Stop binary writers overflowing the stack on deep values

to_cbor, to_msgpack, and to_ubjson recurse once per nesting level.
The parser is iterative, so a value the library accepts can crash on
the way back out.

Keep the existing recursive path for the first 128 levels and finish
anything deeper on a heap stack. Output is unchanged. BSON is left
alone because its extra size walk is a separate change.

Rebased onto the value-type output sink. The heap frames now initialize
every member, which is what -Weffc++ was rejecting.

See #5392.

Signed-off-by: ayush-singh-0601 <singhayush062006@gmail.com>

tests/src/unit-large_json.cpp

@@ -12,6 +12,9 @@
 using nlohmann::json;
 
 #include <algorithm>
+#include <string>
+#include <utility>
+#include <vector>
 
 TEST_CASE("tests on very large JSONs")
 {
@@ -27,3 +30,124 @@ TEST_CASE("tests on very large JSONs")
     }
 }
 
+namespace
+{
+json nested_array(const std::size_t depth, json leaf)
+{
+    json j = std::move(leaf);
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        json a = json::array();
+        a.push_back(std::move(j));
+        j = std::move(a);
+    }
+    return j;
+}
+
+json nested_object(const std::size_t depth, json leaf)
+{
+    json j = std::move(leaf);
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        json o = json::object();
+        o["k"] = std::move(j);
+        j = std::move(o);
+    }
+    return j;
+}
+} // namespace
+
+TEST_CASE("issue #5392 - binary writers on deeply nested values")
+{
+    // 200 is past the point where the writers stop recursing, and still
+    // shallow enough that from_* and operator== (which still recurse) are fine.
+    const json deep_array = nested_array(200, json(0));
+    const json deep_object = nested_object(200, json("x"));
+    const json empty_array = nested_array(200, json::array());
+    const json empty_object = nested_object(200, json::object());
+    const json mixed = nested_object(80, nested_array(80, json(true)));
+
+    SECTION("roundtrip past the recursion bound")
+    {
+        CHECK(json::from_cbor(json::to_cbor(deep_array)) == deep_array);
+        CHECK(json::from_msgpack(json::to_msgpack(deep_array)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, false)) == deep_array);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_array, true, true)) == deep_array);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_array)) == deep_array);
+
+        CHECK(json::from_cbor(json::to_cbor(deep_object)) == deep_object);
+        CHECK(json::from_msgpack(json::to_msgpack(deep_object)) == deep_object);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_object)) == deep_object);
+        CHECK(json::from_ubjson(json::to_ubjson(deep_object, true, true)) == deep_object);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_object)) == deep_object);
+
+        CHECK(json::from_cbor(json::to_cbor(empty_array)) == empty_array);
+        CHECK(json::from_msgpack(json::to_msgpack(empty_array)) == empty_array);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_array)) == empty_array);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_array, true, true)) == empty_array);
+
+        CHECK(json::from_cbor(json::to_cbor(empty_object)) == empty_object);
+        CHECK(json::from_msgpack(json::to_msgpack(empty_object)) == empty_object);
+        CHECK(json::from_ubjson(json::to_ubjson(empty_object)) == empty_object);
+
+        CHECK(json::from_cbor(json::to_cbor(mixed)) == mixed);
+        CHECK(json::from_msgpack(json::to_msgpack(mixed)) == mixed);
+        CHECK(json::from_ubjson(json::to_ubjson(mixed)) == mixed);
+        CHECK(json::from_bjdata(json::to_bjdata(mixed)) == mixed);
+    }
+
+    SECTION("the two ways of writing a value meet at the bound")
+    {
+        for (std::size_t depth = 120; depth <= 140; ++depth)
+        {
+            CAPTURE(depth);
+
+            const json array = nested_array(depth, json(7));
+            CHECK(json::from_cbor(json::to_cbor(array)) == array);
+            CHECK(json::from_msgpack(json::to_msgpack(array)) == array);
+            CHECK(json::from_ubjson(json::to_ubjson(array, true, true)) == array);
+
+            const json object = nested_object(depth, json(7));
+            CHECK(json::from_cbor(json::to_cbor(object)) == object);
+            CHECK(json::from_msgpack(json::to_msgpack(object)) == object);
+            CHECK(json::from_bjdata(json::to_bjdata(object)) == object);
+        }
+    }
+
+    SECTION("a BJData ndarray below the bound is still an ndarray")
+    {
+        const json ndarray = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
+        const json invalid = json({{"_ArrayType_", "nope"}, {"_ArraySize_", {1}}, {"_ArrayData_", {1}}});
+
+        const json deep_ndarray = nested_array(140, ndarray);
+        const json deep_invalid = nested_array(140, invalid);
+
+        CHECK(json::from_bjdata(json::to_bjdata(deep_ndarray)) == deep_ndarray);
+        CHECK(json::from_bjdata(json::to_bjdata(deep_invalid)) == deep_invalid);
+        CHECK(json::from_bjdata(json::to_bjdata(ndarray)) == ndarray);
+    }
+
+    SECTION("does not overflow the C++ stack")
+    {
+        const std::size_t depth = 100000;
+        const json j = json::parse(std::string(depth, '[') + "0" + std::string(depth, ']'));
+
+        std::vector<std::uint8_t> packed;
+        CHECK_NOTHROW(packed = json::to_cbor(j));
+        CHECK(packed.size() > depth);
+
+        CHECK_NOTHROW(packed = json::to_msgpack(j));
+        CHECK(packed.size() > depth);
+
+        CHECK_NOTHROW(packed = json::to_ubjson(j));
+        CHECK(packed.size() > depth);
+
+        CHECK_NOTHROW(packed = json::to_ubjson(j, true, false));
+        CHECK(packed.size() > depth);
+
+        CHECK_NOTHROW(packed = json::to_bjdata(j));
+        CHECK(packed.size() > depth);
+    }
+}
+