Merge branch 'develop' into claude/binary-utf8-roundtrip-5651

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-10-01 07:44:29 +02:00
295 changed files with 5316 additions and 15043 deletions
+43 -96
View File
@@ -18,85 +18,11 @@ using nlohmann::json;
#include <list>
#include <set>
#include "make_test_data_available.hpp"
#include "round_trip_corpus.hpp"
#include "test_utils.hpp"
#include "sax_countdown.hpp"
using utils::SaxCountdown;
namespace
{
class SaxCountdown
{
public:
explicit SaxCountdown(const int count) : events_left(count)
{}
bool null()
{
return events_left-- > 0;
}
bool boolean(bool /*unused*/)
{
return events_left-- > 0;
}
bool number_integer(json::number_integer_t /*unused*/)
{
return events_left-- > 0;
}
bool number_unsigned(json::number_unsigned_t /*unused*/)
{
return events_left-- > 0;
}
bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
{
return events_left-- > 0;
}
bool string(std::string& /*unused*/)
{
return events_left-- > 0;
}
bool binary(std::vector<std::uint8_t>& /*unused*/)
{
return events_left-- > 0;
}
bool start_object(std::size_t /*unused*/)
{
return events_left-- > 0;
}
bool key(std::string& /*unused*/)
{
return events_left-- > 0;
}
bool end_object()
{
return events_left-- > 0;
}
bool start_array(std::size_t /*unused*/)
{
return events_left-- > 0;
}
bool end_array()
{
return events_left-- > 0;
}
bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
{
return false;
}
private:
int events_left = 0;
};
} // namespace
TEST_CASE("CBOR")
{
@@ -2434,6 +2360,39 @@ TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
}
}
TEST_CASE("CBOR round-trip invariants")
{
// This checks what the parse_cbor_fuzzer driver checks (see
// tests/src/fuzzer-parse_cbor.cpp), so that a regression shows up in CI
// rather than as an OSS-Fuzz report: anything from_cbor() returns (j1)
// can be serialized, parsed back (j2), and serialized again to reproduce
// the exact bytes.
for (const auto& j0 : utils::round_trip_corpus::values())
{
json j1;
try
{
// turn the corpus value into a value as from_cbor() returns it
j1 = json::from_cbor(json::to_cbor(j0));
}
catch (const json::exception&)
{
// not every corpus value survives a CBOR round trip (e.g., a
// binary subtype is written with a tag the default tag handler
// then rejects); the fuzzer driver only ever sees values
// from_cbor() actually produced, so skip those here, too
continue;
}
INFO("j1 = " << j1.dump());
const std::vector<std::uint8_t> vec = json::to_cbor(j1);
json j2;
// anything the library writes must be parsable by the library
REQUIRE_NOTHROW(j2 = json::from_cbor(vec));
CHECK(json::to_cbor(j2) == vec);
}
}
TEST_CASE("CBOR roundtrips" * doctest::skip())
{
SECTION("input from flynn")
@@ -2793,33 +2752,21 @@ TEST_CASE("examples from RFC 8949 Appendix A")
CHECK(json::to_cbor(json::parse("1.1")) == std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a}));
CHECK(json::parse("1.1") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a})));
// half-precision float
//CHECK(json::to_cbor(json::parse("1.5")) == std::vector<uint8_t>({0xf9, 0x3e, 0x00}));
// the writer never emits half-precision floats, so these can only be decoded, not encoded
CHECK(json::parse("1.5") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x3e, 0x00})));
// half-precision float
//CHECK(json::to_cbor(json::parse("65504.0")) == std::vector<uint8_t>({0xf9, 0x7b, 0xff}));
CHECK(json::parse("65504.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x7b, 0xff})));
//CHECK(json::to_cbor(json::parse("100000.0")) == std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00}));
CHECK(json::to_cbor(json::parse("100000.0")) == std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00}));
CHECK(json::parse("100000.0") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00})));
//CHECK(json::to_cbor(json::parse("3.4028234663852886e+38")) == std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff}));
CHECK(json::to_cbor(json::parse("3.4028234663852886e+38")) == std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff}));
CHECK(json::parse("3.4028234663852886e+38") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff})));
CHECK(json::to_cbor(json::parse("1.0e+300")) == std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c}));
CHECK(json::parse("1.0e+300") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c})));
// half-precision float
//CHECK(json::to_cbor(json::parse("5.960464477539063e-8")) == std::vector<uint8_t>({0xf9, 0x00, 0x01}));
CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
// half-precision float
//CHECK(json::to_cbor(json::parse("0.00006103515625")) == std::vector<uint8_t>({0xf9, 0x04, 0x00}));
CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
// half-precision float
//CHECK(json::to_cbor(json::parse("-4.0")) == std::vector<uint8_t>({0xf9, 0xc4, 0x00}));
CHECK(json::parse("5.960464477539063e-8") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x01})));
CHECK(json::parse("0.00006103515625") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x04, 0x00})));
CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
CHECK(json::to_cbor(json::parse("-4.1")) == std::vector<uint8_t>({0xfb, 0xc0, 0x10, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66}));
@@ -2950,7 +2897,7 @@ TEST_CASE("Tagged values")
0xD5, 0xD6, 0xD7
})
{
CAPTURE(b);
CAPTURE(b)
// add tag to value
auto v_tagged = v;
@@ -3290,7 +3237,7 @@ TEST_CASE("CBOR large strings and binaries (chunked reader)")
std::size_t{4097}, std::size_t{8192}, std::size_t{100000}
})
{
CAPTURE(len);
CAPTURE(len)
// text string
const json j_string = std::string(len, 'x');