +604,26 @@ static void utf8_string(void)
/* \U+0000 */
"\"\xE0\x80\x80\"",
"\xE0\x80\x80", /* bug: not corrected */
- "\"\\u0000\"",
+ "\"\\uFFFD\"",
},
{
/* \U+0000 */
"\"\xF0\x80\x80\x80\"",
"\xF0\x80\x80\x80", /* bug: not corrected */
- "\"\\u0000\\uFFFF\"", /* bug: want "\"\\u0000\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+0000 */
"\"\xF8\x80\x80\x80\x80\"",
NULL, /* bug: rejected */
- "\"\\u8000\\uFFFF\\uFFFF\"", /* bug: want "\"\\u0000\"" */
+ "\"\\uFFFD\"",
"\xF8\x80\x80\x80\x80",
},
{
/* \U+0000 */
"\"\xFC\x80\x80\x80\x80\x80\"",
NULL, /* bug: rejected */
- "\"\\uC000\\uFFFF\\uFFFF\\uFFFF\"", /* bug: want "\"\\u0000\"" */
+ "\"\\uFFFD\"",
"\xFC\x80\x80\x80\x80\x80",
},
/* 5 Illegal code positions */
@@ -643,92 +632,92 @@ static void utf8_string(void)
/* \U+D800 */
"\"\xED\xA0\x80\"",
"\xED\xA0\x80", /* bug: not corrected */
- "\"\\uD800\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DB7F */
"\"\xED\xAD\xBF\"",
"\xED\xAD\xBF", /* bug: not corrected */
- "\"\\uDB7F\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DB80 */
"\"\xED\xAE\x80\"",
"\xED\xAE\x80", /* bug: not corrected */
- "\"\\uDB80\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DBFF */
"\"\xED\xAF\xBF\"",
"\xED\xAF\xBF", /* bug: not corrected */
- "\"\\uDBFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DC00 */
"\"\xED\xB0\x80\"",
"\xED\xB0\x80", /* bug: not corrected */
- "\"\\uDC00\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DF80 */
"\"\xED\xBE\x80\"",
"\xED\xBE\x80", /* bug: not corrected */
- "\"\\uDF80\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\uFFFD\"",
},
{
/* \U+DFFF */
"\"\xED\xBF\xBF\"",
"\xED\xBF\xBF", /* bug: not corrected */
- "\"\\uDFFF\"", /* bug: want "\"\\uFFFF\"" */
+ "\"\\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 */
- "\"\\uD800\\uDC00\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+D800\U+DFFF */
"\"\xED\xA0\x80\xED\xBF\xBF\"",
"\xED\xA0\x80\xED\xBF\xBF", /* bug: not corrected */
- "\"\\uD800\\uDFFF\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DB7F\U+DC00 */
"\"\xED\xAD\xBF\xED\xB0\x80\"",
"\xED\xAD\xBF\xED\xB0\x80", /* bug: not corrected */
- "\"\\uDB7F\\uDC00\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DB7F\U+DFFF */
"\"\xED\xAD\xBF\xED\xBF\xBF\"",
"\xED\xAD\xBF\xED\xBF\xBF", /* bug: not corrected */
- "\"\\uDB7F\\uDFFF\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DB80\U+DC00 */
"\"\xED\xAE\x80\xED\xB0\x80\"",
"\xED\xAE\x80\xED\xB0\x80", /* bug: not corrected */
- "\"\\uDB80\\uDC00\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DB80\U+DFFF */
"\"\xED\xAE\x80\xED\xBF\xBF\"",
"\xED\xAE\x80\xED\xBF\xBF", /* bug: not corrected */
- "\"\\uDB80\\uDFFF\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DBFF\U+DC00 */
"\"\xED\xAF\xBF\xED\xB0\x80\"",
"\xED\xAF\xBF\xED\xB0\x80", /* bug: not corrected */
- "\"\\uDBFF\\uDC00\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
{
/* \U+DBFF\U+DFFF */
"\"\xED\xAF\xBF\xED\xBF\xBF\"",
"\xED\xAF\xBF\xED\xBF\xBF", /* bug: not corrected */
- "\"\\uDBFF\\uDFFF\"", /* bug: want "\"\\uFFFF\\uFFFF\"" */
+ "\"\\uFFFD\\uFFFD\"",
},
/* 5.3 Other illegal code positions */
/* BMP noncharacters */
@@ -736,25 +725,25 @@ static void utf8_string(void)
/* \U+FFFE */
"\"\xEF\xBF\xBE\"",
"\xEF\xBF\xBE", /* bug: not corrected */
- "\"\\uFFFE\"", /* bug: not corrected */
+ "\"\\uFFFD\"",
},
{
/* \U+FFFF */
"\"\xEF\xBF\xBF\"",
"\xEF\xBF\xBF", /* bug: not corrected */
- "\"\\uFFFF\"",
+ "\"\\uFFFD\"",
},
{
/* U+FDD0 */
"\"\xEF\xB7\x90\"",
"\xEF\xB7\x90", /* bug: not corrected */
- "\"\\uFDD0\"", /* bug: not corrected */
+ "\"\\uFFFD\"",
},
{
/* U+FDEF */
"\"\xEF\xB7\xAF\"",
"\xEF\xB7\xAF", /* bug: not corrected */
- "\"\\uFDEF\"", /* bug: not corrected */
+ "\"\\uFFFD\"",
},
/* Plane 1 .. 16 noncharacters */
{
@@ -792,15 +781,10 @@ static void utf8_string(void)
"\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 */
- "\"\\u07FF\\uFFFF\\u07FF\\uFFFF\\u0BFF\\uFFFF\\u0BFF\\uFFFF"
- "\\u0FFF\\uFFFF\\u0FFF\\uFFFF\\u13FF\\uFFFF\\u13FF\\uFFFF"
- "\\u17FF\\uFFFF\\u17FF\\uFFFF\\u1BFF\\uFFFF\\u1BFF\\uFFFF"
- "\\u1FFF\\uFFFF\\u1FFF\\uFFFF\\u23FF\\uFFFF\\u23FF\\uFFFF"
- "\\u27FF\\uFFFF\\u27FF\\uFFFF\\u2BFF\\uFFFF\\u2BFF\\uFFFF"
- "\\u2FFF\\uFFFF\\u2FFF\\uFFFF\\u33FF\\uFFFF\\u33FF\\uFFFF"
- "\\u37FF\\uFFFF\\u37FF\\uFFFF\\u3BFF\\uFFFF\\u3BFF\\uFFFF"
- "\\u3FFF\\uFFFF\\u3FFF\\uFFFF\\u43FF\\uFFFF\\u43FF\\uFFFF\"",
+ "\"\\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\"",
},
{}
};
@@ -838,8 +822,8 @@ static void utf8_string(void)
qobject_decref(obj);
/*
- * Disabled, because json_out currently contains the crap
- * qobject_to_json() produces.
+ * 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) {
--
1.7.11.7
