Merge remote-tracking branch 'origin/develop' into claude/fix-issue-3989-db7e45

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

tests/CMakeLists.txt

@@ -135,12 +135,14 @@ json_test_set_test_options(test-disabled_exceptions
         #$<$<CXX_COMPILER_ID:MSVC>:/EH>
 )
 
-# raise timeout of expensive Unicode test
-json_test_set_test_options(test-unicode4 TEST_PROPERTIES TIMEOUT 3000)
-
 # only the #972 regression test needs thirdparty/fifo_map on its include path
 json_test_set_test_options(test-regression1 LINK_LIBRARIES fifo_map_include)
 
+# GCC's false -Warray-bounds error with JSON_DIAGNOSTICS only shows up when optimizing (#5742)
+json_test_set_test_options(test-diagnostics-optimized
+    COMPILE_OPTIONS $<$<CXX_COMPILER_ID:GNU>:-O3 -Werror=array-bounds>
+)
+
 #############################################################################
 # add unit tests
 #############################################################################

tests/src/test_utils.hpp

@@ -8,6 +8,7 @@
 
 #pragma once
 
+#include <array> // array
 #include <cstdint> // uint8_t
 #include <cstddef> // size_t
 #include <fstream> // ifstream, ios
@@ -43,6 +44,33 @@ T next_integer_sample(T i, T last, T stride)
     return n < last ? n : last;
 }
 
+// UTF-8 continuation bytes in [lo, hi] that stand in for all of them in the
+// ill-formed UTF-8 tests. Both the lexer's range checks and the serializer's
+// decoder (detail::decode) only distinguish the classes 0x80..0x8F, 0x90..0x9F,
+// and 0xA0..0xBF, so the first and last byte of each class within [lo, hi]
+// exercise every behavior while a test sweeps another byte position through
+// all 256 values (#5418). Define JSON_TEST_UTF8_EXHAUSTIVE to get every byte.
+inline std::vector<int> utf8_continuation_bytes(int lo, int hi)
+{
+    std::vector<int> result;
+#ifdef JSON_TEST_UTF8_EXHAUSTIVE
+    for (int byte = lo; byte <= hi; ++byte)
+    {
+        result.push_back(byte);
+    }
+#else
+    static const std::array<int, 6> class_ends = {{0x80, 0x8F, 0x90, 0x9F, 0xA0, 0xBF}};
+    for (const int byte : class_ends)
+    {
+        if (lo <= byte && byte <= hi)
+        {
+            result.push_back(byte);
+        }
+    }
+#endif
+    return result;
+}
+
 inline std::vector<std::uint8_t> read_binary_file(const std::string& filename)
 {
     std::ifstream file(filename, std::ios::binary);

tests/src/unit-allocator.cpp

@@ -12,6 +12,11 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <valarray>
+#if JSON_HAS_RANGES
+    #include <ranges>
+#endif
+
 namespace
 {
 // special test case to check if memory is leaked if constructor throws
@@ -48,14 +53,7 @@ TEST_CASE("bad_alloc")
     SECTION("bad_alloc")
     {
         // create JSON type using the throwing allocator
-        using bad_json = nlohmann::basic_json<std::map,
-              std::vector,
-              std::string,
-              bool,
-              std::int64_t,
-              std::uint64_t,
-              double,
-              bad_allocator>;
+        using bad_json = nlohmann::json::with_allocator_t<bad_allocator>;
 
         // creating an object should throw
         CHECK_THROWS_AS(bad_json(bad_json::value_t::object), std::bad_alloc&);
@@ -129,14 +127,7 @@ void my_allocator_clean_up(T* p)
 TEST_CASE("controlled bad_alloc")
 {
     // create JSON type using the throwing allocator
-    using my_json = nlohmann::basic_json<std::map,
-          std::vector,
-          std::string,
-          bool,
-          std::int64_t,
-          std::uint64_t,
-          double,
-          my_allocator>;
+    using my_json = nlohmann::json::with_allocator_t<my_allocator>;
 
     SECTION("class json_value")
     {
@@ -593,14 +584,7 @@ TEST_CASE("bad my_allocator::construct")
 {
     SECTION("my_allocator::construct doesn't forward")
     {
-        using bad_alloc_json = nlohmann::basic_json<std::map,
-              std::vector,
-              std::string,
-              bool,
-              std::int64_t,
-              std::uint64_t,
-              double,
-              allocator_no_forward>;
+        using bad_alloc_json = nlohmann::json::with_allocator_t<allocator_no_forward>;
 
         bad_alloc_json j;
         j["test"] = bad_alloc_json::array_t();
@@ -692,3 +676,173 @@ TEST_CASE("destructor performs no allocation, only deallocation")
         CHECK(counting_allocator_deallocations > deallocations_before);
     }
 }
+
+// the no-exceptions CI job skips every CHECK_THROWS_AS, which would leave
+// next_construct_fails set for the next allocation outside a check
+#if !defined(JSON_NOEXCEPTION)
+TEST_CASE("a failed allocation leaves the value unchanged")
+{
+    // create JSON type using the throwing allocator
+    using my_json = nlohmann::basic_json<std::map,
+          std::vector,
+          std::string,
+          bool,
+          std::int64_t,
+          std::uint64_t,
+          double,
+          my_allocator>;
+
+    // Each of these creates a string, array, object, or binary value. The
+    // value must be created before the type is changed: otherwise, a failed
+    // creation left a value of the new type without anything behind it (an
+    // assertion in its destructor, a null pointer everywhere else) or, when
+    // an old value was destroyed first, with a pointer to that destroyed one.
+
+    SECTION("creating a binary value")
+    {
+        const std::vector<std::uint8_t> bytes = {1, 2, 3};
+        my_json _;
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(_ = my_json::binary(bytes), std::bad_alloc&);
+        next_construct_fails = true;
+        CHECK_THROWS_AS(_ = my_json::binary(bytes, 42), std::bad_alloc&);
+        next_construct_fails = true;
+        CHECK_THROWS_AS(_ = my_json::binary(std::vector<std::uint8_t>(bytes)), std::bad_alloc&);
+        next_construct_fails = true;
+        CHECK_THROWS_AS(_ = my_json::binary(std::vector<std::uint8_t>(bytes), 42), std::bad_alloc&);
+        next_construct_fails = false;
+    }
+
+    SECTION("turning a null value into an array or object")
+    {
+        my_json j;
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j[0], std::bad_alloc&);
+        CHECK(j.is_null());
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j["key"], std::bad_alloc&);
+        CHECK(j.is_null());
+
+#ifdef JSON_HAS_CPP_17
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j[std::string_view("key")], std::bad_alloc&);
+        CHECK(j.is_null());
+#endif
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.push_back(my_json(1)), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        const my_json one = 1;
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.push_back(one), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.push_back(my_json::object_t::value_type("key", 1)), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.emplace_back(1), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.emplace("key", 1), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        const my_json object = {{"key", 1}};
+        next_construct_fails = true;
+        CHECK_THROWS_AS(j.update(object), std::bad_alloc&);
+        CHECK(j.is_null());
+
+        next_construct_fails = false;
+    }
+
+    // With iterator debugging, VS 2015's containers construct a proxy with the
+    // allocator in constructors that cannot report its failure, so a failing
+    // allocator crashes this section there (SIGSEGV with VS 2015 Debug x86).
+#if !(defined(_MSC_VER) && _MSC_VER < 1910 && defined(_ITERATOR_DEBUG_LEVEL) && _ITERATOR_DEBUG_LEVEL > 0)
+    SECTION("converting into an existing value")
+    {
+        // to_json replaces the value it is given; the old one must survive a
+        // failed creation of the new one
+        my_json j = "old";
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::string("new")), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::vector<int> {1, 2}), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::vector<bool> {true, false}), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::map<std::string, int> {{"a", 1}}), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, my_json::binary_t({1, 2})), std::bad_alloc&);
+        CHECK(j == "old");
+
+        // the overloads for lvalues of the value types, for the value types
+        // themselves, and for the remaining compatible types
+        const std::string string = "new";
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, string), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, "new"), std::bad_alloc&);
+        CHECK(j == "old");
+
+        // to_json only moves a binary value that it converted from another
+        // container type, which my_json's std::vector<std::uint8_t> is not
+        using binary_constructor = nlohmann::detail::external_constructor<nlohmann::detail::value_t::binary>;
+        next_construct_fails = true;
+        CHECK_THROWS_AS(binary_constructor::construct(j, my_json::binary_t({1, 2})), std::bad_alloc&);
+        CHECK(j == "old");
+
+        my_json::array_t array = {1, 2};
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, array), std::bad_alloc&);
+        CHECK(j == "old");
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::move(array)), std::bad_alloc&);
+        CHECK(j == "old");
+
+        my_json::object_t object = {{"a", 1}};
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, object), std::bad_alloc&);
+        CHECK(j == "old");
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::move(object)), std::bad_alloc&);
+        CHECK(j == "old");
+
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, std::valarray<int> {1, 2}), std::bad_alloc&);
+        CHECK(j == "old");
+
+#if JSON_HAS_RANGES && !defined(__MINGW32__)
+        const std::vector<int> numbers = {1, 2};
+        next_construct_fails = true;
+        CHECK_THROWS_AS(nlohmann::to_json(j, numbers | std::views::filter([](int /*unused*/)
+        {
+            return true;
+        })), std::bad_alloc&);
+        CHECK(j == "old");
+#endif
+
+        next_construct_fails = false;
+        nlohmann::to_json(j, std::vector<int> {1, 2});
+        CHECK(j == my_json({1, 2}));
+    }
+#endif
+}
+#endif

tests/src/unit-alt-string.cpp

@@ -163,16 +163,7 @@ void int_to_string(alt_string& target, std::size_t value)
     target = std::to_string(value).c_str();
 }
 
-using alt_json = nlohmann::basic_json <
-                 std::map,
-                 std::vector,
-                 alt_string,
-                 bool,
-                 std::int64_t,
-                 std::uint64_t,
-                 double,
-                 std::allocator,
-                 nlohmann::adl_serializer >;
+using alt_json = nlohmann::json::with_string_t<alt_string>;
 
 bool operator<(const char* op1, const alt_string& op2) noexcept
 {

tests/src/unit-binary_formats.cpp

@@ -19,7 +19,7 @@ using nlohmann::json;
 #include <vector>
 #include "make_test_data_available.hpp"
 
-TEST_CASE("Binary Formats" * doctest::skip())
+TEST_CASE("Binary Formats")
 {
     SECTION("canada.json")
     {
@@ -147,48 +147,6 @@ TEST_CASE("Binary Formats" * doctest::skip())
         CHECK((100.0 * double(ubjson_3_size) / double(json_size)) == Approx(84.963));
     }
 
-    SECTION("jeopardy.json")
-    {
-        const auto* filename = TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json";
-        json j = json::parse(std::ifstream(filename));
-
-        const auto json_size = j.dump().size();
-        const auto bjdata_1_size = json::to_bjdata(j).size();
-        const auto bjdata_2_size = json::to_bjdata(j, true).size();
-        const auto bjdata_3_size = json::to_bjdata(j, true, true).size();
-        const auto bon8_size = json::to_bon8(j).size();
-        const auto bson_size = json::to_bson({{"", j}}).size(); // wrap array in object for BSON
-        const auto cbor_size = json::to_cbor(j).size();
-        const auto msgpack_size = json::to_msgpack(j).size();
-        const auto ubjson_1_size = json::to_ubjson(j).size();
-        const auto ubjson_2_size = json::to_ubjson(j, true).size();
-        const auto ubjson_3_size = json::to_ubjson(j, true, true).size();
-
-        CHECK(json_size == 52508728);
-        CHECK(bjdata_1_size == 50710965);
-        CHECK(bjdata_2_size == 51144830);
-        CHECK(bjdata_3_size == 51144830);
-        CHECK(bon8_size == 45942080);
-        CHECK(bson_size == 56008520);
-        CHECK(cbor_size == 46187320);
-        CHECK(msgpack_size == 46158575);
-        CHECK(ubjson_1_size == 50710965);
-        CHECK(ubjson_2_size == 51144830);
-        CHECK(ubjson_3_size == 49861422);
-
-        CHECK((100.0 * double(json_size) / double(json_size)) == Approx(100.0));
-        CHECK((100.0 * double(bjdata_1_size) / double(json_size)) == Approx(96.576));
-        CHECK((100.0 * double(bjdata_2_size) / double(json_size)) == Approx(97.402));
-        CHECK((100.0 * double(bjdata_3_size) / double(json_size)) == Approx(97.402));
-        CHECK((100.0 * double(bon8_size) / double(json_size)) == Approx(87.494));
-        CHECK((100.0 * double(bson_size) / double(json_size)) == Approx(106.665));
-        CHECK((100.0 * double(cbor_size) / double(json_size)) == Approx(87.961));
-        CHECK((100.0 * double(msgpack_size) / double(json_size)) == Approx(87.906));
-        CHECK((100.0 * double(ubjson_1_size) / double(json_size)) == Approx(96.576));
-        CHECK((100.0 * double(ubjson_2_size) / double(json_size)) == Approx(97.402));
-        CHECK((100.0 * double(ubjson_3_size) / double(json_size)) == Approx(94.958));
-    }
-
     SECTION("sample.json")
     {
         const auto* filename = TEST_DATA_DIRECTORY "/json_testsuite/sample.json";
@@ -230,6 +188,50 @@ TEST_CASE("Binary Formats" * doctest::skip())
     }
 }
 
+// jeopardy.json is 52 MB and produces ~500 MB of serialization output, so it
+// is kept apart from the cheap corpus files above (#5418)
+TEST_CASE("Binary Formats (jeopardy.json)" * doctest::skip())
+{
+    const auto* filename = TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json";
+    json j = json::parse(std::ifstream(filename));
+
+    const auto json_size = j.dump().size();
+    const auto bjdata_1_size = json::to_bjdata(j).size();
+    const auto bjdata_2_size = json::to_bjdata(j, true).size();
+    const auto bjdata_3_size = json::to_bjdata(j, true, true).size();
+    const auto bon8_size = json::to_bon8(j).size();
+    const auto bson_size = json::to_bson({{"", j}}).size(); // wrap array in object for BSON
+    const auto cbor_size = json::to_cbor(j).size();
+    const auto msgpack_size = json::to_msgpack(j).size();
+    const auto ubjson_1_size = json::to_ubjson(j).size();
+    const auto ubjson_2_size = json::to_ubjson(j, true).size();
+    const auto ubjson_3_size = json::to_ubjson(j, true, true).size();
+
+    CHECK(json_size == 52508728);
+    CHECK(bjdata_1_size == 50710965);
+    CHECK(bjdata_2_size == 51144830);
+    CHECK(bjdata_3_size == 51144830);
+    CHECK(bon8_size == 45942080);
+    CHECK(bson_size == 56008520);
+    CHECK(cbor_size == 46187320);
+    CHECK(msgpack_size == 46158575);
+    CHECK(ubjson_1_size == 50710965);
+    CHECK(ubjson_2_size == 51144830);
+    CHECK(ubjson_3_size == 49861422);
+
+    CHECK((100.0 * double(json_size) / double(json_size)) == Approx(100.0));
+    CHECK((100.0 * double(bjdata_1_size) / double(json_size)) == Approx(96.576));
+    CHECK((100.0 * double(bjdata_2_size) / double(json_size)) == Approx(97.402));
+    CHECK((100.0 * double(bjdata_3_size) / double(json_size)) == Approx(97.402));
+    CHECK((100.0 * double(bon8_size) / double(json_size)) == Approx(87.494));
+    CHECK((100.0 * double(bson_size) / double(json_size)) == Approx(106.665));
+    CHECK((100.0 * double(cbor_size) / double(json_size)) == Approx(87.961));
+    CHECK((100.0 * double(msgpack_size) / double(json_size)) == Approx(87.906));
+    CHECK((100.0 * double(ubjson_1_size) / double(json_size)) == Approx(96.576));
+    CHECK((100.0 * double(ubjson_2_size) / double(json_size)) == Approx(97.402));
+    CHECK((100.0 * double(ubjson_3_size) / double(json_size)) == Approx(94.958));
+}
+
 namespace
 {
 // the binary formats as function pointers for "Binary formats with narrow number types";

tests/src/unit-bjdata.cpp

@@ -1286,6 +1286,32 @@ TEST_CASE("BJData")
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec2), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing BJData high-precision number: invalid number text: 1A", json::parse_error);
                     std::vector<uint8_t> const vec3 = {'H', 'i', 2, '1', '.'};
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec3), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing BJData high-precision number: invalid number text: 1.", json::parse_error);
+                    // Reject NULs where they are read, including trailing NULs and payloads cut off after one.
+                    SECTION("NUL in high-precision number (issue #5753)")
+                    {
+                        for (const auto& vec : std::vector<std::vector<uint8_t>>
+                    {
+                        {'H', 'i', 3, '1', 0, 'x'},
+                        {'H', 'i', 2, '1', 0},
+                        {'H', 'i', 3, '1', 0}
+                    })
+                        {
+                            CAPTURE(vec)
+                            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing BJData high-precision number: invalid number text; last byte: 0x00", json::parse_error);
+                            CHECK(json::from_bjdata(vec, true, false).is_discarded());
+                            CHECK(json::from_bjdata(vec, false, false).is_discarded());
+                        }
+
+                        std::vector<uint8_t> const nested = {'[', 'H', 'i', 3, '1', 0, 'x', ']'};
+                        CHECK_THROWS_WITH_AS(_ = json::from_bjdata(nested), "[json.exception.parse_error.115] parse error at byte 6: syntax error while parsing BJData high-precision number: invalid number text; last byte: 0x00", json::parse_error);
+                        CHECK(json::from_bjdata(nested, true, false).is_discarded());
+
+                        std::vector<uint8_t> const valid = {'H', 'i', 1, '1'};
+                        const auto j = json::from_bjdata(valid);
+                        CHECK(j.is_number_unsigned());
+                        CHECK(j == json(1));
+                    }
+
                     std::vector<uint8_t> const vec_overflow = {'H', 'i', 5, '1', 'e', '4', '0', '0'};
                     CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vec_overflow), "[json.exception.out_of_range.406] number overflow parsing '1e400'", json::out_of_range);
                     std::vector<uint8_t> const vec4 = {'H', 2, '1', '0'};

tests/src/unit-brace-init-copy-semantics.cpp

@@ -72,6 +72,28 @@ TEST_CASE("JSON_BRACE_INIT_COPY_SEMANTICS")
         CHECK(j7 == json::array({1, 2}));
     }
 
+    SECTION("single-element brace initialization copies a pair-shaped array value (#5662)")
+    {
+        // a JSON value that happens to be a 2-element array whose first
+        // element is a string must still be copied, not turned into an
+        // object; only a braced list written in the source, such as the
+        // inner {"key", "value"} of {{"key", "value"}}, describes an object
+        json const pair_shaped = json::array({"key", 42});
+
+        json const j1{pair_shaped};
+        CHECK(j1.is_array());
+        CHECK(j1 == pair_shaped);
+
+        json const j2 = {pair_shaped};
+        CHECK(j2.is_array());
+        CHECK(j2 == pair_shaped);
+
+        // the same holds for an rvalue of the same shape
+        json const j3{json::array({"key", 42})};
+        CHECK(j3.is_array());
+        CHECK(j3 == pair_shaped);
+    }
+
     SECTION("what the macro does not change")
     {
         // lists with more than one element are unaffected

tests/src/unit-cbor.cpp

@@ -1699,7 +1699,7 @@ TEST_CASE("CBOR")
             CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x61, 0X61})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
             CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xBF, 0x61, 0X61})), "[json.exception.parse_error.110] parse error at byte 4: syntax error while parsing CBOR value: unexpected end of input", json::parse_error&);
             CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B); last byte: 0x00", json::parse_error&);
             CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x41})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
 
             CHECK(json::from_cbor(std::vector<uint8_t>({0x18}), true, false).is_discarded());
@@ -2305,22 +2305,21 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
 {
     // Reading an indefinite-length string or byte array used to call itself
     // once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
-    // the call stack before any of the input was rejected. The open levels are
-    // counted now, and the levels below prove the reader still reads the same
-    // values and reports the same errors at the same byte offsets.
+    // the call stack before any of the input was rejected. Nested indefinite
+    // chunks are now rejected at the second byte, without recursing.
     json _;
 
-    SECTION("many open levels are reported, not crashed on")
+    SECTION("nested levels are rejected, not crashed on")
     {
         const std::vector<uint8_t> input(200000, 0x7F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: indefinite-length string is not allowed inside indefinite-length string; last byte: 0x7F", json::parse_error&);
         CHECK(json::from_cbor(input, true, false).is_discarded());
     }
 
-    SECTION("many open levels are reported, not crashed on (binary)")
+    SECTION("nested levels are rejected, not crashed on (binary)")
     {
         const std::vector<uint8_t> input(200000, 0x5F);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: indefinite-length binary array is not allowed inside indefinite-length binary array; last byte: 0x5F", json::parse_error&);
         CHECK(json::from_cbor(input, true, false).is_discarded());
     }
 
@@ -2328,22 +2327,22 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
     {
         CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
         CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
-        // nested indefinite-length strings are concatenated across levels
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
+        // empty and nonempty definite-length chunks concatenate in order
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 'a', 0x60, 0x61, 'b', 0x61, 'c', 0xFF})) == json("abc"));
         CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
     }
 
     SECTION("chunks are still concatenated (binary)")
     {
         CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
-        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0xFF})) == json::binary({}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0x40, 0x41, 0x62, 0x41, 0x63, 0xFF})) == json::binary({0x61, 0x62, 0x63}));
     }
 
     SECTION("a chunk that is not a string is still rejected")
     {
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B); last byte: 0x00", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B); last byte: 0x00", json::parse_error&);
     }
 
     SECTION("a break marker outside an indefinite-length string is not a string")
@@ -2896,9 +2895,17 @@ TEST_CASE("examples from RFC 8949 Appendix A")
     {
         const auto packed = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.cbor");
         json j;
-        CHECK_NOTHROW(j = json::from_cbor(packed));
+        // the fixture's tail contains nested indefinite-length byte strings.
+        CHECK_THROWS_WITH_AS(j = json::from_cbor(packed), "[json.exception.parse_error.113] parse error at byte 513: syntax error while parsing CBOR binary: indefinite-length binary array is not allowed inside indefinite-length binary array; last byte: 0x5F", json::parse_error&);
 
-        const auto expected = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.out");
+        // keep the byte-for-byte decoding check for its valid prefix: the first
+        // 512 encoded bytes contain 468 payload bytes in definite-length chunks.
+        auto valid_prefix = packed;
+        valid_prefix.resize(512);
+        valid_prefix.push_back(0xFF);
+        auto expected = utils::read_binary_file(TEST_DATA_DIRECTORY "/binary_data/cbor_binary.out");
+        expected.resize(468);
+        CHECK_NOTHROW(j = json::from_cbor(valid_prefix));
         CHECK(j == json::binary(expected));
 
         // 0xd8

tests/src/unit-custom-base-class.cpp

@@ -38,20 +38,7 @@ class json_metadata
 };
 
 template<class T>
-using json_with_metadata =
-    nlohmann::basic_json <
-    std::map,
-    std::vector,
-    std::string,
-    bool,
-    std::int64_t,
-    std::uint64_t,
-    double,
-    std::allocator,
-    nlohmann::adl_serializer,
-    std::vector<std::uint8_t>,
-    json_metadata<T>
-    >;
+using json_with_metadata = nlohmann::json::with_base_class_t<json_metadata<T>>;
 
 TEST_CASE("JSON Node Metadata")
 {
@@ -268,19 +255,7 @@ class visitor_adaptor
     void do_visit(const Ptr& ptr, const Fnc& fnc) const;
 };
 
-using json_with_visitor_t = nlohmann::basic_json <
-                            std::map,
-                            std::vector,
-                            std::string,
-                            bool,
-                            std::int64_t,
-                            std::uint64_t,
-                            double,
-                            std::allocator,
-                            nlohmann::adl_serializer,
-                            std::vector<std::uint8_t>,
-                            visitor_adaptor
-                            >;
+using json_with_visitor_t = nlohmann::json::with_base_class_t<visitor_adaptor>;
 
 template <class Fnc>
 void visitor_adaptor::visit(const Fnc& fnc) const

tests/src/unit-custom-object-type.cpp

@@ -10,7 +10,9 @@
 
 #include <nlohmann/json.hpp>
 
+#include <cstddef>
 #include <cstdint>
+#include <iterator>
 #include <map>
 #include <string>
 #include <type_traits>
@@ -196,6 +198,198 @@ struct void_erase_map : std::map<Key, T, Compare, Allocator>
 
 using void_erase_json = nlohmann::basic_json<void_erase_map>;
 
+// wraps an iterator, but only offers the LegacyForwardIterator operations,
+// like the iterators of std::unordered_map and other hash maps
+template<class BaseIterator>
+class forward_only_iterator
+{
+    BaseIterator m_it{};
+
+  public:
+    using iterator_category = std::forward_iterator_tag;
+    using value_type = typename std::iterator_traits<BaseIterator>::value_type;
+    using difference_type = typename std::iterator_traits<BaseIterator>::difference_type;
+    using pointer = typename std::iterator_traits<BaseIterator>::pointer;
+    using reference = typename std::iterator_traits<BaseIterator>::reference;
+
+    forward_only_iterator() = default;
+    explicit forward_only_iterator(BaseIterator it) : m_it(it) {}
+
+    BaseIterator base() const
+    {
+        return m_it;
+    }
+
+    reference operator*() const
+    {
+        return *m_it;
+    }
+    pointer operator->() const
+    {
+        return &*m_it;
+    }
+    forward_only_iterator& operator++()
+    {
+        ++m_it;
+        return *this;
+    }
+    forward_only_iterator operator++(int)
+    {
+        auto result = *this;
+        ++m_it;
+        return result;
+    }
+
+    friend bool operator==(const forward_only_iterator& lhs, const forward_only_iterator& rhs)
+    {
+        return lhs.m_it == rhs.m_it;
+    }
+    friend bool operator!=(const forward_only_iterator& lhs, const forward_only_iterator& rhs)
+    {
+        return lhs.m_it != rhs.m_it;
+    }
+};
+
+// An ObjectType whose iterators are forward-only, as those of hash maps are;
+// it has no rbegin() and its iterators no operator--. A hash map is not used
+// directly for the same reason as in no_key_compare_map above.
+template<class Key, class T, class Compare, class Allocator>
+class forward_only_map
+{
+    using map_t = std::map<Key, T, Compare, Allocator>;
+    map_t data;
+
+  public:
+    using key_type = typename map_t::key_type;
+    using mapped_type = typename map_t::mapped_type;
+    using value_type = typename map_t::value_type;
+    using size_type = typename map_t::size_type;
+    using allocator_type = typename map_t::allocator_type;
+    using iterator = forward_only_iterator<typename map_t::iterator>;
+    using const_iterator = forward_only_iterator<typename map_t::const_iterator>;
+
+    forward_only_map() noexcept(std::is_nothrow_default_constructible<map_t>::value) : data() {}
+
+    template<class InputIt>
+    forward_only_map(InputIt first, InputIt last) : data(first, last) {}
+
+    iterator begin() noexcept
+    {
+        return iterator(data.begin());
+    }
+    iterator end() noexcept
+    {
+        return iterator(data.end());
+    }
+    const_iterator begin() const noexcept
+    {
+        return const_iterator(data.begin());
+    }
+    const_iterator end() const noexcept
+    {
+        return const_iterator(data.end());
+    }
+    const_iterator cbegin() const noexcept
+    {
+        return const_iterator(data.cbegin());
+    }
+    const_iterator cend() const noexcept
+    {
+        return const_iterator(data.cend());
+    }
+
+    bool empty() const noexcept
+    {
+        return data.empty();
+    }
+    size_type size() const noexcept
+    {
+        return data.size();
+    }
+    size_type max_size() const noexcept
+    {
+        return data.max_size();
+    }
+    void clear() noexcept
+    {
+        data.clear();
+    }
+
+    iterator find(const key_type& key)
+    {
+        return iterator(data.find(key));
+    }
+    const_iterator find(const key_type& key) const
+    {
+        return const_iterator(data.find(key));
+    }
+    size_type count(const key_type& key) const
+    {
+        return data.count(key);
+    }
+
+    std::pair<iterator, bool> emplace(const key_type& key, const mapped_type& value)
+    {
+        const auto result = data.emplace(key, value);
+        return {iterator(result.first), result.second};
+    }
+
+    std::pair<iterator, bool> insert(const value_type& value)
+    {
+        const auto result = data.insert(value);
+        return {iterator(result.first), result.second};
+    }
+
+    template<class InputIt>
+    void insert(InputIt first, InputIt last)
+    {
+        data.insert(first, last);
+    }
+
+    mapped_type& operator[](const key_type& key)
+    {
+        return data[key];
+    }
+
+    mapped_type& at(const key_type& key)
+    {
+        return data.at(key);
+    }
+    const mapped_type& at(const key_type& key) const
+    {
+        return data.at(key);
+    }
+
+    iterator erase(iterator pos)
+    {
+        return iterator(data.erase(pos.base()));
+    }
+    iterator erase(iterator first, iterator last)
+    {
+        return iterator(data.erase(first.base(), last.base()));
+    }
+    size_type erase(const key_type& key)
+    {
+        return data.erase(key);
+    }
+
+    void swap(forward_only_map& other) noexcept(noexcept(data.swap(other.data)))
+    {
+        data.swap(other.data);
+    }
+
+    friend bool operator==(const forward_only_map& lhs, const forward_only_map& rhs)
+    {
+        return lhs.data == rhs.data;
+    }
+    friend bool operator<(const forward_only_map& lhs, const forward_only_map& rhs)
+    {
+        return lhs.data < rhs.data;
+    }
+};
+
+using forward_only_json = nlohmann::basic_json<forward_only_map>;
+
 } // namespace
 
 TEST_CASE("object type whose erase() returns void")
@@ -322,3 +516,46 @@ TEST_CASE("object type without key_compare")
     }
 }
 
+
+TEST_CASE("object type with forward-only iterators")
+{
+    CHECK(std::is_same<std::iterator_traits<forward_only_json::object_t::iterator>::iterator_category,
+          std::forward_iterator_tag>::value);
+
+    SECTION("destroying nested objects and arrays")
+    {
+        forward_only_json j;
+        j["a"] = 1;
+        j["b"]["c"] = "x";
+        j["b"]["d"] = forward_only_json::array();
+        j["b"]["d"].push_back(forward_only_json::object());
+        j["b"]["d"].push_back(true);
+        j["b"]["e"]["f"]["g"] = nullptr;
+        j["h"] = forward_only_json::object();
+        j["i"]["j"] = 2;
+
+        CHECK(j.size() == 4);
+        CHECK(j["b"].size() == 3);
+        CHECK(j["b"]["d"].size() == 2);
+        CHECK(j["b"]["e"]["f"]["g"].is_null());
+
+        CHECK(j.erase("b") == 1);
+        CHECK(j.size() == 3);
+        j = 42;
+        CHECK(j == 42);
+    }
+
+    SECTION("destroying a deeply nested object")
+    {
+        constexpr std::size_t depth = 100000;
+        forward_only_json j;
+        forward_only_json* cur = &j;
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            (*cur)["s"] = i;
+            cur = &(*cur)["o"];
+        }
+        CHECK(j["o"]["o"]["s"] == 2);
+        // destroyed at the end of scope without recursing per level
+    }
+}

tests/src/unit-diagnostics-optimized.cpp

@@ -0,0 +1,80 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// Regression test for https://github.com/nlohmann/json/issues/5742: with
+// JSON_DIAGNOSTICS, GCC (12 to at least 16) reported a false -Warray-bounds
+// error in the inlined set_parents() at -O3. The type of a new string was set
+// before the string was allocated, so GCC had to assume that operator new
+// could change it again and checked the object branch of set_parents()
+// against the string's allocation. Setting the type after creating the value
+// avoids this. The warning depends on GCC's inlining decisions, so the
+// sections cover two patterns that trigger it on different GCC versions
+// (#4819 and #5742).
+// On GCC, this file is compiled with -O3 -Werror=array-bounds (see
+// tests/CMakeLists.txt), so the test fails to build if the warning returns.
+
+#include "doctest_compatibility.h"
+
+#ifdef JSON_DIAGNOSTICS
+    #undef JSON_DIAGNOSTICS
+#endif
+
+#define JSON_DIAGNOSTICS 1
+
+#include <nlohmann/json.hpp>
+using nlohmann::json;
+
+#include <algorithm>
+#include <iterator>
+#include <utility>
+#include <vector>
+
+namespace
+{
+enum class diag_color
+{
+    red,
+    green,
+    blue
+};
+
+void to_json(json& j, const diag_color& c)
+{
+    static const std::pair<diag_color, json> m[] = // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+    {
+        {diag_color::red, "r"},
+        {diag_color::green, "g"},
+        {diag_color::blue, "b"},
+    };
+    const auto* it = std::find_if(std::begin(m), std::end(m), [c](const std::pair<diag_color, json>& p)
+    {
+        return p.first == c;
+    });
+    j = it->second;
+}
+} // namespace
+
+TEST_CASE("diagnostics with optimization")
+{
+    SECTION("issue #4819 - object in vector")
+    {
+        std::vector<json> jsons{};
+        jsons.emplace_back(json({{"key", "value"}}));
+        CHECK(jsons.back()["key"] == "value");
+    }
+
+    SECTION("issue #5742 - string values from a static table")
+    {
+        json j = json::array();
+        j.push_back(diag_color::red);
+        j.push_back(diag_color::green);
+        j.push_back(diag_color::blue);
+        CHECK(j.dump() == R"(["r","g","b"])");
+        CHECK_THROWS_WITH_AS(j[1].get<int>(), "[json.exception.type_error.302] (/1) type must be number, but is string", json::type_error);
+    }
+}

tests/src/unit-msgpack-cpp17.cpp

@@ -0,0 +1,99 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// This file contains the C++17-only part of unit-msgpack.cpp (std::byte
+// input). It is kept in a separate translation unit so the (much larger)
+// unit-msgpack.cpp does not need to be compiled and run a second time just
+// for this one test case (#5418).
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+using nlohmann::json;
+
+#ifdef JSON_HAS_CPP_17
+#include <cstddef>
+#include <vector>
+
+// Test suite for verifying MessagePack handling with std::byte input
+TEST_CASE("MessagePack with std::byte")
+{
+
+    SECTION("std::byte compatibility")
+    {
+        SECTION("vector roundtrip")
+        {
+            json original =
+            {
+                {"name", "test"},
+                {"value", 42},
+                {"array", {1, 2, 3}}
+            };
+
+            std::vector<uint8_t> temp = json::to_msgpack(original);
+            // Convert the uint8_t vector to std::byte vector
+            std::vector<std::byte> msgpack_data(temp.size());
+            for (size_t i = 0; i < temp.size(); ++i)
+            {
+                msgpack_data[i] = std::byte(temp[i]);
+            }
+            // Deserialize from std::byte vector back to JSON
+            json from_bytes;
+            CHECK_NOTHROW(from_bytes = json::from_msgpack(msgpack_data));
+
+            CHECK(from_bytes == original);
+        }
+
+        SECTION("empty vector")
+        {
+            const std::vector<std::byte> empty_data;
+            CHECK_THROWS_WITH_AS([&]()
+            {
+                [[maybe_unused]] auto result = json::from_msgpack(empty_data);
+                return true;
+            }
+            (),
+            "[json.exception.parse_error.110] parse error at byte 1: syntax error while parsing MessagePack value: unexpected end of input",
+            json::parse_error&);
+        }
+
+        SECTION("comparison with workaround")
+        {
+            json original =
+            {
+                {"string", "hello"},
+                {"integer", 42},
+                {"float", 3.14},
+                {"boolean", true},
+                {"null", nullptr},
+                {"array", {1, 2, 3}},
+                {"object", {{"key", "value"}}}
+            };
+
+            std::vector<uint8_t> temp = json::to_msgpack(original);
+
+            std::vector<std::byte> msgpack_data(temp.size());
+            for (size_t i = 0; i < temp.size(); ++i)
+            {
+                msgpack_data[i] = std::byte(temp[i]);
+            }
+            // Attempt direct deserialization using std::byte input
+            const json direct_result = json::from_msgpack(msgpack_data);
+
+            // Test the workaround approach: reinterpret as unsigned char* and use iterator range
+            const auto* const char_start = reinterpret_cast<unsigned char const*>(msgpack_data.data());
+            const auto* const char_end = char_start + msgpack_data.size();
+            json workaround_result = json::from_msgpack(char_start, char_end);
+
+            // Verify that the final deserialized JSON matches the original JSON
+            CHECK(direct_result == workaround_result);
+            CHECK(direct_result == original);
+        }
+    }
+}
+#endif

tests/src/unit-msgpack.cpp

@@ -2173,85 +2173,6 @@ TEST_CASE("MessagePack roundtrips" * doctest::skip())
     }
 }
 
-#ifdef JSON_HAS_CPP_17
-// Test suite for verifying MessagePack handling with std::byte input
-TEST_CASE("MessagePack with std::byte")
-{
-
-    SECTION("std::byte compatibility")
-    {
-        SECTION("vector roundtrip")
-        {
-            json original =
-            {
-                {"name", "test"},
-                {"value", 42},
-                {"array", {1, 2, 3}}
-            };
-
-            std::vector<uint8_t> temp = json::to_msgpack(original);
-            // Convert the uint8_t vector to std::byte vector
-            std::vector<std::byte> msgpack_data(temp.size());
-            for (size_t i = 0; i < temp.size(); ++i)
-            {
-                msgpack_data[i] = std::byte(temp[i]);
-            }
-            // Deserialize from std::byte vector back to JSON
-            json from_bytes;
-            CHECK_NOTHROW(from_bytes = json::from_msgpack(msgpack_data));
-
-            CHECK(from_bytes == original);
-        }
-
-        SECTION("empty vector")
-        {
-            const std::vector<std::byte> empty_data;
-            CHECK_THROWS_WITH_AS([&]()
-            {
-                [[maybe_unused]] auto result = json::from_msgpack(empty_data);
-                return true;
-            }
-            (),
-            "[json.exception.parse_error.110] parse error at byte 1: syntax error while parsing MessagePack value: unexpected end of input",
-            json::parse_error&);
-        }
-
-        SECTION("comparison with workaround")
-        {
-            json original =
-            {
-                {"string", "hello"},
-                {"integer", 42},
-                {"float", 3.14},
-                {"boolean", true},
-                {"null", nullptr},
-                {"array", {1, 2, 3}},
-                {"object", {{"key", "value"}}}
-            };
-
-            std::vector<uint8_t> temp = json::to_msgpack(original);
-
-            std::vector<std::byte> msgpack_data(temp.size());
-            for (size_t i = 0; i < temp.size(); ++i)
-            {
-                msgpack_data[i] = std::byte(temp[i]);
-            }
-            // Attempt direct deserialization using std::byte input
-            const json direct_result = json::from_msgpack(msgpack_data);
-
-            // Test the workaround approach: reinterpret as unsigned char* and use iterator range
-            const auto* const char_start = reinterpret_cast<unsigned char const*>(msgpack_data.data());
-            const auto* const char_end = char_start + msgpack_data.size();
-            json workaround_result = json::from_msgpack(char_start, char_end);
-
-            // Verify that the final deserialized JSON matches the original JSON
-            CHECK(direct_result == workaround_result);
-            CHECK(direct_result == original);
-        }
-    }
-}
-#endif
-
 // the fake sizes below do not fit into a 32-bit std::size_t
 // with clang and libstdc++ 10, the std::filesystem::path conversion that
 // C++17 builds consider for every string type is ambiguous for a class

tests/src/unit-regression2.cpp

@@ -1400,6 +1400,8 @@ TEST_CASE("regression test - #3989 SAX parse_error() returning true")
             {json::input_format_t::ubjson, {'[', 'H', 'i', 5, '1', '2', 'a', 'b', 'c', 'H', 'i', 2, '1', '.', 'H', 'i', 3, 'a', 'b', 'c', 'H', 'i', 3, '4', '.', '5', ']'}, {12, 1, nullptr, 4.5}, 3},
             // BJData, too
             {json::input_format_t::bjdata, {'[', 'C', 0xFF, 'H', 'i', 2, '-', '1', 'H', 'i', 2, '-', 'x', ']'}, {replacement_character(), -1, nullptr}, 2},
+            // a NUL ends a high-precision number, as it ends JSON text
+            {json::input_format_t::ubjson, {'[', 'H', 'i', 4, '1', '2', 0, '9', 'H', 'i', 2, 0, '1', 'i', 3, ']'}, {12, nullptr, 3}, 2},
             // BON8: members whose key is not a string are skipped
             {json::input_format_t::bon8, {0x89, 0x91, 0x92, 0xC9, 0x40, 0x82, 0x91, 0x92, 0x61, 0x93}, {{"a", 3}}, 2},
             {json::input_format_t::bon8, {0x8B, 0x91, 0x85, 0x91, 0xFE, 0xFA, 0x8B, 'x', 0x91, 0xFE, 0x61, 0x93, 0xFE}, {{"a", 3}}, 2},
@@ -1516,6 +1518,11 @@ TEST_CASE("regression test - #3989 SAX parse_error() returning true")
         CHECK(bon8.errors == 1);
         CHECK(bon8.value == json({{"a", 1}}));
 
+        // an indefinite-length string inside an indefinite-length string
+        const auto nested = parse_binary_recovering({0x82, 0x01, 0x7F, 0x7F, 0x61, 'a', 0xFF, 0xFF}, json::input_format_t::cbor);
+        CHECK(nested.errors == 1);
+        CHECK(nested.value == json({1}));
+
         // a skipped member that the input ends in
         const auto truncated = parse_binary_recovering({0xA2, 0x01, 0x82, 0x01}, json::input_format_t::cbor);
         CHECK(truncated.errors == 2);

tests/src/unit-regression3.cpp

@@ -862,6 +862,46 @@ TEST_CASE("issue #5338 - truncated CBOR tagged binary subtype is rejected")
     }
 }
 
+TEST_CASE("issue #5676 - SAX parsing of CBOR tags")
+{
+    const json expected = json::binary({1, 2, 3}, 42);
+    const auto cbor = json::to_cbor(expected);
+
+    nlohmann::detail::json_sax_acceptor<json> acceptor;
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor));
+    CHECK_FALSE(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                                true, false, false, json::cbor_tag_handler_t::error));
+
+    CHECK(json::sax_parse(cbor, &acceptor, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::ignore));
+
+    json parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> sax(parsed);
+    CHECK(json::sax_parse(cbor, &sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(parsed == expected);
+
+    json iterator_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> iterator_sax(iterator_parsed);
+    CHECK(json::sax_parse(cbor.begin(), cbor.end(), &iterator_sax, json::input_format_t::cbor,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(iterator_parsed == expected);
+
+    json span_parsed;
+    nlohmann::detail::json_sax_dom_parser<json, nlohmann::detail::string_input_adapter_type> span_sax(span_parsed);
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(cbor.data(), cbor.size()), &span_sax,
+                          json::input_format_t::cbor, true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(span_parsed == expected);
+
+    const std::string text = "null";
+    CHECK(json::sax_parse(text, &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(text.begin(), text.end(), &acceptor, json::input_format_t::json,
+                          true, false, false, json::cbor_tag_handler_t::store));
+    CHECK(json::sax_parse(nlohmann::detail::span_input_adapter(text.data(), text.size()), &acceptor,
+                          json::input_format_t::json, true, false, false, json::cbor_tag_handler_t::store));
+}
+
 TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with an object")
 {
     json t = {{"k", 1}};
@@ -920,4 +960,12 @@ TEST_CASE("regression test #5476 - array type without reserve()")
     }
 }
 
+TEST_CASE("issue #5317 - nested indefinite-length CBOR string chunks are rejected")
+{
+    json _;
+    CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0xFF})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: indefinite-length string is not allowed inside indefinite-length string; last byte: 0x7F", json::parse_error&);
+    CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0xFF})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR binary: indefinite-length binary array is not allowed inside indefinite-length binary array; last byte: 0x5F", json::parse_error&);
+    CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<std::uint8_t>({0xA1, 0x7F, 0x7F, 0xFF, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: indefinite-length string is not allowed inside indefinite-length string; last byte: 0x7F", json::parse_error&);
+}
+
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-ubjson.cpp

@@ -802,6 +802,32 @@ TEST_CASE("UBJSON")
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec2), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1A", json::parse_error);
                     std::vector<uint8_t> const vec3 = {'H', 'i', 2, '1', '.'};
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec3), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text: 1.", json::parse_error);
+                    // Reject NULs where they are read, including trailing NULs and payloads cut off after one.
+                    SECTION("NUL in high-precision number (issue #5753)")
+                    {
+                        for (const auto& vec : std::vector<std::vector<uint8_t>>
+                    {
+                        {'H', 'i', 3, '1', 0, 'x'},
+                        {'H', 'i', 2, '1', 0},
+                        {'H', 'i', 3, '1', 0}
+                    })
+                        {
+                            CAPTURE(vec)
+                            CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec), "[json.exception.parse_error.115] parse error at byte 5: syntax error while parsing UBJSON high-precision number: invalid number text; last byte: 0x00", json::parse_error);
+                            CHECK(json::from_ubjson(vec, true, false).is_discarded());
+                            CHECK(json::from_ubjson(vec, false, false).is_discarded());
+                        }
+
+                        std::vector<uint8_t> const nested = {'[', 'H', 'i', 3, '1', 0, 'x', ']'};
+                        CHECK_THROWS_WITH_AS(_ = json::from_ubjson(nested), "[json.exception.parse_error.115] parse error at byte 6: syntax error while parsing UBJSON high-precision number: invalid number text; last byte: 0x00", json::parse_error);
+                        CHECK(json::from_ubjson(nested, true, false).is_discarded());
+
+                        std::vector<uint8_t> const valid = {'H', 'i', 1, '1'};
+                        const auto j = json::from_ubjson(valid);
+                        CHECK(j.is_number_unsigned());
+                        CHECK(j == json(1));
+                    }
+
                     std::vector<uint8_t> const vec_overflow = {'H', 'i', 5, '1', 'e', '4', '0', '0'};
                     CHECK_THROWS_WITH_AS(_ = json::from_ubjson(vec_overflow), "[json.exception.out_of_range.406] number overflow parsing '1e400'", json::out_of_range&);
                     std::vector<uint8_t> const vec4 = {'H', 2, '1', '0'};

tests/src/unit-udt.cpp

@@ -23,6 +23,7 @@ using nlohmann::json;
     using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
 #endif
 
+#include <deque>
 #include <map>
 #include <memory>
 #include <string>
@@ -684,8 +685,7 @@ static std::ostream& operator<<(std::ostream& os, small_pod l)
 TEST_CASE("custom serializer for pods" * doctest::test_suite("udt"))
 {
     using custom_json =
-        nlohmann::basic_json<std::map, std::vector, std::string, bool,
-        std::int64_t, std::uint64_t, double, std::allocator, pod_serializer>;
+        nlohmann::json::with_json_serializer_t<pod_serializer>;
 
     auto p = udt::small_pod{42, '/', 42};
     custom_json const j = p;
@@ -703,7 +703,7 @@ TEST_CASE("custom serializer for pods" * doctest::test_suite("udt"))
 template <typename T, typename>
 struct another_adl_serializer;
 
-using custom_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, double, std::allocator, another_adl_serializer>;
+using custom_json = nlohmann::json::with_json_serializer_t<another_adl_serializer>;
 
 template <typename T, typename>
 struct another_adl_serializer
@@ -734,6 +734,80 @@ TEST_CASE("custom serializer that does adl by default" * doctest::test_suite("ud
     CHECK(me == cj.get<udt::person>());
 }
 
+TEST_CASE("with_*_t aliases" * doctest::test_suite("udt"))
+{
+    // a custom base class used to check with_base_class_t
+    struct custom_base_class {};
+
+    CHECK(std::is_same<json::with_object_t<std::deque>,
+          nlohmann::basic_json<std::deque, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_array_t<std::deque>,
+          nlohmann::basic_json<std::map, std::deque, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_string_t<std::wstring>,
+          nlohmann::basic_json<std::map, std::vector, std::wstring, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_boolean_t<int>,
+          nlohmann::basic_json<std::map, std::vector, std::string, int,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_integers_t<std::int32_t, std::uint32_t>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int32_t, std::uint32_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_float_t<float>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, float, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_allocator_t<std::allocator>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_json_serializer_t<nlohmann::adl_serializer>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    CHECK(std::is_same<json::with_binary_t<std::vector<char>>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<char>>>::value);
+
+    CHECK(std::is_same<json::with_base_class_t<custom_base_class>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>, custom_base_class>>::value);
+
+    // with_string_t on ordered_json must keep ordered_map as the object type
+    CHECK(std::is_same<nlohmann::ordered_json::with_string_t<std::wstring>,
+          nlohmann::basic_json<nlohmann::ordered_map, std::vector, std::wstring, bool,
+          std::int64_t, std::uint64_t, double, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+
+    // the aliases are members of the resulting type, so they can be chained
+    CHECK(std::is_same<json::with_integers_t<int, unsigned int>::with_float_t<float>,
+          nlohmann::basic_json<std::map, std::vector, std::string, bool,
+          int, unsigned int, float, std::allocator,
+          nlohmann::adl_serializer, std::vector<std::uint8_t>>>::value);
+    CHECK(std::is_same<json::with_float_t<float>::with_integers_t<int, unsigned int>,
+          json::with_integers_t<int, unsigned int>::with_float_t<float>>::value);
+
+    // replacing the object type of json with ordered_map yields ordered_json
+    CHECK(std::is_same<json::with_object_t<nlohmann::ordered_map>, nlohmann::ordered_json>::value);
+    CHECK(std::is_same<nlohmann::ordered_json::with_object_t<std::map>, json>::value);
+}
+
 TEST_CASE("different basic_json types conversions")
 {
     SECTION("null")

tests/src/unit-unicode1.cpp

@@ -1,623 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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"
-
-// for some reason including this after the json header leads to linker errors with VS 2017...
-#include <locale>
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <fstream>
-#include <sstream>
-#include <iomanip>
-#include "make_test_data_available.hpp"
-#include "test_utils.hpp"
-
-TEST_CASE("Unicode (1/5)" * doctest::skip())
-{
-    SECTION("\\uxxxx sequences")
-    {
-        // create an escaped string from a code point
-        const auto codepoint_to_unicode = [](std::size_t cp)
-        {
-            // code points are represented as a six-character sequence: a
-            // reverse solidus, followed by the lowercase letter u, followed
-            // by four hexadecimal digits that encode the character's code
-            // point
-            std::stringstream ss;
-            ss << "\\u" << std::setw(4) << std::setfill('0') << std::hex << cp;
-            return ss.str();
-        };
-
-        SECTION("correct sequences")
-        {
-            // generate all UTF-8 code points; in total, 1112064 code points are
-            // generated: 0x1FFFFF code points - 2048 invalid values between
-            // 0xD800 and 0xDFFF.
-            for (std::size_t cp = 0; cp <= 0x10FFFFu; ++cp)
-            {
-                // string to store the code point as in \uxxxx format
-                std::string json_text = "\"";
-
-                // decide whether to use one or two \uxxxx sequences
-                if (cp < 0x10000u)
-                {
-                    // The Unicode standard permanently reserves these code point
-                    // values for UTF-16 encoding of the high and low surrogates, and
-                    // they will never be assigned a character, so there should be no
-                    // reason to encode them. The official Unicode standard says that
-                    // no UTF forms, including UTF-16, can encode these code points.
-                    if (cp >= 0xD800u && cp <= 0xDFFFu)
-                    {
-                        // if we would not skip these code points, we would get a
-                        // "missing low surrogate" exception
-                        continue;
-                    }
-
-                    // code points in the Basic Multilingual Plane can be
-                    // represented with one \uxxxx sequence
-                    json_text += codepoint_to_unicode(cp);
-                }
-                else
-                {
-                    // To escape an extended character that is not in the Basic
-                    // Multilingual Plane, the character is represented as a
-                    // 12-character sequence, encoding the UTF-16 surrogate pair
-                    const auto codepoint1 = 0xd800u + (((cp - 0x10000u) >> 10) & 0x3ffu);
-                    const auto codepoint2 = 0xdc00u + ((cp - 0x10000u) & 0x3ffu);
-                    json_text += codepoint_to_unicode(codepoint1) + codepoint_to_unicode(codepoint2);
-                }
-
-                json_text += "\"";
-                CAPTURE(json_text)
-                json _;
-                CHECK_NOTHROW(_ = json::parse(json_text));
-            }
-        }
-
-        SECTION("incorrect sequences")
-        {
-            SECTION("incorrect surrogate values")
-            {
-                json _;
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uDC00\\uDC00\""), "[json.exception.parse_error.101] parse error at line 1, column 7: syntax error while parsing value - invalid string: surrogate U+DC00..U+DFFF must follow U+D800..U+DBFF; last read: '\"\\uDC00'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD7FF\\uDC00\""), "[json.exception.parse_error.101] parse error at line 1, column 13: syntax error while parsing value - invalid string: surrogate U+DC00..U+DFFF must follow U+D800..U+DBFF; last read: '\"\\uD7FF\\uDC00'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD800]\""), "[json.exception.parse_error.101] parse error at line 1, column 8: syntax error while parsing value - invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF; last read: '\"\\uD800]'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD800\\v\""), "[json.exception.parse_error.101] parse error at line 1, column 9: syntax error while parsing value - invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF; last read: '\"\\uD800\\v'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD800\\u123\""), "[json.exception.parse_error.101] parse error at line 1, column 13: syntax error while parsing value - invalid string: '\\u' must be followed by 4 hex digits; last read: '\"\\uD800\\u123\"'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD800\\uDBFF\""), "[json.exception.parse_error.101] parse error at line 1, column 13: syntax error while parsing value - invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF; last read: '\"\\uD800\\uDBFF'", json::parse_error&);
-
-                CHECK_THROWS_WITH_AS(_ = json::parse("\"\\uD800\\uE000\""), "[json.exception.parse_error.101] parse error at line 1, column 13: syntax error while parsing value - invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF; last read: '\"\\uD800\\uE000'", json::parse_error&);
-            }
-        }
-
-#if 0 // NOLINT(readability-avoid-unconditional-preprocessor-if)
-        SECTION("incorrect sequences")
-        {
-            SECTION("high surrogate without low surrogate")
-            {
-                // D800..DBFF are high surrogates and must be followed by low
-                // surrogates DC00..DFFF; here, nothing follows
-                for (std::size_t cp = 0xD800u; cp <= 0xDBFFu; ++cp)
-                {
-                    std::string json_text = "\"" + codepoint_to_unicode(cp) + "\"";
-                    CAPTURE(json_text)
-                    CHECK_THROWS_AS(json::parse(json_text), json::parse_error&);
-                }
-            }
-
-            SECTION("high surrogate with wrong low surrogate")
-            {
-                // D800..DBFF are high surrogates and must be followed by low
-                // surrogates DC00..DFFF; here a different sequence follows
-                for (std::size_t cp1 = 0xD800u; cp1 <= 0xDBFFu; ++cp1)
-                {
-                    for (std::size_t cp2 = 0x0000u; cp2 <= 0xFFFFu; ++cp2)
-                    {
-                        if (0xDC00u <= cp2 && cp2 <= 0xDFFFu)
-                        {
-                            continue;
-                        }
-
-                        std::string json_text = "\"" + codepoint_to_unicode(cp1) + codepoint_to_unicode(cp2) + "\"";
-                        CAPTURE(json_text)
-                        CHECK_THROWS_AS(json::parse(json_text), json::parse_error&);
-                    }
-                }
-            }
-
-            SECTION("low surrogate without high surrogate")
-            {
-                // low surrogates DC00..DFFF must follow high surrogates; here,
-                // they occur alone
-                for (std::size_t cp = 0xDC00u; cp <= 0xDFFFu; ++cp)
-                {
-                    std::string json_text = "\"" + codepoint_to_unicode(cp) + "\"";
-                    CAPTURE(json_text)
-                    CHECK_THROWS_AS(json::parse(json_text), json::parse_error&);
-                }
-            }
-
-        }
-#endif
-    }
-
-    SECTION("read all unicode characters")
-    {
-        // read a file with all Unicode characters stored as single-character
-        // strings in a JSON array
-        std::ifstream f(TEST_DATA_DIRECTORY "/json_nlohmann_tests/all_unicode.json");
-        json j;
-        CHECK_NOTHROW(f >> j);
-
-        // the array has 1112064 + 1 elements (a terminating "null" value)
-        // Note: 1112064 = 0x1FFFFF code points - 2048 invalid values between
-        // 0xD800 and 0xDFFF.
-        CHECK(j.size() == 1112065);
-
-        SECTION("check JSON Pointers")
-        {
-            for (const auto& s : j)
-            {
-                // skip non-string JSON values
-                if (!s.is_string())
-                {
-                    continue;
-                }
-
-                auto ptr = s.get<std::string>();
-
-                // tilde must be followed by 0 or 1
-                if (ptr == "~")
-                {
-                    ptr += "0";
-                }
-
-                // JSON Pointers must begin with "/"
-                ptr.insert(0, "/");
-
-                CHECK_NOTHROW(json::json_pointer("/" + ptr));
-
-                // check escape/unescape roundtrip
-                auto escaped = nlohmann::detail::escape(ptr);
-                nlohmann::detail::unescape(escaped);
-                CHECK(escaped == ptr);
-            }
-        }
-    }
-
-    SECTION("ignore byte-order-mark")
-    {
-        SECTION("in a stream")
-        {
-            // read a file with a UTF-8 BOM
-            std::ifstream f(TEST_DATA_DIRECTORY "/json_nlohmann_tests/bom.json");
-            json j;
-            CHECK_NOTHROW(f >> j);
-        }
-
-        SECTION("with an iterator")
-        {
-            std::string i = "\xef\xbb\xbf{\n   \"foo\": true\n}";
-            json _;
-            CHECK_NOTHROW(_ = json::parse(i.begin(), i.end()));
-        }
-    }
-
-    SECTION("error for incomplete/wrong BOM")
-    {
-        json _;
-        CHECK_THROWS_AS(_ = json::parse("\xef\xbb"), json::parse_error&);
-        CHECK_THROWS_AS(_ = json::parse("\xef\xbb\xbb"), json::parse_error&);
-    }
-}
-
-namespace
-{
-void roundtrip(bool success_expected, const std::string& s);
-
-void roundtrip(bool success_expected, const std::string& s)
-{
-    CAPTURE(s)
-    json _;
-
-    // create JSON string value
-    const json j = s;
-    // create JSON text
-    const std::string ps = std::string("\"") + s + "\"";
-
-    if (success_expected)
-    {
-        // serialization succeeds
-        // dump() is nodiscard; this only checks that dumping does not throw
-        CHECK_NOTHROW(utils::ignore_return_value(j.dump()));
-
-        // exclude parse test for U+0000
-        if (s[0] != '\0')
-        {
-            // parsing JSON text succeeds
-            CHECK_NOTHROW(_ = json::parse(ps));
-        }
-
-        // roundtrip succeeds
-        CHECK_NOTHROW(_ = json::parse(j.dump()));
-
-        // after roundtrip, the same string is stored
-        const json jr = json::parse(j.dump());
-        CHECK(jr.get<std::string>() == s);
-    }
-    else
-    {
-        // serialization fails
-        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
-
-        // parsing JSON text fails
-        CHECK_THROWS_AS(_ = json::parse(ps), json::parse_error&);
-    }
-}
-} // namespace
-
-TEST_CASE("Markus Kuhn's UTF-8 decoder capability and stress test")
-{
-    // Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> - 2015-08-28 - CC BY 4.0
-    // http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
-
-    SECTION("1  Some correct UTF-8 text")
-    {
-        roundtrip(true, "κόσμε");
-    }
-
-    SECTION("2  Boundary condition test cases")
-    {
-        SECTION("2.1  First possible sequence of a certain length")
-        {
-            // 2.1.1  1 byte  (U-00000000)
-            roundtrip(true, std::string("\0", 1));
-            // 2.1.2  2 bytes (U-00000080)
-            roundtrip(true, "\xc2\x80");
-            // 2.1.3  3 bytes (U-00000800)
-            roundtrip(true, "\xe0\xa0\x80");
-            // 2.1.4  4 bytes (U-00010000)
-            roundtrip(true, "\xf0\x90\x80\x80");
-
-            // 2.1.5  5 bytes (U-00200000)
-            roundtrip(false, "\xF8\x88\x80\x80\x80");
-            // 2.1.6  6 bytes (U-04000000)
-            roundtrip(false, "\xFC\x84\x80\x80\x80\x80");
-        }
-
-        SECTION("2.2  Last possible sequence of a certain length")
-        {
-            // 2.2.1  1 byte  (U-0000007F)
-            roundtrip(true, "\x7f");
-            // 2.2.2  2 bytes (U-000007FF)
-            roundtrip(true, "\xdf\xbf");
-            // 2.2.3  3 bytes (U-0000FFFF)
-            roundtrip(true, "\xef\xbf\xbf");
-
-            // 2.2.4  4 bytes (U-001FFFFF)
-            roundtrip(false, "\xF7\xBF\xBF\xBF");
-            // 2.2.5  5 bytes (U-03FFFFFF)
-            roundtrip(false, "\xFB\xBF\xBF\xBF\xBF");
-            // 2.2.6  6 bytes (U-7FFFFFFF)
-            roundtrip(false, "\xFD\xBF\xBF\xBF\xBF\xBF");
-        }
-
-        SECTION("2.3  Other boundary conditions")
-        {
-            // 2.3.1  U-0000D7FF = ed 9f bf
-            roundtrip(true, "\xed\x9f\xbf");
-            // 2.3.2  U-0000E000 = ee 80 80
-            roundtrip(true, "\xee\x80\x80");
-            // 2.3.3  U-0000FFFD = ef bf bd
-            roundtrip(true, "\xef\xbf\xbd");
-            // 2.3.4  U-0010FFFF = f4 8f bf bf
-            roundtrip(true, "\xf4\x8f\xbf\xbf");
-
-            // 2.3.5  U-00110000 = f4 90 80 80
-            roundtrip(false, "\xf4\x90\x80\x80");
-        }
-    }
-
-    SECTION("3  Malformed sequences")
-    {
-        SECTION("3.1  Unexpected continuation bytes")
-        {
-            // Each unexpected continuation byte should be separately signalled as a
-            // malformed sequence of its own.
-
-            // 3.1.1  First continuation byte 0x80
-            roundtrip(false, "\x80");
-            // 3.1.2  Last  continuation byte 0xbf
-            roundtrip(false, "\xbf");
-
-            // 3.1.3  2 continuation bytes
-            roundtrip(false, "\x80\xbf");
-            // 3.1.4  3 continuation bytes
-            roundtrip(false, "\x80\xbf\x80");
-            // 3.1.5  4 continuation bytes
-            roundtrip(false, "\x80\xbf\x80\xbf");
-            // 3.1.6  5 continuation bytes
-            roundtrip(false, "\x80\xbf\x80\xbf\x80");
-            // 3.1.7  6 continuation bytes
-            roundtrip(false, "\x80\xbf\x80\xbf\x80\xbf");
-            // 3.1.8  7 continuation bytes
-            roundtrip(false, "\x80\xbf\x80\xbf\x80\xbf\x80");
-
-            // 3.1.9  Sequence of all 64 possible continuation bytes (0x80-0xbf)
-            roundtrip(false, "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf");
-        }
-
-        SECTION("3.2  Lonely start characters")
-        {
-            // 3.2.1  All 32 first bytes of 2-byte sequences (0xc0-0xdf)
-            roundtrip(false, "\xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf");
-            // 3.2.2  All 16 first bytes of 3-byte sequences (0xe0-0xef)
-            roundtrip(false, "\xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee \xef");
-            // 3.2.3  All 8 first bytes of 4-byte sequences (0xf0-0xf7)
-            roundtrip(false, "\xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7");
-            // 3.2.4  All 4 first bytes of 5-byte sequences (0xf8-0xfb)
-            roundtrip(false, "\xf8 \xf9 \xfa \xfb");
-            // 3.2.5  All 2 first bytes of 6-byte sequences (0xfc-0xfd)
-            roundtrip(false, "\xfc \xfd");
-        }
-
-        SECTION("3.3  Sequences with last continuation byte missing")
-        {
-            // All bytes of an incomplete sequence should be signalled as a single
-            // malformed sequence, i.e., you should see only a single replacement
-            // character in each of the next 10 tests. (Characters as in section 2)
-
-            // 3.3.1  2-byte sequence with last byte missing (U+0000)
-            roundtrip(false, "\xc0");
-            // 3.3.2  3-byte sequence with last byte missing (U+0000)
-            roundtrip(false, "\xe0\x80");
-            // 3.3.3  4-byte sequence with last byte missing (U+0000)
-            roundtrip(false, "\xf0\x80\x80");
-            // 3.3.4  5-byte sequence with last byte missing (U+0000)
-            roundtrip(false, "\xf8\x80\x80\x80");
-            // 3.3.5  6-byte sequence with last byte missing (U+0000)
-            roundtrip(false, "\xfc\x80\x80\x80\x80");
-            // 3.3.6  2-byte sequence with last byte missing (U-000007FF)
-            roundtrip(false, "\xdf");
-            // 3.3.7  3-byte sequence with last byte missing (U-0000FFFF)
-            roundtrip(false, "\xef\xbf");
-            // 3.3.8  4-byte sequence with last byte missing (U-001FFFFF)
-            roundtrip(false, "\xf7\xbf\xbf");
-            // 3.3.9  5-byte sequence with last byte missing (U-03FFFFFF)
-            roundtrip(false, "\xfb\xbf\xbf\xbf");
-            // 3.3.10 6-byte sequence with last byte missing (U-7FFFFFFF)
-            roundtrip(false, "\xfd\xbf\xbf\xbf\xbf");
-        }
-
-        SECTION("3.4  Concatenation of incomplete sequences")
-        {
-            // All the 10 sequences of 3.3 concatenated, you should see 10 malformed
-            // sequences being signalled:
-            roundtrip(false, "\xc0\xe0\x80\xf0\x80\x80\xf8\x80\x80\x80\xfc\x80\x80\x80\x80\xdf\xef\xbf\xf7\xbf\xbf\xfb\xbf\xbf\xbf\xfd\xbf\xbf\xbf\xbf");
-        }
-
-        SECTION("3.5  Impossible bytes")
-        {
-            // The following two bytes cannot appear in a correct UTF-8 string
-
-            // 3.5.1  fe
-            roundtrip(false, "\xfe");
-            // 3.5.2  ff
-            roundtrip(false, "\xff");
-            // 3.5.3  fe fe ff ff
-            roundtrip(false, "\xfe\xfe\xff\xff");
-        }
-    }
-
-    SECTION("4  Overlong sequences")
-    {
-        // The following sequences are not malformed according to the letter of
-        // the Unicode 2.0 standard. However, they are longer then necessary and
-        // a correct UTF-8 encoder is not allowed to produce them. A "safe UTF-8
-        // decoder" should reject them just like malformed sequences for two
-        // reasons: (1) It helps to debug applications if overlong sequences are
-        // not treated as valid representations of characters, because this helps
-        // to spot problems more quickly. (2) Overlong sequences provide
-        // alternative representations of characters, that could maliciously be
-        // used to bypass filters that check only for ASCII characters. For
-        // instance, a 2-byte encoded line feed (LF) would not be caught by a
-        // line counter that counts only 0x0a bytes, but it would still be
-        // processed as a line feed by an unsafe UTF-8 decoder later in the
-        // pipeline. From a security point of view, ASCII compatibility of UTF-8
-        // sequences means also, that ASCII characters are *only* allowed to be
-        // represented by ASCII bytes in the range 0x00-0x7f. To ensure this
-        // aspect of ASCII compatibility, use only "safe UTF-8 decoders" that
-        // reject overlong UTF-8 sequences for which a shorter encoding exists.
-
-        SECTION("4.1  Examples of an overlong ASCII character")
-        {
-            // With a safe UTF-8 decoder, all the following five overlong
-            // representations of the ASCII character slash ("/") should be rejected
-            // like a malformed UTF-8 sequence, for instance by substituting it with
-            // a replacement character. If you see a slash below, you do not have a
-            // safe UTF-8 decoder!
-
-            // 4.1.1 U+002F = c0 af
-            roundtrip(false, "\xc0\xaf");
-            // 4.1.2 U+002F = e0 80 af
-            roundtrip(false, "\xe0\x80\xaf");
-            // 4.1.3 U+002F = f0 80 80 af
-            roundtrip(false, "\xf0\x80\x80\xaf");
-            // 4.1.4 U+002F = f8 80 80 80 af
-            roundtrip(false, "\xf8\x80\x80\x80\xaf");
-            // 4.1.5 U+002F = fc 80 80 80 80 af
-            roundtrip(false, "\xfc\x80\x80\x80\x80\xaf");
-        }
-
-        SECTION("4.2  Maximum overlong sequences")
-        {
-            // Below you see the highest Unicode value that is still resulting in an
-            // overlong sequence if represented with the given number of bytes. This
-            // is a boundary test for safe UTF-8 decoders. All five characters should
-            // be rejected like malformed UTF-8 sequences.
-
-            // 4.2.1  U-0000007F = c1 bf
-            roundtrip(false, "\xc1\xbf");
-            // 4.2.2  U-000007FF = e0 9f bf
-            roundtrip(false, "\xe0\x9f\xbf");
-            // 4.2.3  U-0000FFFF = f0 8f bf bf
-            roundtrip(false, "\xf0\x8f\xbf\xbf");
-            // 4.2.4  U-001FFFFF = f8 87 bf bf bf
-            roundtrip(false, "\xf8\x87\xbf\xbf\xbf");
-            // 4.2.5  U-03FFFFFF = fc 83 bf bf bf bf
-            roundtrip(false, "\xfc\x83\xbf\xbf\xbf\xbf");
-        }
-
-        SECTION("4.3  Overlong representation of the NUL character")
-        {
-            // The following five sequences should also be rejected like malformed
-            // UTF-8 sequences and should not be treated like the ASCII NUL
-            // character.
-
-            // 4.3.1  U+0000 = c0 80
-            roundtrip(false, "\xc0\x80");
-            // 4.3.2  U+0000 = e0 80 80
-            roundtrip(false, "\xe0\x80\x80");
-            // 4.3.3  U+0000 = f0 80 80 80
-            roundtrip(false, "\xf0\x80\x80\x80");
-            // 4.3.4  U+0000 = f8 80 80 80 80
-            roundtrip(false, "\xf8\x80\x80\x80\x80");
-            // 4.3.5  U+0000 = fc 80 80 80 80 80
-            roundtrip(false, "\xfc\x80\x80\x80\x80\x80");
-        }
-    }
-
-    SECTION("5  Illegal code positions")
-    {
-        // The following UTF-8 sequences should be rejected like malformed
-        // sequences, because they never represent valid ISO 10646 characters and
-        // a UTF-8 decoder that accepts them might introduce security problems
-        // comparable to overlong UTF-8 sequences.
-
-        SECTION("5.1 Single UTF-16 surrogates")
-        {
-            // 5.1.1  U+D800 = ed a0 80
-            roundtrip(false, "\xed\xa0\x80");
-            // 5.1.2  U+DB7F = ed ad bf
-            roundtrip(false, "\xed\xad\xbf");
-            // 5.1.3  U+DB80 = ed ae 80
-            roundtrip(false, "\xed\xae\x80");
-            // 5.1.4  U+DBFF = ed af bf
-            roundtrip(false, "\xed\xaf\xbf");
-            // 5.1.5  U+DC00 = ed b0 80
-            roundtrip(false, "\xed\xb0\x80");
-            // 5.1.6  U+DF80 = ed be 80
-            roundtrip(false, "\xed\xbe\x80");
-            // 5.1.7  U+DFFF = ed bf bf
-            roundtrip(false, "\xed\xbf\xbf");
-        }
-
-        SECTION("5.2 Paired UTF-16 surrogates")
-        {
-            // 5.2.1  U+D800 U+DC00 = ed a0 80 ed b0 80
-            roundtrip(false, "\xed\xa0\x80\xed\xb0\x80");
-            // 5.2.2  U+D800 U+DFFF = ed a0 80 ed bf bf
-            roundtrip(false, "\xed\xa0\x80\xed\xbf\xbf");
-            // 5.2.3  U+DB7F U+DC00 = ed ad bf ed b0 80
-            roundtrip(false, "\xed\xad\xbf\xed\xb0\x80");
-            // 5.2.4  U+DB7F U+DFFF = ed ad bf ed bf bf
-            roundtrip(false, "\xed\xad\xbf\xed\xbf\xbf");
-            // 5.2.5  U+DB80 U+DC00 = ed ae 80 ed b0 80
-            roundtrip(false, "\xed\xae\x80\xed\xb0\x80");
-            // 5.2.6  U+DB80 U+DFFF = ed ae 80 ed bf bf
-            roundtrip(false, "\xed\xae\x80\xed\xbf\xbf");
-            // 5.2.7  U+DBFF U+DC00 = ed af bf ed b0 80
-            roundtrip(false, "\xed\xaf\xbf\xed\xb0\x80");
-            // 5.2.8  U+DBFF U+DFFF = ed af bf ed bf bf
-            roundtrip(false, "\xed\xaf\xbf\xed\xbf\xbf");
-        }
-
-        SECTION("5.3 Noncharacter code positions")
-        {
-            // The following "noncharacters" are "reserved for internal use" by
-            // applications, and according to older versions of the Unicode Standard
-            // "should never be interchanged". Unicode Corrigendum #9 dropped the
-            // latter restriction. Nevertheless, their presence in incoming UTF-8 data
-            // can remain a potential security risk, depending on what use is made of
-            // these codes subsequently. Examples of such internal use:
-            //
-            //  - Some file APIs with 16-bit characters may use the integer value -1
-            //    = U+FFFF to signal an end-of-file (EOF) or error condition.
-            //
-            //  - In some UTF-16 receivers, code point U+FFFE might trigger a
-            //    byte-swap operation (to convert between UTF-16LE and UTF-16BE).
-            //
-            // With such internal use of noncharacters, it may be desirable and safer
-            // to block those code points in UTF-8 decoders, as they should never
-            // occur legitimately in incoming UTF-8 data, and could trigger unsafe
-            // behaviour in subsequent processing.
-
-            // Particularly problematic noncharacters in 16-bit applications:
-
-            // 5.3.1  U+FFFE = ef bf be
-            roundtrip(true, "\xef\xbf\xbe");
-            // 5.3.2  U+FFFF = ef bf bf
-            roundtrip(true, "\xef\xbf\xbf");
-
-            // 5.3.3  U+FDD0 .. U+FDEF
-            roundtrip(true, "\xEF\xB7\x90");
-            roundtrip(true, "\xEF\xB7\x91");
-            roundtrip(true, "\xEF\xB7\x92");
-            roundtrip(true, "\xEF\xB7\x93");
-            roundtrip(true, "\xEF\xB7\x94");
-            roundtrip(true, "\xEF\xB7\x95");
-            roundtrip(true, "\xEF\xB7\x96");
-            roundtrip(true, "\xEF\xB7\x97");
-            roundtrip(true, "\xEF\xB7\x98");
-            roundtrip(true, "\xEF\xB7\x99");
-            roundtrip(true, "\xEF\xB7\x9A");
-            roundtrip(true, "\xEF\xB7\x9B");
-            roundtrip(true, "\xEF\xB7\x9C");
-            roundtrip(true, "\xEF\xB7\x9D");
-            roundtrip(true, "\xEF\xB7\x9E");
-            roundtrip(true, "\xEF\xB7\x9F");
-            roundtrip(true, "\xEF\xB7\xA0");
-            roundtrip(true, "\xEF\xB7\xA1");
-            roundtrip(true, "\xEF\xB7\xA2");
-            roundtrip(true, "\xEF\xB7\xA3");
-            roundtrip(true, "\xEF\xB7\xA4");
-            roundtrip(true, "\xEF\xB7\xA5");
-            roundtrip(true, "\xEF\xB7\xA6");
-            roundtrip(true, "\xEF\xB7\xA7");
-            roundtrip(true, "\xEF\xB7\xA8");
-            roundtrip(true, "\xEF\xB7\xA9");
-            roundtrip(true, "\xEF\xB7\xAA");
-            roundtrip(true, "\xEF\xB7\xAB");
-            roundtrip(true, "\xEF\xB7\xAC");
-            roundtrip(true, "\xEF\xB7\xAD");
-            roundtrip(true, "\xEF\xB7\xAE");
-            roundtrip(true, "\xEF\xB7\xAF");
-
-            // 5.3.4  U+nFFFE U+nFFFF (for n = 1..10)
-            roundtrip(true, "\xF0\x9F\xBF\xBF");
-            roundtrip(true, "\xF0\xAF\xBF\xBF");
-            roundtrip(true, "\xF0\xBF\xBF\xBF");
-            roundtrip(true, "\xF1\x8F\xBF\xBF");
-            roundtrip(true, "\xF1\x9F\xBF\xBF");
-            roundtrip(true, "\xF1\xAF\xBF\xBF");
-            roundtrip(true, "\xF1\xBF\xBF\xBF");
-            roundtrip(true, "\xF2\x8F\xBF\xBF");
-            roundtrip(true, "\xF2\x9F\xBF\xBF");
-            roundtrip(true, "\xF2\xAF\xBF\xBF");
-        }
-    }
-}

tests/src/unit-unicode2.cpp

@@ -1,612 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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"
-
-// for some reason including this after the json header leads to linker errors with VS 2017...
-#include <locale>
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <fstream>
-#include <sstream>
-#include <iostream>
-#include <iomanip>
-#include "make_test_data_available.hpp"
-#include "test_utils.hpp"
-
-// this test suite uses static variables with non-trivial destructors
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-namespace
-{
-extern size_t calls;
-size_t calls = 0;
-
-void check_utf8dump(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    static std::string json_string;
-    json_string.clear();
-
-    CAPTURE(byte1)
-    CAPTURE(byte2)
-    CAPTURE(byte3)
-    CAPTURE(byte4)
-
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    CAPTURE(json_string)
-
-    // store the string in a JSON value
-    static json j;
-    static json j2;
-    j = json_string;
-    j2 = "abc" + json_string + "xyz";
-
-    static std::string s_ignored;
-    static std::string s_ignored2;
-    static std::string s_ignored_ascii;
-    static std::string s_ignored2_ascii;
-    static std::string s_replaced;
-    static std::string s_replaced2;
-    static std::string s_replaced_ascii;
-    static std::string s_replaced2_ascii;
-
-    // dumping with ignore/replace must not throw in any case
-    s_ignored = j.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored2 = j2.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored_ascii = j.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_ignored2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_replaced = j.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced2 = j2.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced_ascii = j.dump(-1, ' ', true, json::error_handler_t::replace);
-    s_replaced2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::replace);
-
-    if (success_expected)
-    {
-        static std::string s_strict;
-        // strict mode must not throw if success is expected
-        s_strict = j.dump();
-        // all dumps should agree on the string
-        CHECK(s_strict == s_ignored);
-        CHECK(s_strict == s_replaced);
-    }
-    else
-    {
-        // strict mode must throw if success is not expected
-        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
-        // ignore and replace must create different dumps
-        CHECK(s_ignored != s_replaced);
-
-        // check that replace string contains a replacement character
-        CHECK(s_replaced.find("\xEF\xBF\xBD") != std::string::npos);
-    }
-
-    // check that prefix and suffix are preserved
-    CHECK(s_ignored2.substr(1, 3) == "abc");
-    CHECK(s_ignored2.substr(s_ignored2.size() - 4, 3) == "xyz");
-    CHECK(s_ignored2_ascii.substr(1, 3) == "abc");
-    CHECK(s_ignored2_ascii.substr(s_ignored2_ascii.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2.substr(1, 3) == "abc");
-    CHECK(s_replaced2.substr(s_replaced2.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2_ascii.substr(1, 3) == "abc");
-    CHECK(s_replaced2_ascii.substr(s_replaced2_ascii.size() - 4, 3) == "xyz");
-}
-
-void check_utf8string(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-// create and check a JSON string with up to four UTF-8 bytes
-void check_utf8string(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    if (++calls % 100000 == 0)
-    {
-        std::cout << calls << " of 455355 UTF-8 strings checked" << std::endl; // NOLINT(performance-avoid-endl)
-    }
-
-    static std::string json_string;
-    json_string = "\"";
-
-    CAPTURE(byte1)
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        CAPTURE(byte2)
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        CAPTURE(byte3)
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        CAPTURE(byte4)
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    json_string += "\"";
-
-    CAPTURE(json_string)
-
-    json _;
-    if (success_expected)
-    {
-        CHECK_NOTHROW(_ = json::parse(json_string));
-    }
-    else
-    {
-        CHECK_THROWS_AS(_ = json::parse(json_string), json::parse_error&);
-    }
-}
-} // namespace
-
-TEST_CASE("Unicode (2/5)" * doctest::skip())
-{
-    SECTION("RFC 3629")
-    {
-        /*
-        RFC 3629 describes in Sect. 4 the syntax of UTF-8 byte sequences as
-        follows:
-
-            A UTF-8 string is a sequence of octets representing a sequence of UCS
-            characters.  An octet sequence is valid UTF-8 only if it matches the
-            following syntax, which is derived from the rules for encoding UTF-8
-            and is expressed in the ABNF of [RFC2234].
-
-            UTF8-octets = *( UTF8-char )
-            UTF8-char   = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
-            UTF8-1      = %x00-7F
-            UTF8-2      = %xC2-DF UTF8-tail
-            UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
-                          %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
-            UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
-                          %xF4 %x80-8F 2( UTF8-tail )
-            UTF8-tail   = %x80-BF
-        */
-
-        SECTION("ill-formed first byte")
-        {
-            for (int byte1 = 0x80; byte1 <= 0xC1; ++byte1)
-            {
-                check_utf8string(false, byte1);
-                check_utf8dump(false, byte1);
-            }
-
-            for (int byte1 = 0xF5; byte1 <= 0xFF; ++byte1)
-            {
-                check_utf8string(false, byte1);
-                check_utf8dump(false, byte1);
-            }
-        }
-
-        SECTION("UTF8-1 (x00-x7F)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0x00; byte1 <= 0x7F; ++byte1)
-                {
-                    // unescaped control characters are parse errors in JSON
-                    if (0x00 <= byte1 && byte1 <= 0x1F)
-                    {
-                        check_utf8string(false, byte1);
-                        continue;
-                    }
-
-                    // a single quote is a parse error in JSON
-                    if (byte1 == 0x22)
-                    {
-                        check_utf8string(false, byte1);
-                        continue;
-                    }
-
-                    // a single backslash is a parse error in JSON
-                    if (byte1 == 0x5C)
-                    {
-                        check_utf8string(false, byte1);
-                        continue;
-                    }
-
-                    // all other characters are OK
-                    check_utf8string(true, byte1);
-                    check_utf8dump(true, byte1);
-                }
-            }
-        }
-
-        SECTION("UTF8-2 (xC2-xDF UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xC2; byte1 <= 0xDF; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(true, byte1, byte2);
-                        check_utf8dump(true, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xC2; byte1 <= 0xDF; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xC2; byte1 <= 0xDF; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0xBF)
-                        {
-                            continue;
-                        }
-
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-        }
-
-        SECTION("UTF8-3 (xE0 xA0-BF UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xE0; byte1 <= 0xE0; ++byte1)
-                {
-                    for (int byte2 = 0xA0; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(true, byte1, byte2, byte3);
-                            check_utf8dump(true, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xE0; byte1 <= 0xE0; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xE0; byte1 <= 0xE0; ++byte1)
-                {
-                    for (int byte2 = 0xA0; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xE0; byte1 <= 0xE0; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0xA0 <= byte2 && byte2 <= 0xBF)
-                        {
-                            continue;
-                        }
-
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xE0; byte1 <= 0xE0; ++byte1)
-                {
-                    for (int byte2 = 0xA0; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // skip correct third byte
-                            if (0x80 <= byte3 && byte3 <= 0xBF)
-                            {
-                                continue;
-                            }
-
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-        }
-
-        SECTION("UTF8-3 (xE1-xEC UTF8-tail UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xE1; byte1 <= 0xEC; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(true, byte1, byte2, byte3);
-                            check_utf8dump(true, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xE1; byte1 <= 0xEC; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xE1; byte1 <= 0xEC; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xE1; byte1 <= 0xEC; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0xBF)
-                        {
-                            continue;
-                        }
-
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xE1; byte1 <= 0xEC; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // skip correct third byte
-                            if (0x80 <= byte3 && byte3 <= 0xBF)
-                            {
-                                continue;
-                            }
-
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-        }
-
-        SECTION("UTF8-3 (xED x80-9F UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xED; byte1 <= 0xED; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x9F; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(true, byte1, byte2, byte3);
-                            check_utf8dump(true, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xED; byte1 <= 0xED; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xED; byte1 <= 0xED; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x9F; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xED; byte1 <= 0xED; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0x9F)
-                        {
-                            continue;
-                        }
-
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xED; byte1 <= 0xED; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x9F; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // skip correct third byte
-                            if (0x80 <= byte3 && byte3 <= 0xBF)
-                            {
-                                continue;
-                            }
-
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-        }
-
-        SECTION("UTF8-3 (xEE-xEF UTF8-tail UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xEE; byte1 <= 0xEF; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(true, byte1, byte2, byte3);
-                            check_utf8dump(true, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xEE; byte1 <= 0xEF; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xEE; byte1 <= 0xEF; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xEE; byte1 <= 0xEF; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0xBF)
-                        {
-                            continue;
-                        }
-
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xEE; byte1 <= 0xEF; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // skip correct third byte
-                            if (0x80 <= byte3 && byte3 <= 0xBF)
-                            {
-                                continue;
-                            }
-
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-        }
-    }
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-unicode3.cpp

@@ -1,326 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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"
-
-// for some reason including this after the json header leads to linker errors with VS 2017...
-#include <locale>
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <fstream>
-#include <sstream>
-#include <iostream>
-#include <iomanip>
-#include "make_test_data_available.hpp"
-#include "test_utils.hpp"
-
-// this test suite uses static variables with non-trivial destructors
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-namespace
-{
-extern size_t calls;
-size_t calls = 0;
-
-void check_utf8dump(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    static std::string json_string;
-    json_string.clear();
-
-    CAPTURE(byte1)
-    CAPTURE(byte2)
-    CAPTURE(byte3)
-    CAPTURE(byte4)
-
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    CAPTURE(json_string)
-
-    // store the string in a JSON value
-    static json j;
-    static json j2;
-    j = json_string;
-    j2 = "abc" + json_string + "xyz";
-
-    static std::string s_ignored;
-    static std::string s_ignored2;
-    static std::string s_ignored_ascii;
-    static std::string s_ignored2_ascii;
-    static std::string s_replaced;
-    static std::string s_replaced2;
-    static std::string s_replaced_ascii;
-    static std::string s_replaced2_ascii;
-
-    // dumping with ignore/replace must not throw in any case
-    s_ignored = j.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored2 = j2.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored_ascii = j.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_ignored2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_replaced = j.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced2 = j2.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced_ascii = j.dump(-1, ' ', true, json::error_handler_t::replace);
-    s_replaced2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::replace);
-
-    if (success_expected)
-    {
-        static std::string s_strict;
-        // strict mode must not throw if success is expected
-        s_strict = j.dump();
-        // all dumps should agree on the string
-        CHECK(s_strict == s_ignored);
-        CHECK(s_strict == s_replaced);
-    }
-    else
-    {
-        // strict mode must throw if success is not expected
-        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
-        // ignore and replace must create different dumps
-        CHECK(s_ignored != s_replaced);
-
-        // check that replace string contains a replacement character
-        CHECK(s_replaced.find("\xEF\xBF\xBD") != std::string::npos);
-    }
-
-    // check that prefix and suffix are preserved
-    CHECK(s_ignored2.substr(1, 3) == "abc");
-    CHECK(s_ignored2.substr(s_ignored2.size() - 4, 3) == "xyz");
-    CHECK(s_ignored2_ascii.substr(1, 3) == "abc");
-    CHECK(s_ignored2_ascii.substr(s_ignored2_ascii.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2.substr(1, 3) == "abc");
-    CHECK(s_replaced2.substr(s_replaced2.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2_ascii.substr(1, 3) == "abc");
-    CHECK(s_replaced2_ascii.substr(s_replaced2_ascii.size() - 4, 3) == "xyz");
-}
-
-void check_utf8string(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-// create and check a JSON string with up to four UTF-8 bytes
-void check_utf8string(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    if (++calls % 100000 == 0)
-    {
-        std::cout << calls << " of 1641521 UTF-8 strings checked" << std::endl; // NOLINT(performance-avoid-endl)
-    }
-
-    static std::string json_string;
-    json_string = "\"";
-
-    CAPTURE(byte1)
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        CAPTURE(byte2)
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        CAPTURE(byte3)
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        CAPTURE(byte4)
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    json_string += "\"";
-
-    CAPTURE(json_string)
-
-    json _;
-    if (success_expected)
-    {
-        CHECK_NOTHROW(_ = json::parse(json_string));
-    }
-    else
-    {
-        CHECK_THROWS_AS(_ = json::parse(json_string), json::parse_error&);
-    }
-}
-} // namespace
-
-TEST_CASE("Unicode (3/5)" * doctest::skip())
-{
-    SECTION("RFC 3629")
-    {
-        /*
-        RFC 3629 describes in Sect. 4 the syntax of UTF-8 byte sequences as
-        follows:
-
-            A UTF-8 string is a sequence of octets representing a sequence of UCS
-            characters.  An octet sequence is valid UTF-8 only if it matches the
-            following syntax, which is derived from the rules for encoding UTF-8
-            and is expressed in the ABNF of [RFC2234].
-
-            UTF8-octets = *( UTF8-char )
-            UTF8-char   = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
-            UTF8-1      = %x00-7F
-            UTF8-2      = %xC2-DF UTF8-tail
-            UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
-                          %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
-            UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
-                          %xF4 %x80-8F 2( UTF8-tail )
-            UTF8-tail   = %x80-BF
-        */
-
-        SECTION("UTF8-4 (xF0 x90-BF UTF8-tail UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
-                            {
-                                check_utf8string(true, byte1, byte2, byte3, byte4);
-                                check_utf8dump(true, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing fourth byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x90 <= byte2 && byte2 <= 0xBF)
-                        {
-                            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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // 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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong fourth byte")
-            {
-                for (int byte1 = 0xF0; byte1 <= 0xF0; ++byte1)
-                {
-                    for (int byte2 = 0x90; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
-                            {
-                                // skip correct fourth byte
-                                if (0x80 <= byte4 && byte4 <= 0xBF)
-                                {
-                                    continue;
-                                }
-
-                                check_utf8string(false, byte1, byte2, byte3, byte4);
-                                check_utf8dump(false, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-unicode4.cpp

@@ -1,326 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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"
-
-// for some reason including this after the json header leads to linker errors with VS 2017...
-#include <locale>
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <fstream>
-#include <sstream>
-#include <iostream>
-#include <iomanip>
-#include "make_test_data_available.hpp"
-#include "test_utils.hpp"
-
-// this test suite uses static variables with non-trivial destructors
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-namespace
-{
-extern size_t calls;
-size_t calls = 0;
-
-void check_utf8dump(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    static std::string json_string;
-    json_string.clear();
-
-    CAPTURE(byte1)
-    CAPTURE(byte2)
-    CAPTURE(byte3)
-    CAPTURE(byte4)
-
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    CAPTURE(json_string)
-
-    // store the string in a JSON value
-    static json j;
-    static json j2;
-    j = json_string;
-    j2 = "abc" + json_string + "xyz";
-
-    static std::string s_ignored;
-    static std::string s_ignored2;
-    static std::string s_ignored_ascii;
-    static std::string s_ignored2_ascii;
-    static std::string s_replaced;
-    static std::string s_replaced2;
-    static std::string s_replaced_ascii;
-    static std::string s_replaced2_ascii;
-
-    // dumping with ignore/replace must not throw in any case
-    s_ignored = j.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored2 = j2.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored_ascii = j.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_ignored2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_replaced = j.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced2 = j2.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced_ascii = j.dump(-1, ' ', true, json::error_handler_t::replace);
-    s_replaced2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::replace);
-
-    if (success_expected)
-    {
-        static std::string s_strict;
-        // strict mode must not throw if success is expected
-        s_strict = j.dump();
-        // all dumps should agree on the string
-        CHECK(s_strict == s_ignored);
-        CHECK(s_strict == s_replaced);
-    }
-    else
-    {
-        // strict mode must throw if success is not expected
-        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
-        // ignore and replace must create different dumps
-        CHECK(s_ignored != s_replaced);
-
-        // check that replace string contains a replacement character
-        CHECK(s_replaced.find("\xEF\xBF\xBD") != std::string::npos);
-    }
-
-    // check that prefix and suffix are preserved
-    CHECK(s_ignored2.substr(1, 3) == "abc");
-    CHECK(s_ignored2.substr(s_ignored2.size() - 4, 3) == "xyz");
-    CHECK(s_ignored2_ascii.substr(1, 3) == "abc");
-    CHECK(s_ignored2_ascii.substr(s_ignored2_ascii.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2.substr(1, 3) == "abc");
-    CHECK(s_replaced2.substr(s_replaced2.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2_ascii.substr(1, 3) == "abc");
-    CHECK(s_replaced2_ascii.substr(s_replaced2_ascii.size() - 4, 3) == "xyz");
-}
-
-void check_utf8string(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-// create and check a JSON string with up to four UTF-8 bytes
-void check_utf8string(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    if (++calls % 100000 == 0)
-    {
-        std::cout << calls << " of 5517507 UTF-8 strings checked" << std::endl; // NOLINT(performance-avoid-endl)
-    }
-
-    static std::string json_string;
-    json_string = "\"";
-
-    CAPTURE(byte1)
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        CAPTURE(byte2)
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        CAPTURE(byte3)
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        CAPTURE(byte4)
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    json_string += "\"";
-
-    CAPTURE(json_string)
-
-    json _;
-    if (success_expected)
-    {
-        CHECK_NOTHROW(_ = json::parse(json_string));
-    }
-    else
-    {
-        CHECK_THROWS_AS(_ = json::parse(json_string), json::parse_error&);
-    }
-}
-} // namespace
-
-TEST_CASE("Unicode (4/5)" * doctest::skip())
-{
-    SECTION("RFC 3629")
-    {
-        /*
-        RFC 3629 describes in Sect. 4 the syntax of UTF-8 byte sequences as
-        follows:
-
-            A UTF-8 string is a sequence of octets representing a sequence of UCS
-            characters.  An octet sequence is valid UTF-8 only if it matches the
-            following syntax, which is derived from the rules for encoding UTF-8
-            and is expressed in the ABNF of [RFC2234].
-
-            UTF8-octets = *( UTF8-char )
-            UTF8-char   = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
-            UTF8-1      = %x00-7F
-            UTF8-2      = %xC2-DF UTF8-tail
-            UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
-                          %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
-            UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
-                          %xF4 %x80-8F 2( UTF8-tail )
-            UTF8-tail   = %x80-BF
-        */
-
-        SECTION("UTF8-4 (xF1-F3 UTF8-tail UTF8-tail UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
-                            {
-                                check_utf8string(true, byte1, byte2, byte3, byte4);
-                                check_utf8dump(true, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing fourth byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0xBF)
-                        {
-                            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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // 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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong fourth byte")
-            {
-                for (int byte1 = 0xF1; byte1 <= 0xF3; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0xBF; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
-                            {
-                                // skip correct fourth byte
-                                if (0x80 <= byte4 && byte4 <= 0xBF)
-                                {
-                                    continue;
-                                }
-
-                                check_utf8string(false, byte1, byte2, byte3, byte4);
-                                check_utf8dump(false, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-unicode5.cpp

@@ -1,326 +0,0 @@
-//     __ _____ _____ _____
-//  __|  |   __|     |   | |  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"
-
-// for some reason including this after the json header leads to linker errors with VS 2017...
-#include <locale>
-
-#include <nlohmann/json.hpp>
-using nlohmann::json;
-
-#include <fstream>
-#include <sstream>
-#include <iostream>
-#include <iomanip>
-#include "make_test_data_available.hpp"
-#include "test_utils.hpp"
-
-// this test suite uses static variables with non-trivial destructors
-DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
-DOCTEST_CLANG_SUPPRESS_WARNING("-Wexit-time-destructors")
-
-namespace
-{
-extern size_t calls;
-size_t calls = 0;
-
-void check_utf8dump(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    static std::string json_string;
-    json_string.clear();
-
-    CAPTURE(byte1)
-    CAPTURE(byte2)
-    CAPTURE(byte3)
-    CAPTURE(byte4)
-
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    CAPTURE(json_string)
-
-    // store the string in a JSON value
-    static json j;
-    static json j2;
-    j = json_string;
-    j2 = "abc" + json_string + "xyz";
-
-    static std::string s_ignored;
-    static std::string s_ignored2;
-    static std::string s_ignored_ascii;
-    static std::string s_ignored2_ascii;
-    static std::string s_replaced;
-    static std::string s_replaced2;
-    static std::string s_replaced_ascii;
-    static std::string s_replaced2_ascii;
-
-    // dumping with ignore/replace must not throw in any case
-    s_ignored = j.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored2 = j2.dump(-1, ' ', false, json::error_handler_t::ignore);
-    s_ignored_ascii = j.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_ignored2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::ignore);
-    s_replaced = j.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced2 = j2.dump(-1, ' ', false, json::error_handler_t::replace);
-    s_replaced_ascii = j.dump(-1, ' ', true, json::error_handler_t::replace);
-    s_replaced2_ascii = j2.dump(-1, ' ', true, json::error_handler_t::replace);
-
-    if (success_expected)
-    {
-        static std::string s_strict;
-        // strict mode must not throw if success is expected
-        s_strict = j.dump();
-        // all dumps should agree on the string
-        CHECK(s_strict == s_ignored);
-        CHECK(s_strict == s_replaced);
-    }
-    else
-    {
-        // strict mode must throw if success is not expected
-        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
-        // ignore and replace must create different dumps
-        CHECK(s_ignored != s_replaced);
-
-        // check that replace string contains a replacement character
-        CHECK(s_replaced.find("\xEF\xBF\xBD") != std::string::npos);
-    }
-
-    // check that prefix and suffix are preserved
-    CHECK(s_ignored2.substr(1, 3) == "abc");
-    CHECK(s_ignored2.substr(s_ignored2.size() - 4, 3) == "xyz");
-    CHECK(s_ignored2_ascii.substr(1, 3) == "abc");
-    CHECK(s_ignored2_ascii.substr(s_ignored2_ascii.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2.substr(1, 3) == "abc");
-    CHECK(s_replaced2.substr(s_replaced2.size() - 4, 3) == "xyz");
-    CHECK(s_replaced2_ascii.substr(1, 3) == "abc");
-    CHECK(s_replaced2_ascii.substr(s_replaced2_ascii.size() - 4, 3) == "xyz");
-}
-
-void check_utf8string(bool success_expected, int byte1, int byte2, int byte3, int byte4);
-
-// create and check a JSON string with up to four UTF-8 bytes
-void check_utf8string(bool success_expected, int byte1, int byte2 = -1, int byte3 = -1, int byte4 = -1)
-{
-    if (++calls % 100000 == 0)
-    {
-        std::cout << calls << " of 1246225 UTF-8 strings checked" << std::endl; // NOLINT(performance-avoid-endl)
-    }
-
-    static std::string json_string;
-    json_string = "\"";
-
-    CAPTURE(byte1)
-    json_string += std::string(1, static_cast<char>(byte1));
-
-    if (byte2 != -1)
-    {
-        CAPTURE(byte2)
-        json_string += std::string(1, static_cast<char>(byte2));
-    }
-
-    if (byte3 != -1)
-    {
-        CAPTURE(byte3)
-        json_string += std::string(1, static_cast<char>(byte3));
-    }
-
-    if (byte4 != -1)
-    {
-        CAPTURE(byte4)
-        json_string += std::string(1, static_cast<char>(byte4));
-    }
-
-    json_string += "\"";
-
-    CAPTURE(json_string)
-
-    json _;
-    if (success_expected)
-    {
-        CHECK_NOTHROW(_ = json::parse(json_string));
-    }
-    else
-    {
-        CHECK_THROWS_AS(_ = json::parse(json_string), json::parse_error&);
-    }
-}
-} // namespace
-
-TEST_CASE("Unicode (5/5)" * doctest::skip())
-{
-    SECTION("RFC 3629")
-    {
-        /*
-        RFC 3629 describes in Sect. 4 the syntax of UTF-8 byte sequences as
-        follows:
-
-            A UTF-8 string is a sequence of octets representing a sequence of UCS
-            characters.  An octet sequence is valid UTF-8 only if it matches the
-            following syntax, which is derived from the rules for encoding UTF-8
-            and is expressed in the ABNF of [RFC2234].
-
-            UTF8-octets = *( UTF8-char )
-            UTF8-char   = UTF8-1 / UTF8-2 / UTF8-3 / UTF8-4
-            UTF8-1      = %x00-7F
-            UTF8-2      = %xC2-DF UTF8-tail
-            UTF8-3      = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
-                          %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
-            UTF8-4      = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
-                          %xF4 %x80-8F 2( UTF8-tail )
-            UTF8-tail   = %x80-BF
-        */
-
-        SECTION("UTF8-4 (xF4 x80-8F UTF8-tail UTF8-tail)")
-        {
-            SECTION("well-formed")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x8F; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x80; byte4 <= 0xBF; ++byte4)
-                            {
-                                check_utf8string(true, byte1, byte2, byte3, byte4);
-                                check_utf8dump(true, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing second byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    check_utf8string(false, byte1);
-                    check_utf8dump(false, byte1);
-                }
-            }
-
-            SECTION("ill-formed: missing third byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x8F; ++byte2)
-                    {
-                        check_utf8string(false, byte1, byte2);
-                        check_utf8dump(false, byte1, byte2);
-                    }
-                }
-            }
-
-            SECTION("ill-formed: missing fourth byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x8F; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            check_utf8string(false, byte1, byte2, byte3);
-                            check_utf8dump(false, byte1, byte2, byte3);
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong second byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x00; byte2 <= 0xFF; ++byte2)
-                    {
-                        // skip correct second byte
-                        if (0x80 <= byte2 && byte2 <= 0x8F)
-                        {
-                            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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong third byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x8F; ++byte2)
-                    {
-                        for (int byte3 = 0x00; byte3 <= 0xFF; ++byte3)
-                        {
-                            // 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);
-                            }
-                        }
-                    }
-                }
-            }
-
-            SECTION("ill-formed: wrong fourth byte")
-            {
-                for (int byte1 = 0xF4; byte1 <= 0xF4; ++byte1)
-                {
-                    for (int byte2 = 0x80; byte2 <= 0x8F; ++byte2)
-                    {
-                        for (int byte3 = 0x80; byte3 <= 0xBF; ++byte3)
-                        {
-                            for (int byte4 = 0x00; byte4 <= 0xFF; ++byte4)
-                            {
-                                // skip correct fourth byte
-                                if (0x80 <= byte4 && byte4 <= 0xBF)
-                                {
-                                    continue;
-                                }
-
-                                check_utf8string(false, byte1, byte2, byte3, byte4);
-                                check_utf8dump(false, byte1, byte2, byte3, byte4);
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-}
-
-DOCTEST_CLANG_SUPPRESS_WARNING_POP