to_bson() silently emits corrupt documents when a length exceeds INT32_MAX (#5314)

tests/src/unit-bson.cpp

@@ -11,12 +11,35 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <cstdint>
 #include <fstream>
 #include <limits>
 #include <sstream>
+#include <vector>
 #include "make_test_data_available.hpp"
 #include "test_utils.hpp"
 
+namespace
+{
+// a binary container that reports a size beyond INT32_MAX without allocating
+// that much memory, so the BSON length overflow can be tested cheaply
+class huge_binary_t : public std::vector<std::uint8_t>
+{
+  public:
+    using std::vector<std::uint8_t>::vector;
+
+    size_type size() const noexcept // NOLINT(readability-convert-member-functions-to-static)
+    {
+        // one byte more than the BSON length field can represent
+        return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
+    }
+};
+
+using huge_binary_json = nlohmann::basic_json <
+                         std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
+                         double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
+} // namespace
+
 TEST_CASE("BSON")
 {
     SECTION("individual values not supported")
@@ -80,6 +103,14 @@ TEST_CASE("BSON")
 #endif
     }
 
+    SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
+    {
+        huge_binary_json j;
+        j["b"] = huge_binary_json::binary(huge_binary_t{});
+
+        CHECK_THROWS_WITH_AS(huge_binary_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_binary_json::out_of_range&);
+    }
+
     SECTION("string length must be at least 1")
     {
         // from https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=11175