The JSON parser treats each half of a surrogate pair as unpaired
surrogate. Fix it to recognize surrogate pairs.
Signed-off-by: Markus Armbruster <arm...@redhat.com>
---
qobject/json-parser.c | 16 +++++++++++++++-
tests/check-qjson.c | 3 +--
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/qobject/json-parser.c b/qobject/json-parser.c
index bb54886809..703065fa2b 100644
--- a/qobject/json-parser.c
+++ b/qobject/json-parser.c
@@ -115,7 +115,7 @@ static QString *parse_string(JSONParserContext *ctxt,
JSONToken *token)
const char *ptr = token->str;
QString *str;
char quote;
- int cp, i;
+ int cp, i, leading_surrogate;
char *end;
ssize_t len;
char utf8_buf[5];
@@ -156,6 +156,8 @@ static QString *parse_string(JSONParserContext *ctxt,
JSONToken *token)
qstring_append_chr(str, '\t');
break;
case 'u':
+ leading_surrogate = 0;
+ hex:
cp = 0;
for (i = 0; i < 4; i++) {
ptr++;
@@ -168,6 +170,18 @@ static QString *parse_string(JSONParserContext *ctxt,
JSONToken *token)
cp |= hex2decimal(*ptr);
}
+ if (cp >= 0xD800 && cp <= 0xDBFF && !leading_surrogate
+ && ptr[1] == '\\' && ptr[2] == 'u') {
+ ptr += 2;
+ leading_surrogate = cp;
+ goto hex;
+ }
+ if (cp >= 0xDC00 && cp <= 0xDFFF && leading_surrogate) {
+ cp &= 0x3FF;
+ cp |= (leading_surrogate & 0x3FF) << 10;
+ cp += 0x010000;
+ }
+
if (mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp) < 0) {
parse_error(ctxt, token,
"\\u%.4s is not a valid Unicode character",
diff --git a/tests/check-qjson.c b/tests/check-qjson.c
index 422697459f..3d3a3f105f 100644
--- a/tests/check-qjson.c
+++ b/tests/check-qjson.c
@@ -61,8 +61,7 @@ static void escaped_string(void)
{ "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 */
- NULL },
+ "quadruple byte utf-8 \xF0\x9D\x84\x9E" },
{ "\\z", NULL },
{ "\\ux", NULL },
{ "\\u1x", NULL },
--
2.17.1
