amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-05 06:00:29 +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-bson.cpp
+37
View File
@@ -154,6 +154,43 @@ TEST_CASE("BSON")
#endif
}
SECTION("ill-formed UTF-8 (see #5529, #5651)")
{
// a BSON document {"s": "\xC0\xAE"} (0xC0 0xAE is an overlong
// encoding of '.'); the BSON spec does not require a decoder to
// reject ill-formed UTF-8 in a string value, so the reader hands the
// bytes back unchanged
const std::vector<uint8_t> v =
{
0x0F, 0x00, 0x00, 0x00, // document length
0x02, 's', 0x00, // type 0x02 (string), key "s"
0x03, 0x00, 0x00, 0x00, // string length (including null)
0xc0, 0xae, 0x00, // string content and its null terminator
0x00 // document terminator
};
json j;
CHECK_NOTHROW(j = json::from_bson(v));
REQUIRE(j.is_object());
REQUIRE(j.contains("s"));
CHECK(j["s"].get_ref<const json::string_t&>() == std::string("\xc0\xae"));
// dump() still requires valid UTF-8 and throws for such a value
CHECK_THROWS_AS(j.dump(), json::type_error&);
// to_bson() writes the bytes back unchanged, as before 3.13.0,
// unless JSON_STRICT_BINARY_UTF8 is enabled (see unit-binary_utf8_strict.cpp)
CHECK(json::from_bson(json::to_bson(j)) == j);
CHECK(json::from_bson(json::to_bson(json{{"s", "\xFF"}})) == json{{"s", "\xFF"}});
// a truncated multi-byte sequence
CHECK(json::from_bson(json::to_bson(json{{"s", "\xC3"}})) == json{{"s", "\xC3"}});
// an encoded surrogate half (U+D800)
CHECK(json::from_bson(json::to_bson(json{{"s", "\xED\xA0\x80"}})) == json{{"s", "\xED\xA0\x80"}});
// an overlong encoding of '.'
CHECK(json::from_bson(json::to_bson(json{{"s", "\xC0\xAF"}})) == json{{"s", "\xC0\xAF"}});
// an object key with ill-formed UTF-8 is kept as well
CHECK(json::from_bson(json::to_bson(json{{"\xFF", 1}})) == json{{"\xFF", 1}});
}
SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
{
// out_of_range.412 is thrown from a single shared helper