Add tests for uncovered code paths

Cover code the test suite did not reach, found from the Coveralls report
of develop and a local coverage run of HEAD:

- dump() of every kind of value below the bound of the recursive descent
  (pretty-printed objects, binary values, discarded values, scalars), and
  flushes of the escape and write buffers mid-string and mid-binary
- the iterative comparison: objects with different keys, containers that
  are a prefix of each other, and elements that cannot be ordered, each
  both at the top level and below the nesting bound
- SAX handlers that stop at any event, including the end of a nested
  container, in the BSON, CBOR, MessagePack, UBJSON and BJData readers
- from_bson/cbor/msgpack/ubjson/bjdata returning a discarded value
  through the iterator and pointer overloads
- JSON Patch, diff, merge_patch and update(..., true) on ordered_json
- smaller gaps: get_allocator(), to_ubjson/to_bjdata into a string,
  value() with an unresolvable JSON pointer, integer/float comparison
  below the integer range and with negative fractions, conversion to a
  custom binary type, std::formatter::parse on a spec without '}',
  unescape() of a lone '~', and the callback parser's start_array()

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

tests/src/unit-allocator.cpp

@@ -37,6 +37,12 @@ struct bad_allocator : std::allocator<T>
 };
 } // namespace
 
+TEST_CASE("get_allocator")
+{
+    const auto alloc = nlohmann::json::get_allocator();
+    CHECK(alloc == std::allocator<nlohmann::json>());
+}
+
 TEST_CASE("bad_alloc")
 {
     SECTION("bad_alloc")

tests/src/unit-bjdata.cpp

@@ -3763,6 +3763,49 @@ TEST_CASE("BJData")
     }
 }
 
+TEST_CASE("BJData input that cannot be read is discarded by every overload")
+{
+    std::vector<std::uint8_t> input = json::to_bjdata(json({{"a", {1, 2}}}));
+    input.pop_back();
+
+    json _;
+    CHECK_THROWS_AS(_ = json::from_bjdata(input.begin(), input.end()), json::parse_error&);
+    CHECK(json::from_bjdata(input, true, false).is_discarded());
+    CHECK(json::from_bjdata(input.begin(), input.end(), true, false).is_discarded());
+}
+
+TEST_CASE("BJData SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::bjdata))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_bjdata(j)) == 20);
+    CHECK(count_events(json::to_bjdata(j, true)) == 20);
+    CHECK(count_events(json::to_bjdata(j, true, true)) == 20);
+
+    // an ND-array is announced as an annotated object: start_object, then
+    // _ArrayType_, _ArraySize_ and _ArrayData_ with its elements
+    const json ndarray = json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": [2, 2], "_ArrayData_": [1, 2, 3, 4]})");
+    CHECK(count_events(json::to_bjdata(ndarray, true, true)) == 16);
+}
+
 TEST_CASE("issue #5405 - array reserve for definite-length BJData arrays")
 {
 #if !defined(JSON_NOEXCEPTION)
@@ -4247,6 +4290,54 @@ TEST_CASE("all BJData first bytes")
 }
 #endif
 
+TEST_CASE("BJData and UBJSON can be written to a string")
+{
+    const std::vector<json> values =
+    {
+        {{"a", {1, 2.5, "x", nullptr}}, {"b", json::binary({1, 2})}},
+        // an annotated ND-array, and objects that only look like one
+        json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": [2, 2], "_ArrayData_": [1, 2, 3, 4]})"),
+        json::parse(R"({"_ArrayType_": 1, "_ArraySize_": [2, 2], "_ArrayData_": [1, 2, 3, 4]})"),
+        json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": 4, "_ArrayData_": [1, 2, 3, 4]})"),
+        json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": [2, -2], "_ArrayData_": [1, 2, 3, 4]})"),
+        json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": [2, 2], "_ArrayData_": [1, 2, 3]})"),
+        json::parse(R"({"_ArrayType_": "uint8", "_ArraySize_": [2, 2], "_ArrayData_": 1})"),
+    };
+
+    for (const auto& j : values)
+    {
+        CAPTURE(j.dump());
+        for (const bool use_size :
+                {
+                    false, true
+                })
+        {
+            for (const bool use_type :
+                    {
+                        false, true
+                    })
+            {
+                if (use_type && !use_size)
+                {
+                    continue;
+                }
+                CAPTURE(use_size);
+                CAPTURE(use_type);
+
+                const auto bjdata = json::to_bjdata(j, use_size, use_type);
+                std::string bjdata_string;
+                json::to_bjdata(j, bjdata_string, use_size, use_type);
+                CHECK(bjdata_string == std::string(bjdata.begin(), bjdata.end()));
+
+                const auto ubjson = json::to_ubjson(j, use_size, use_type);
+                std::string ubjson_string;
+                json::to_ubjson(j, ubjson_string, use_size, use_type);
+                CHECK(ubjson_string == std::string(ubjson.begin(), ubjson.end()));
+            }
+        }
+    }
+}
+
 TEST_CASE("BJData use_type requires use_size")
 {
     SECTION("non-empty object throws other_error.502")
@@ -4265,6 +4356,17 @@ TEST_CASE("BJData use_type requires use_size")
                              json::other_error&);
     }
 
+    SECTION("non-empty binary value throws other_error.502")
+    {
+        const json j = json::binary({1, 2, 3});
+        CHECK_THROWS_WITH_AS(json::to_bjdata(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+        CHECK_THROWS_WITH_AS(json::to_ubjson(j, false, true),
+                             "[json.exception.other_error.502] use_type requires use_size = true",
+                             json::other_error&);
+    }
+
     SECTION("scalars do not throw with use_type=true, use_count=false")
     {
         CHECK_NOTHROW(json::to_bjdata(42, false, true));

tests/src/unit-bson.cpp

@@ -1244,6 +1244,44 @@ TEST_CASE("BSON nesting does not consume the call stack")
     }
 }
 
+TEST_CASE("BSON input that cannot be read is discarded by every overload")
+{
+    std::vector<std::uint8_t> input = json::to_bson(json({{"a", {1, 2}}}));
+    input.pop_back();
+
+    json _;
+    CHECK_THROWS_AS(_ = json::from_bson(input.begin(), input.end()), json::parse_error&);
+    CHECK(json::from_bson(input, true, false).is_discarded());
+    CHECK(json::from_bson(input.begin(), input.end(), true, false).is_discarded());
+    CHECK(json::from_bson(input.data(), input.size(), true, false).is_discarded());
+    CHECK(json::from_bson({input.data(), input.size()}, true, false).is_discarded());
+}
+
+TEST_CASE("BSON SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::bson))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_bson(j)) == 20);
+}
+
 TEST_CASE("BSON numerical data")
 {
     SECTION("number")

tests/src/unit-cbor.cpp

@@ -2122,6 +2122,45 @@ TEST_CASE("CBOR nesting does not consume the call stack")
     }
 }
 
+TEST_CASE("CBOR input that cannot be read is discarded by every overload")
+{
+    std::vector<std::uint8_t> input = json::to_cbor(json({{"a", {1, 2}}}));
+    input.pop_back();
+
+    json _;
+    CHECK_THROWS_AS(_ = json::from_cbor(input.begin(), input.end()), json::parse_error&);
+    CHECK(json::from_cbor(input, true, false).is_discarded());
+    CHECK(json::from_cbor(input.begin(), input.end(), true, false).is_discarded());
+    CHECK(json::from_cbor(input.data(), input.size(), true, false).is_discarded());
+    CHECK(json::from_cbor({input.data(), input.size()}, true, false).is_discarded());
+}
+
+TEST_CASE("CBOR SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::cbor))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_cbor(j)) == 20);
+    CHECK(count_events(std::vector<std::uint8_t>({0xBF, 0x61, 'a', 0x9F, 0x01, 0xFF, 0xFF})) == 6);
+}
+
 TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
 {
     // Reading an indefinite-length string or byte array used to call itself

tests/src/unit-comparison.cpp

@@ -359,6 +359,15 @@ TEST_CASE("lexicographical comparison operators")
             CHECK(json(1) < json(1.5));
             CHECK(json(1.5) < json(2));
             CHECK(json(2) > json(1.5));
+            CHECK(json(-1) > json(-1.5));
+            CHECK(json(-1.5) < json(-1));
+            CHECK(json(-2) < json(-1.5));
+
+            // a float below the range of the integer type
+            CHECK(json(0) > json(-1e30));
+            CHECK(json(-1e30) < json(0));
+            CHECK(json(0u) > json(-0.5));
+            CHECK(json(-0.5) < json(0u));
 
             // a NaN operand stays unordered against either integer kind
             CHECK_FALSE(json(1) == json(nan));
@@ -735,3 +744,84 @@ TEST_CASE("regression #3868 - heterogeneous comparisons compile under C++20 (P24
     }
 }
 #endif
+
+TEST_CASE("containers are compared element by element")
+{
+    // Containers nested deeper than a bound are compared without the call
+    // stack, by code of their own; every relation is checked both at the top
+    // level and below that bound.
+    const auto deep = [](const json & j, const std::size_t depth)
+    {
+        json result = j;
+        for (std::size_t i = 0; i < depth; ++i)
+        {
+            result = json::array({std::move(result)});
+        }
+        return result;
+    };
+
+    for (const std::size_t depth : std::vector<std::size_t> {0, 200})
+    {
+        CAPTURE(depth);
+
+        // objects with different keys
+        {
+            const json a = deep({{"a", 1}}, depth);
+            const json b = deep({{"b", 1}}, depth);
+            CHECK_FALSE(a == b);
+            CHECK(a != b);
+            CHECK(a < b);
+            CHECK(b > a);
+            CHECK_FALSE(b < a);
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((a <=> b) == std::partial_ordering::less); // *NOPAD*
+            CHECK((b <=> a) == std::partial_ordering::greater); // *NOPAD*
+            CHECK((a <=> a) == std::partial_ordering::equivalent); // *NOPAD*
+#endif
+        }
+
+        // a container that is a prefix of the other one
+        {
+            // the one that runs out of elements first is the smaller one
+            const json shorter = deep({1}, depth);
+            const json longer = deep({1, 2}, depth);
+            CHECK(shorter < longer);
+            CHECK(longer > shorter);
+            CHECK_FALSE(longer < shorter);
+            CHECK_FALSE(shorter == longer);
+
+            const json smaller_object = deep({{"a", 1}}, depth);
+            const json larger_object = deep({{"a", 1}, {"b", 2}}, depth);
+            CHECK(smaller_object < larger_object);
+            CHECK(larger_object > smaller_object);
+            CHECK_FALSE(smaller_object == larger_object);
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            CHECK((shorter <=> longer) == std::partial_ordering::less); // *NOPAD*
+            CHECK((longer <=> shorter) == std::partial_ordering::greater); // *NOPAD*
+#endif
+        }
+
+        // elements that cannot be ordered
+        {
+            const double nan = std::numeric_limits<double>::quiet_NaN();
+            const json lhs = deep({nan, 1}, depth);
+            const json rhs = deep({nan, 2}, depth);
+
+            CHECK_FALSE(lhs == lhs);
+            CHECK_FALSE(rhs < lhs);
+#if JSON_HAS_THREE_WAY_COMPARISON
+            // JSON_HAS_CPP_20 (do not remove; see note at top of file)
+            // operator<=> stops there, as std::lexicographical_compare_three_way
+            // does, and operator< is derived from it
+            CHECK((lhs <=> rhs) == std::partial_ordering::unordered); // *NOPAD*
+            CHECK_FALSE(lhs < rhs);
+#else
+            // operator< skips a pair of elements that cannot be ordered, as
+            // std::lexicographical_compare does, and the next pair decides
+            CHECK(lhs < rhs);
+#endif
+        }
+    }
+}

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

@@ -49,6 +49,16 @@ TEST_CASE("binary type whose value type is not std::uint8_t")
         CHECK(char_binary_json::binary({}).dump() == R"({"bytes":[],"subtype":null})");
     }
 
+    SECTION("a value is converted to the binary type if it is binary or an array")
+    {
+        const std::vector<char> chars{'\0', '\x01', '\x7F'};
+        CHECK(char_binary_json::binary(chars).get<std::vector<char>>() == chars);
+        CHECK(char_binary_json({0, 1, 127}).get<std::vector<char>>() == chars);
+        CHECK_THROWS_WITH_AS(char_binary_json(1).get<std::vector<char>>(),
+                             "[json.exception.type_error.302] type must be binary or array, but is number",
+                             char_binary_json::type_error&);
+    }
+
     SECTION("the default binary type is unchanged")
     {
         CHECK(nlohmann::json::binary({0, 1, 255}, 42).dump() == R"({"bytes":[0,1,255],"subtype":42})");

tests/src/unit-element_access2.cpp

@@ -1517,6 +1517,16 @@ TEST_CASE_TEMPLATE("element access 2 (throwing tests)", Json, nlohmann::json, nl
                     CHECK(j.value("/not/existing"_json_pointer, Json({{"foo", "bar"}})) == Json({{"foo", "bar"}}));
                     CHECK(j.value("/not/existing"_json_pointer, Json({10, 100})) == Json({10, 100}));
 
+                    // an array index that is out of range, too large to be
+                    // represented, or "-", and a token below a scalar
+                    CHECK(j.value("/array/3"_json_pointer, 2) == 2);
+                    CHECK(j.value("/array/-"_json_pointer, 2) == 2);
+                    CHECK(j.value("/array/99999999999999999999999999"_json_pointer, 2) == 2);
+                    CHECK(j.value("/integer/0"_json_pointer, 2) == 2);
+                    CHECK(j.value("/string/x"_json_pointer, 2) == 2);
+                    CHECK(j.value("/null/x"_json_pointer, 2) == 2);
+                    CHECK(j.value("/array/0"_json_pointer, 2) == 1);
+
                     CHECK(j_const.value("/not/existing"_json_pointer, 2) == 2);
                     CHECK(j_const.value("/not/existing"_json_pointer, 2u) == 2u);
                     CHECK(j_const.value("/not/existing"_json_pointer, false) == false);

tests/src/unit-json_patch.cpp

@@ -1751,3 +1751,72 @@ TEST_CASE("JSON patch - diff emits array removals in descending index order")
         CHECK(source.patch(patch) == target);
     }
 }
+
+TEST_CASE("JSON patch - every operation on ordered_json")
+{
+    using nlohmann::ordered_json;
+
+    const ordered_json doc = {{"foo", "bar"}, {"arr", {1, 2, 3}}, {"obj", {{"a", 1}}}};
+
+    SECTION("successful operations")
+    {
+        const ordered_json patch = ordered_json::parse(R"([
+            {"op": "add", "path": "/obj/b", "value": 2},
+            {"op": "add", "path": "/arr/1", "value": 9},
+            {"op": "add", "path": "/arr/-", "value": 4},
+            {"op": "remove", "path": "/arr/0"},
+            {"op": "remove", "path": "/obj/a"},
+            {"op": "replace", "path": "/foo", "value": "baz"},
+            {"op": "move", "from": "/foo", "path": "/moved"},
+            {"op": "copy", "from": "/obj", "path": "/copied"},
+            {"op": "test", "path": "/copied/b", "value": 2}
+        ])");
+
+        const ordered_json expected = ordered_json::parse(R"({
+            "arr": [9, 2, 3, 4], "obj": {"b": 2}, "moved": "baz", "copied": {"b": 2}
+        })");
+
+        CHECK(doc.patch(patch) == expected);
+
+        // adding to the root replaces the document
+        CHECK(doc.patch(ordered_json::parse(R"([{"op": "add", "path": "", "value": [1]}])")) == ordered_json({1}));
+    }
+
+    SECTION("failing operations")
+    {
+        ordered_json _;
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "add", "path": "/arr/4", "value": 1}])")),
+                             "[json.exception.out_of_range.401] array index 4 is out of range", ordered_json::out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "add", "path": "/nope/x", "value": 1}])")),
+                             "[json.exception.out_of_range.403] key 'nope' not found", ordered_json::out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "remove", "path": "/obj/nope"}])")),
+                             "[json.exception.out_of_range.403] key 'nope' not found", ordered_json::out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "remove", "path": "/arr/3"}])")),
+                             "[json.exception.out_of_range.401] array index 3 is out of range", ordered_json::out_of_range&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "test", "path": "/foo", "value": "qux"}])")),
+                             "[json.exception.other_error.501] unsuccessful: {\"op\":\"test\",\"path\":\"/foo\",\"value\":\"qux\"}", ordered_json::other_error&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "add", "path": "/foo"}])")),
+                             "[json.exception.parse_error.105] parse error: operation 'add' must have member 'value'", ordered_json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = doc.patch(ordered_json::parse(R"([{"op": "move", "from": "/obj", "path": "/obj/a/b"}])")),
+                             "[json.exception.out_of_range.414] cannot move value: 'from' path '/obj' is a proper prefix of 'path' '/obj/a/b'", ordered_json::out_of_range&);
+    }
+
+    SECTION("diff reproduces the target")
+    {
+        const ordered_json source = {{"a", 1}, {"b", 2}, {"c", {{"x", 1}}}, {"l", {1, 2, 3}}};
+        const std::vector<ordered_json> targets =
+        {
+            // a key removed, a key added, a nested change, a shorter array
+            {{"a", 1}, {"c", {{"x", 2}}}, {"l", {1}}, {"d", 4}},
+            // the same keys in another order
+            {{"c", {{"x", 1}}}, {"a", 1}, {"b", 2}, {"l", {1, 2, 3}}},
+            // new keys ahead of the common ones
+            {{"new", true}, {"a", 1}, {"b", 3}, {"c", {{"x", 1}}}, {"l", {1, 2, 3}}},
+        };
+        for (const auto& target : targets)
+        {
+            CAPTURE(target.dump());
+            CHECK(source.patch(ordered_json::diff(source, target)) == target);
+        }
+    }
+}

tests/src/unit-json_pointer.cpp

@@ -872,3 +872,16 @@ TEST_CASE("JSON pointers")
     }
 #endif
 }
+
+TEST_CASE("unescaping keeps a '~' that does not start an escape sequence")
+{
+    // the parser of a JSON pointer rejects such reference tokens before it
+    // unescapes them, so this is only reachable by calling unescape directly
+    std::string s = "a~2b~";
+    nlohmann::detail::unescape(s);
+    CHECK(s == "a~2b~");
+
+    s = "~0~1~";
+    nlohmann::detail::unescape(s);
+    CHECK(s == "~/~");
+}

tests/src/unit-merge_patch.cpp

@@ -345,3 +345,32 @@ TEST_CASE("JSON Merge Patch on deeply nested values")
         CHECK(p->at("x") == 1);
     }
 }
+
+TEST_CASE("JSON Merge Patch and update on ordered_json")
+{
+    using nlohmann::ordered_json;
+
+    SECTION("merge_patch")
+    {
+        ordered_json target = ordered_json::parse(R"({"a": {"b": 1, "c": 2}, "d": 3, "e": [1]})");
+        target.merge_patch(ordered_json::parse(R"({"a": {"b": null, "f": 4}, "d": {"x": {"y": null}}, "e": null, "g": {"h": 5}})"));
+        CHECK(target == ordered_json::parse(R"({"a": {"c": 2, "f": 4}, "d": {"x": {}}, "g": {"h": 5}})"));
+
+        // a patch that is not an object replaces the target
+        target.merge_patch(ordered_json({1, 2}));
+        CHECK(target == ordered_json({1, 2}));
+        // an object patch turns a target that is not an object into one
+        target.merge_patch(ordered_json::parse(R"({"k": {"l": null}})"));
+        CHECK(target == ordered_json::parse(R"({"k": {}})"));
+    }
+
+    SECTION("update with merge_objects")
+    {
+        ordered_json target = ordered_json::parse(R"({"a": {"b": 1, "c": {"d": 2}}, "e": 3})");
+        target.update(ordered_json::parse(R"({"a": {"c": {"x": 1}, "f": 4}, "e": {"y": 5}, "g": 6})"), true);
+        CHECK(target == ordered_json::parse(R"({"a": {"b": 1, "c": {"d": 2, "x": 1}, "f": 4}, "e": {"y": 5}, "g": 6})"));
+
+        target.update(ordered_json::parse(R"({"a": 1})"), false);
+        CHECK(target == ordered_json::parse(R"({"a": 1, "e": {"y": 5}, "g": 6})"));
+    }
+}

tests/src/unit-msgpack.cpp

@@ -1759,6 +1759,44 @@ TEST_CASE("MessagePack nesting does not consume the call stack")
     }
 }
 
+TEST_CASE("MessagePack input that cannot be read is discarded by every overload")
+{
+    std::vector<std::uint8_t> input = json::to_msgpack(json({{"a", {1, 2}}}));
+    input.pop_back();
+
+    json _;
+    CHECK_THROWS_AS(_ = json::from_msgpack(input.begin(), input.end()), json::parse_error&);
+    CHECK(json::from_msgpack(input, true, false).is_discarded());
+    CHECK(json::from_msgpack(input.begin(), input.end(), true, false).is_discarded());
+    CHECK(json::from_msgpack(input.data(), input.size(), true, false).is_discarded());
+    CHECK(json::from_msgpack({input.data(), input.size()}, true, false).is_discarded());
+}
+
+TEST_CASE("MessagePack SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::msgpack))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_msgpack(j)) == 20);
+}
+
 TEST_CASE("single MessagePack roundtrip")
 {
     SECTION("sample.json")

tests/src/unit-serialization.cpp

@@ -629,3 +629,153 @@ TEST_CASE("serialization of deeply nested values")
         }
     }
 }
+
+namespace
+{
+// wraps @a inner into @a depth single-element arrays
+json wrap_in_arrays(const json& inner, const std::size_t depth)
+{
+    json j = inner;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        j = json::array({std::move(j)});
+    }
+    return j;
+}
+
+// what wrap_in_arrays(inner, depth).dump(2) is expected to be: the arrays
+// around inner.dump(2), with inner's own lines indented by the depth
+std::string expected_pretty_in_arrays(const json& inner, const std::size_t depth)
+{
+    std::string expected;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        expected += std::string(2 * i, ' ') + "[\n";
+    }
+
+    const std::string indent(2 * depth, ' ');
+    expected += indent;
+    for (const char c : inner.dump(2))
+    {
+        expected += c;
+        if (c == '\n')
+        {
+            expected += indent;
+        }
+    }
+
+    for (std::size_t i = depth; i > 0; --i)
+    {
+        expected += '\n' + std::string(2 * (i - 1), ' ') + ']';
+    }
+    return expected;
+}
+} // namespace
+
+TEST_CASE("serialization of every kind of value below the bound of the descent")
+{
+    // Values nested deeper than the bound are written without the call stack,
+    // by code of their own; each kind of value must come out the same there as
+    // it does at the top level, compact and pretty-printed.
+    std::vector<json> values =
+    {
+        json::parse(R"({"a": 1, "b": [1, 2, {"c": "x"}], "d": {}, "e": []})"),
+        json::parse(R"([1, [2, 3], {"k": null}, "s"])"),
+        json::object(),
+        json::array(),
+        json::binary({1, 2, 3}, 42),
+        json::binary({1, 2, 3}),
+        json::binary({}, 7),
+        json::binary({}),
+        "a string with \"escapes\"\n",
+        true,
+        false,
+        -42,
+        42u,
+        1.5,
+        nullptr,
+        json(json::value_t::discarded),
+    };
+    // a pretty-printed object whose members are themselves deep
+    values.push_back({{"x", wrap_in_arrays(1, 5)}, {"y", {{"z", 2}}}});
+
+    for (const std::size_t depth : std::vector<std::size_t> {1, 200})
+    {
+        CAPTURE(depth);
+        for (const auto& inner : values)
+        {
+            CAPTURE(inner.dump());
+            const json j = wrap_in_arrays(inner, depth);
+            CHECK(j.dump() == std::string(depth, '[') + inner.dump() + std::string(depth, ']'));
+            CHECK(j.dump(2) == expected_pretty_in_arrays(inner, depth));
+        }
+    }
+
+    SECTION("pretty-printed objects across the bound")
+    {
+        for (std::size_t d = 120; d <= 140; ++d)
+        {
+            CAPTURE(d);
+
+            // built from the inside out: {"k": <level below>, "n": <level>}
+            json j = 7;
+            std::string expected = "7";
+            for (std::size_t i = d; i > 0; --i)
+            {
+                j = json({{"k", std::move(j)}, {"n", i}});
+
+                const std::string indent(2 * i, ' ');
+                const std::string outer_indent(2 * (i - 1), ' ');
+                expected = "{\n" + indent + "\"k\": " + expected + ",\n"
+                           + indent + "\"n\": " + std::to_string(i) + "\n" + outer_indent + "}";
+            }
+
+            CHECK(j.dump(2) == expected);
+            CHECK(json::parse(j.dump(2)) == j);
+            CHECK(json::parse(j.dump()) == j);
+        }
+    }
+}
+
+TEST_CASE("serializer buffers are flushed mid-string and mid-binary")
+{
+    SECTION("a long run of escaped characters")
+    {
+        // each character is escaped on its own, so the escape buffer fills up
+        const json newlines = std::string(600, '\n');
+        std::string expected = "\"";
+        for (int i = 0; i < 600; ++i)
+        {
+            expected += "\\n";
+        }
+        expected += '"';
+        CHECK(newlines.dump() == expected);
+
+        // every character is \u-escaped under ensure_ascii
+        std::string umlauts;
+        std::string escaped_umlauts = "\"";
+        for (int i = 0; i < 300; ++i)
+        {
+            umlauts += "\xC3\xA4";
+            escaped_umlauts += "\\u00e4";
+        }
+        escaped_umlauts += '"';
+        CHECK(json(umlauts).dump(-1, ' ', true) == escaped_umlauts);
+    }
+
+    SECTION("a large binary value")
+    {
+        std::vector<std::uint8_t> bytes(3000);
+        std::string expected_bytes;
+        std::string expected_pretty_bytes;
+        for (std::size_t i = 0; i < bytes.size(); ++i)
+        {
+            bytes[i] = static_cast<std::uint8_t>(i % 256);
+            expected_bytes += (i == 0 ? "" : ",") + std::to_string(i % 256);
+            expected_pretty_bytes += (i == 0 ? "" : ", ") + std::to_string(i % 256);
+        }
+        const json j = json::binary(bytes);
+        CHECK(j.dump() == "{\"bytes\":[" + expected_bytes + "],\"subtype\":null}");
+        CHECK(j.dump(2) == "{\n  \"bytes\": [" + expected_pretty_bytes + "],\n  \"subtype\": null\n}");
+    }
+}

tests/src/unit-std-format.cpp

@@ -102,6 +102,29 @@ TEST_CASE("std::formatter<nlohmann::json>")
         CHECK_THROWS_AS(std::vformat("{:{}}", std::make_format_args(j, dynamic_width)), std::format_error); // dynamic width
     }
 
+    SECTION("a format spec may run to the end of the parse context")
+    {
+        // std::format always hands parse() a range that still holds the closing
+        // '}', but a parse context may also end right after the spec
+        const auto parse = [](const char* spec)
+        {
+            std::format_parse_context ctx(spec);
+            std::formatter<json> f;
+            CHECK(f.parse(ctx) == ctx.end());
+            return f;
+        };
+
+        CHECK(parse("").indent == -1);
+        CHECK(parse(">").indent == -1);
+        CHECK(parse("#").indent == 4);
+        CHECK(parse("3").indent == 3);
+        CHECK(parse("#12").indent == 12);
+
+        const auto f = parse(".>");
+        CHECK(f.indent == -1);
+        CHECK(f.indent_char == '.');
+    }
+
     SECTION("std::format_to writes through an arbitrary output iterator")
     {
         const json j = {{"foo", 1}, {"bar", {1, 2, 3}}};

tests/src/unit-ubjson.cpp

@@ -1640,6 +1640,29 @@ TEST_CASE("UBJSON")
                 });
                 CHECK_THROWS_AS(_ = json::sax_parse(v_ubjson, &scp, json::input_format_t::ubjson), json::out_of_range&);
             }
+
+            SECTION("array with a known size, read with a callback")
+            {
+                // a sized array announces its length to start_array()
+                std::vector<uint8_t> const v_ubjson = {'[', '#', 'i', 2, 'i', 1, 'i', 2};
+                json j;
+                nlohmann::detail::json_sax_dom_callback_parser<json, decltype(nlohmann::detail::input_adapter(v_ubjson))> scp(j, [](int /*unused*/, json::parse_event_t /*unused*/, const json& /*unused*/) noexcept
+                {
+                    return true;
+                });
+                CHECK(json::sax_parse(v_ubjson, &scp, json::input_format_t::ubjson));
+                CHECK(j == json({1, 2}));
+
+                // the readers reject a size this large before they announce
+                // it, so it can only reach start_array() directly (the largest
+                // value stands for an unknown size and is never checked)
+                json k;
+                nlohmann::detail::json_sax_dom_callback_parser<json, decltype(nlohmann::detail::input_adapter(v_ubjson))> scp2(k, [](int /*unused*/, json::parse_event_t /*unused*/, const json& /*unused*/) noexcept
+                {
+                    return true;
+                });
+                CHECK_THROWS_AS(scp2.start_array((std::numeric_limits<std::size_t>::max)() - 1), json::out_of_range&);
+            }
         }
     }
 
@@ -2255,6 +2278,46 @@ TEST_CASE("UBJSON nesting does not consume the call stack")
     }
 }
 
+TEST_CASE("UBJSON input that cannot be read is discarded by every overload")
+{
+    std::vector<std::uint8_t> input = json::to_ubjson(json({{"a", {1, 2}}}));
+    input.pop_back();
+
+    json _;
+    CHECK_THROWS_AS(_ = json::from_ubjson(input.begin(), input.end()), json::parse_error&);
+    CHECK(json::from_ubjson(input, true, false).is_discarded());
+    CHECK(json::from_ubjson(input.begin(), input.end(), true, false).is_discarded());
+    CHECK(json::from_ubjson(input.data(), input.size(), true, false).is_discarded());
+    CHECK(json::from_ubjson({input.data(), input.size()}, true, false).is_discarded());
+}
+
+TEST_CASE("UBJSON SAX parsing stops at every event")
+{
+    // Containers are opened and closed by the loop that reads them; a SAX
+    // handler that rejects any event - including the end of a nested
+    // container - must stop the parse right there.
+    const auto count_events = [](const std::vector<std::uint8_t>& input)
+    {
+        int events = 0;
+        while (true)
+        {
+            SaxCountdown scp(events);
+            if (json::sax_parse(input, &scp, json::input_format_t::ubjson))
+            {
+                return events;
+            }
+            ++events;
+            REQUIRE(events < 1000);
+        }
+    };
+
+    // 20 events: every container kind closes inside another one
+    const json j = json::parse(R"({"a": [1, {"b": []}], "c": {"d": [[2]]}})");
+    CHECK(count_events(json::to_ubjson(j)) == 20);
+    CHECK(count_events(json::to_ubjson(j, true)) == 20);
+    CHECK(count_events(json::to_ubjson(j, true, true)) == 20);
+}
+
 TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
 {
     // An element of type 'Z', 'T' or 'F' is encoded by its marker alone, so an