amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-04 21:50:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Follow each binary format's UTF-8 rule: strict writers (CBOR/UBJSON/BJData/BSON), lenient readers (#5741)

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-10-04 12:13:48 +02:00
committed by GitHub
parent 40021f38fb
commit f56b418c56
32 changed files with 651 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/src/unit-bjdata.cpp
+37
View File
@@ -3906,6 +3906,43 @@ TEST_CASE("Universal Binary JSON Specification Examples 1")
CHECK(json::to_bjdata(j) == v);
CHECK(json::from_bjdata(v) == j);
}
SECTION("ill-formed UTF-8 (see #5529, #5651)")
{
// none of the binary format specs requires a decoder to reject
// ill-formed UTF-8 in a text string, so a value whose bytes are
// not valid UTF-8 (0xC0 0xAE is an overlong encoding of '.')
// round-trips byte for byte as a string value; to_bjdata() writes
// the bytes unchanged, as before 3.13.0, unless
// JSON_STRICT_BINARY_UTF8 is enabled (see
// unit-binary_utf8_strict.cpp)
const std::vector<uint8_t> v = {'S', 'i', 2, 0xc0, 0xae};
json j;
CHECK_NOTHROW(j = json::from_bjdata(v));
REQUIRE(j.is_string());
CHECK(j.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
CHECK_THROWS_AS(j.dump(), json::type_error&);
CHECK(json::from_bjdata(json::to_bjdata(j)) == j);
// the same bytes as an object key round-trip as well
const std::vector<uint8_t> v_key = {'{', 'i', 2, 0xc0, 0xae, 'i', 1, '}'};
json j_key;
CHECK_NOTHROW(j_key = json::from_bjdata(v_key));
REQUIRE(j_key.is_object());
CHECK(j_key.contains(std::string("\xc0\xae")));
CHECK(json::from_bjdata(json::to_bjdata(j_key)) == j_key);
CHECK(json::from_bjdata(json::to_bjdata(json("\xFF"))) == json("\xFF"));
// a truncated multi-byte sequence
CHECK(json::from_bjdata(json::to_bjdata(json("\xC3"))) == json("\xC3"));
// an encoded surrogate half (U+D800)
CHECK(json::from_bjdata(json::to_bjdata(json("\xED\xA0\x80"))) == json("\xED\xA0\x80"));
// an overlong encoding of '.'
CHECK(json::from_bjdata(json::to_bjdata(json("\xC0\xAF"))) == json("\xC0\xAF"));
// an object key with ill-formed UTF-8 is kept the same way
CHECK(json::from_bjdata(json::to_bjdata(json{{"\xFF", 1}})) == json{{"\xFF", 1}});
}
}
SECTION("Array Type")