Merge branch 'develop' into claude/issue-5387-duplicate-check-bd7853

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-09-23 20:01:45 +02:00
14 changed files with 1713 additions and 484 deletions
+198
View File
@@ -0,0 +1,198 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++ (supporting code)
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#include "doctest_compatibility.h"
#include <nlohmann/json.hpp>
using nlohmann::json;
#include <cstdint>
#include <string>
#include <vector>
namespace
{
// a spread of values exercising every writer path: scalars of each width, the
// float paths, strings, binary, and containers big enough to reallocate
std::vector<json> test_values()
{
json big_array = json::array();
for (int i = 0; i < 5000; ++i)
{
big_array.push_back(i);
}
json big_object = json::object();
for (int i = 0; i < 1000; ++i)
{
big_object[std::to_string(i)] = i;
}
return
{
json(nullptr), json(true), json(false),
json(0), json(-1), json(255), json(-129), json(65535), json(-32769),
json(4294967295U), json(-2147483649LL), json(18446744073709551615ULL),
json(0.0), json(-0.5), json(3.1415926535897932),
json(""), json("hello"), json(std::string(1000, 'x')),
json::binary({0x00, 0x01, 0x02}, 42),
json::array(), json::object(),
json::array({1, 2, 3}), json({{"a", 1}, {"b", nullptr}}),
json({{"nested", {{"deep", json::array({1, "two", 3.0, nullptr})}}}}),
big_array, big_object
};
}
// values to_bson() accepts: the document must be an object
std::vector<json> bson_values()
{
json big_object = json::object();
for (int i = 0; i < 1000; ++i)
{
big_object[std::to_string(i)] = i;
}
return
{
json::object(),
json({{"a", 1}, {"b", nullptr}, {"c", true}, {"d", 2.5}, {"e", "text"}}),
json({{"arr", json::array({1, 2, 3})}, {"obj", {{"k", "v"}}}}),
big_object
};
}
} // namespace
// The vector-returning to_*(j) overloads write through the non-virtual
// output_vector_sink, while to_*(j, adapter) goes through output_adapter_sink.
// The two are separate code paths that must stay byte-for-byte identical; these
// checks fail if either overload is ever changed without the other.
TEST_CASE("binary writer output sinks")
{
SECTION("vector sink and adapter sink agree")
{
// note: no SUBCASE inside these loops - doctest keys subcases by
// name/file/line, so a subcase in a loop body would only ever run for
// the first iteration
for (const auto& j : test_values())
{
CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
std::vector<std::uint8_t> cbor;
json::to_cbor(j, cbor);
CHECK(json::to_cbor(j) == cbor);
std::vector<std::uint8_t> msgpack;
json::to_msgpack(j, msgpack);
CHECK(json::to_msgpack(j) == msgpack);
for (const bool use_size :
{
false, true
})
{
for (const bool use_type :
{
false, true
})
{
if (use_type && !use_size)
{
continue; // not a supported combination
}
CAPTURE(use_size);
CAPTURE(use_type);
std::vector<std::uint8_t> ubjson;
json::to_ubjson(j, ubjson, use_size, use_type);
CHECK(json::to_ubjson(j, use_size, use_type) == ubjson);
}
}
for (const auto version :
{
json::bjdata_version_t::draft2, json::bjdata_version_t::draft3
})
{
std::vector<std::uint8_t> bjdata;
json::to_bjdata(j, bjdata, false, false, version);
CHECK(json::to_bjdata(j, false, false, version) == bjdata);
}
}
for (const auto& j : bson_values())
{
CAPTURE(j.dump());
std::vector<std::uint8_t> bson;
json::to_bson(j, bson);
CHECK(json::to_bson(j) == bson);
}
}
SECTION("the char adapter produces the same bytes")
{
for (const auto& j : test_values())
{
CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
const std::vector<std::uint8_t> expected = json::to_cbor(j);
std::vector<char> as_char;
json::to_cbor(j, as_char);
REQUIRE(as_char.size() == expected.size());
std::vector<std::uint8_t> as_bytes;
as_bytes.reserve(as_char.size());
for (const char c : as_char)
{
as_bytes.push_back(static_cast<std::uint8_t>(c));
}
CHECK(as_bytes == expected);
}
}
}
// binary_reserve_hint() is documented as a *lower* bound on the serialized size,
// so that reserving it up front can never leave the returned vector holding
// capacity beyond what the value actually needs.
TEST_CASE("binary_reserve_hint never over-reserves")
{
for (const auto& j : test_values())
{
CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
const std::size_t hint = nlohmann::detail::binary_reserve_hint(j);
CHECK(hint <= json::to_cbor(j).size());
CHECK(hint <= json::to_msgpack(j).size());
CHECK(hint <= json::to_ubjson(j).size());
CHECK(hint <= json::to_ubjson(j, true, true).size());
CHECK(hint <= json::to_bjdata(j).size());
}
for (const auto& j : bson_values())
{
CAPTURE(j.dump());
CHECK(nlohmann::detail::binary_reserve_hint(j) <= json::to_bson(j).size());
}
SECTION("scalars get no hint")
{
CHECK(nlohmann::detail::binary_reserve_hint(json(nullptr)) == 0);
CHECK(nlohmann::detail::binary_reserve_hint(json(42)) == 0);
CHECK(nlohmann::detail::binary_reserve_hint(json("a string")) == 0);
CHECK(nlohmann::detail::binary_reserve_hint(json::binary({0x01})) == 0);
}
SECTION("containers are hinted from their element count")
{
CHECK(nlohmann::detail::binary_reserve_hint(json::array()) == 1);
CHECK(nlohmann::detail::binary_reserve_hint(json::array({1, 2, 3})) == 4);
CHECK(nlohmann::detail::binary_reserve_hint(json::object()) == 1);
CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
}
}
+9
View File
@@ -791,6 +791,15 @@ TEST_CASE("BSON")
}
}
TEST_CASE("regression test - BSON binary subtype rejects a value that doesn't fit a single byte")
{
json const doc255 = {{"b", json::binary({1, 2}, 255)}};
CHECK(json::from_bson(json::to_bson(doc255))["b"].get_binary().subtype() == 255);
CHECK_THROWS_AS(json::to_bson(json{{"b", json::binary({1, 2}, 256)}}), json::out_of_range);
CHECK_THROWS_WITH_AS(json::to_bson(json{{"b", json::binary({1, 2}, 300)}}), "[json.exception.out_of_range.415] subtype 300 is too large for the BSON binary subtype (max 255)", json::out_of_range);
}
TEST_CASE("BSON input/output_adapters")
{
const json json_representation =
+15 -80
View File
@@ -2261,86 +2261,6 @@ TEST_CASE("parser class")
#endif
}
#if JSON_DIAGNOSTIC_POSITIONS
TEST_CASE("diagnostic positions: value lifetime")
{
SECTION("copy constructor copies positions, recursively")
{
const std::string s = R"({"a":1,"b":[1,2,3]})";
const json a = json::parse(s);
const json b = a; // NOLINT(performance-unnecessary-copy-initialization)
CHECK(b.start_pos() == a.start_pos());
CHECK(b.end_pos() == a.end_pos());
CHECK(b["b"].start_pos() == a["b"].start_pos());
CHECK(b["b"].end_pos() == a["b"].end_pos());
}
SECTION("move constructor resets the moved-from value to npos")
{
const std::string s = R"({"a":1,"b":[1,2,3]})";
json a = json::parse(s);
const auto a_start = a.start_pos();
const auto a_end = a.end_pos();
const json b(std::move(a));
CHECK(b.start_pos() == a_start);
CHECK(b.end_pos() == a_end);
CHECK(a.start_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
CHECK(a.end_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
}
SECTION("swap() exchanges positions along with the values")
{
// basic_json::swap() (and the friend swap() that forwards to it) used
// to swap only m_data.m_type/m_data.m_value, leaving
// start_position/end_position untouched -- unlike copy-assignment's
// operator=(basic_json), which swaps positions as part of its
// copy-and-swap implementation. After swap(a, b), each value ended up
// with the *other* value's content but its *own* original position.
// This is now fixed so that swap() is consistent with copy-assignment.
json a = json::parse(R"({"a":1})");
json b = json::parse(R"([1,2,3,4,5])");
const auto a_start = a.start_pos();
const auto a_end = a.end_pos();
const auto b_start = b.start_pos();
const auto b_end = b.end_pos();
// lengths (and thus end positions) differ, which is enough to tell
// after the swap whether positions actually moved with the values
CHECK(a_end != b_end);
using std::swap;
swap(a, b);
CHECK(a == json::parse(R"([1,2,3,4,5])"));
CHECK(b == json::parse(R"({"a":1})"));
CHECK(a.start_pos() == b_start);
CHECK(a.end_pos() == b_end);
CHECK(b.start_pos() == a_start);
CHECK(b.end_pos() == a_end);
// member swap() behaves the same as the free function
json c = json::parse(R"({"a":1})");
json d = json::parse(R"([1,2,3,4,5])");
const auto c_start = c.start_pos();
const auto c_end = c.end_pos();
const auto d_start = d.start_pos();
const auto d_end = d.end_pos();
c.swap(d);
CHECK(c.start_pos() == d_start);
CHECK(c.end_pos() == d_end);
CHECK(d.start_pos() == c_start);
CHECK(d.end_pos() == c_end);
}
}
#endif
// this test relies on parse errors being thrown, so it is skipped when
// exceptions are disabled (json::parse aborts instead of throwing there)
#if !defined(JSON_NOEXCEPTION)
@@ -2546,6 +2466,21 @@ TEST_CASE("diagnostic positions: value lifetime, input adapters, and SAX")
CHECK(a.end_pos() == b_end);
CHECK(b.start_pos() == a_start);
CHECK(b.end_pos() == a_end);
// member swap() behaves the same as the free function
json c = json::parse(R"({"a":1})");
json d = json::parse(R"([1,2,3,4,5])");
const auto c_start = c.start_pos();
const auto c_end = c.end_pos();
const auto d_start = d.start_pos();
const auto d_end = d.end_pos();
c.swap(d);
CHECK(c.start_pos() == d_start);
CHECK(c.end_pos() == d_end);
CHECK(d.start_pos() == c_start);
CHECK(d.end_pos() == c_end);
}
SECTION("mutating a parsed document leaves positions of unrelated values untouched")
+14
View File
@@ -641,6 +641,20 @@ TEST_CASE("modifiers")
CHECK_THROWS_WITH_AS(j_array.insert(j_array.end(), j_other_array.begin(), j_other_array2.end()), "[json.exception.invalid_iterator.210] iterators do not fit",
json::invalid_iterator&);
}
SECTION("iterators not pointing into an array")
{
json j_object2 = {{"k", 1}, {"l", 2}};
json j_primitive = 5;
json j_null;
CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_object2.begin(), j_object2.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
json::invalid_iterator&);
CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_primitive.begin(), j_primitive.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
json::invalid_iterator&);
CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_null.begin(), j_null.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
json::invalid_iterator&);
}
}
SECTION("range for object")
+15
View File
@@ -1682,6 +1682,21 @@ TEST_CASE("issue #5405 - array reserve for definite-length MessagePack arrays")
}
}
TEST_CASE("regression test - MessagePack ext type rejects a subtype that doesn't fit a single byte")
{
// subtype 0-255 must still round-trip correctly (regression guard, pre-existing behavior)
CHECK(json::from_msgpack(json::to_msgpack(json::binary({1, 2}, 0))).get_binary().subtype() == 0);
CHECK(json::from_msgpack(json::to_msgpack(json::binary({1, 2}, 200))).get_binary().subtype() == 200);
CHECK(json::from_msgpack(json::to_msgpack(json::binary({1, 2}, 255))).get_binary().subtype() == 255);
// a subtype > 255 must throw instead of silently truncating
CHECK_THROWS_AS(json::to_msgpack(json::binary({1, 2}, 256)), json::out_of_range);
CHECK_THROWS_WITH_AS(json::to_msgpack(json::binary({1, 2}, 70000)), "[json.exception.out_of_range.415] subtype 70000 is too large for the MessagePack ext type (max 255)", json::out_of_range);
// a binary value with no subtype at all must be unaffected
CHECK(json::from_msgpack(json::to_msgpack(json::binary({1, 2}))).get_binary().has_subtype() == false);
}
// use this testcase outside [hide] to run it with Valgrind
TEST_CASE("MessagePack nesting does not consume the call stack")
{
+81
View File
@@ -115,3 +115,84 @@ TEST_CASE("copying an ordered_json with nested values")
CHECK(mutated["a"]["b"]["x"] == 99);
}
}
TEST_CASE("regression test - diff() must account for ordered_json member order")
{
SECTION("pure reorder, no value changes")
{
ordered_json a = {{"a", 1}, {"b", 2}};
ordered_json b = {{"b", 2}, {"a", 1}};
CHECK(a != b); // order-sensitive equality
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("new key must land at the front")
{
ordered_json c = {{"b", 2}};
ordered_json e = {{"a", 1}, {"b", 2}};
CHECK(c.patch(ordered_json::diff(c, e)) == e);
}
SECTION("reorder plus a value change on one of the reordered keys")
{
ordered_json a = {{"a", 1}, {"b", 2}};
ordered_json b = {{"b", 20}, {"a", 1}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("reorder plus a deleted key")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
ordered_json b = {{"b", 2}, {"a", 1}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("reorder plus a nested value that itself needs a recursive diff")
{
ordered_json a = {{"a", {{"x", 1}, {"y", 2}}}, {"b", 2}};
ordered_json b = {{"b", 2}, {"a", {{"x", 1}, {"y", 99}}}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("three or more keys shuffled into a different order")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}, {"d", 4}};
ordered_json b = {{"d", 4}, {"b", 2}, {"a", 1}, {"c", 3}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("matching order still produces a minimal patch (fast path unaffected)")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
ordered_json b = {{"a", 1}, {"b", 20}, {"c", 3}};
auto p = ordered_json::diff(a, b);
// only the changed value should be touched, not a wholesale remove+add
CHECK(p.size() == 1);
CHECK(p[0]["op"] == "replace");
CHECK(p[0]["path"] == "/b");
CHECK(a.patch(p) == b);
}
SECTION("plain json (std::map-backed) is unaffected by same-key-different-insertion-order")
{
json a;
a["b"] = 2;
a["a"] = 1;
json b;
b["a"] = 1;
b["b"] = 2;
// std::map iteration is always sorted by key, so a == b regardless of
// insertion order, and diff() must still produce the same minimal
// (empty) result as before this fix
CHECK(a == b);
auto p = json::diff(a, b);
CHECK(p.empty());
CHECK(a.patch(p) == b);
}
}
+102
View File
@@ -763,4 +763,106 @@ TEST_CASE("regression tests 2")
}
TEST_CASE("regression test - parser callback must not lose a duplicate key's prior value")
{
// a callback that rejects only the scalar value 2
const json::parser_callback_t drop_value_2 = [](int /*depth*/, json::parse_event_t ev, json & v) noexcept
{
return !(ev == json::parse_event_t::value && v == 2);
};
SECTION("duplicate key, second (scalar) value rejected - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an object rejected at object_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::object_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an array rejected at array_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":[9,9]})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::array_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value accepted (scalar) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":2})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":2}");
}
SECTION("duplicate key, second value accepted (object) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":{\"x\":2}}");
}
SECTION("brand new (non-duplicate) key, value rejected - member is fully absent")
{
const json j = json::parse(R"({"a":1,"b":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key nested two levels deep")
{
const json j = json::parse(R"({"outer":{"a":1,"a":2}})", drop_value_2);
CHECK(j.dump() == "{\"outer\":{\"a\":1}}");
}
SECTION("three occurrences of the same key - middle rejected, last accepted")
{
const json j = json::parse(R"({"k":1,"k":2,"k":3})", drop_value_2);
CHECK(j.dump() == "{\"k\":3}");
}
}
TEST_CASE("regression test - excessive binary container size honors allow_exceptions=false")
{
// CBOR array with declared length 2^63
const std::vector<std::uint8_t> cbor = {0x9b, 0x80, 0, 0, 0, 0, 0, 0, 0};
// CBOR map with declared length 2^63
const std::vector<std::uint8_t> cbor_m = {0xbb, 0x80, 0, 0, 0, 0, 0, 0, 0};
// UBJSON array with declared length 2^63-1
const std::vector<std::uint8_t> ubj = {'[', '#', 'L', 0x7f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
// BJData array with declared length 2^63-1 (little endian)
const std::vector<std::uint8_t> bjd = {'[', '#', 'L', 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f};
// allow_exceptions=false must report failure instead of throwing/aborting
CHECK(json::from_cbor(cbor, true, false).is_discarded());
CHECK(json::from_cbor(cbor_m, true, false).is_discarded());
CHECK(json::from_ubjson(ubj, true, false).is_discarded());
CHECK(json::from_bjdata(bjd, true, false).is_discarded());
// allow_exceptions=true (the default) must still throw exactly as before.
// The exact message text is not checked here: on platforms where
// std::size_t is 32-bit, the CBOR reader's own length-narrowing check
// (get_cbor_container_size(), unrelated to this fix) intercepts a
// declared length of 2^63 before it ever reaches the check this test
// targets, with different (but equally valid, and already correct)
// wording -- see unit-cbor.cpp for coverage of that message.
json _;
CHECK_THROWS_AS(_ = json::from_cbor(cbor), json::out_of_range);
// regression guard: a genuinely truncated CBOR input must remain discarded
CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
}
DOCTEST_CLANG_SUPPRESS_WARNING_POP