wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-11-04 13:38:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Cut Unicode ill-formed byte sweeps to one representative prefix

Browse Source 
Wrong-2nd and wrong-3rd-byte sections iterated every valid trailing
byte, which dominated Linux --no-skip runtime without testing extra
properties. Pin those bytes to a single valid continuation.

The fourth-byte typo is left to #5416 so this change stands alone.

Signed-off-by: elix3r <157088510+22elix3r@users.noreply.github.com>
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
elix3r authored and Niels Lohmann committed 2026-09-27 21:44:47 +02:00
1 parent 373005f7ac
commit c6bb0844f3
3 files changed
+65 -85
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/src/unit-unicode4.cpp
+17 -21
View File
@@ -250,6 +250,11 @@ TEST_CASE("Unicode (4/5)" * doctest::skip())
SECTION("ill-formed: wrong second byte")
{
// Pin later continuation bytes; the 2nd-byte property does not
// depend on them. Lead bytes F1-F3 stay, as they define this
// sequence class (#5418).
const int byte3 = 0x80;
const int byte4 = 0x80;
for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
{
for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
@@ -260,38 +265,29 @@ TEST_CASE("Unicode (4/5)" * doctest::skip())
continue;
}
for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
{
for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
{
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
}
SECTION("ill-formed: wrong third byte")
{
// Pin 2nd/4th bytes to one valid continuation (#5418).
const int byte2 = 0x80;
const int byte4 = 0x80;
for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
{
for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
{
for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
// skip correct third byte
if (0x80 <= byte3 && byte3 <= 0xBF)
{
// skip correct third byte
if (0x80 <= byte3 && byte3 <= 0xBF)
{
continue;
}
for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
{
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
continue;
}
check_utf8string(false, byte1, byte2, byte3, byte4);
check_utf8dump(false, byte1, byte2, byte3, byte4);
}
}
}