From 0bc01a066cc1bb87705072eed6b195b08d53525a Mon Sep 17 00:00:00 2001
From: Jonas Greitemann <jgreitemann@gmail.com>
Date: Sat, 6 Jun 2026 16:40:58 +0200
Subject: [PATCH] Add (failing) regression test for `strtod` locale TOCTOU bug

In debug builds, this test fails with `SIGABRT` due to an assertion.
In release builds, truncation of the fractional part will be detected.

Sometimes, this test may also cause memory violation (`SIGSEGV`) due to
it being undefined behavior to set locale and use locale-dependent
functions concurrently. On Windows, this does not happen since the
global locale is protected by a mutex.

This test assumes that a locale called "de_DE.UTF-8" exists on the host.
If it does not, the test bails out but does not fail. The locale name is
hard-coded because it is impossible to query available locales portably.
"de_DE.UTF-8" is an accepted format on Ubuntu, macOS, and Windows.

Signed-off-by: Jonas Greitemann <jgreitemann@gmail.com>
---
 tests/CMakeLists.txt           |  4 ++++
 tests/src/unit-regression2.cpp | 41 ++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
index 4383b582c..47524982c 100644
--- a/tests/CMakeLists.txt
+++ b/tests/CMakeLists.txt
@@ -121,6 +121,10 @@ json_test_set_test_options(test-disabled_exceptions
 # raise timeout of expensive Unicode test
 json_test_set_test_options(test-unicode4 TEST_PROPERTIES TIMEOUT 3000)
 
+# link pthreads to tests that need it
+find_package(Threads REQUIRED)
+json_test_set_test_options(test-regression2 LINK_LIBRARIES Threads::Threads)
+
 #############################################################################
 # add unit tests
 #############################################################################
diff --git a/tests/src/unit-regression2.cpp b/tests/src/unit-regression2.cpp
index 7ae4170d3..83b646475 100644
--- a/tests/src/unit-regression2.cpp
+++ b/tests/src/unit-regression2.cpp
@@ -26,8 +26,11 @@ using ordered_json = nlohmann::ordered_json;
     using namespace nlohmann::literals; // NOLINT(google-build-using-namespace)
 #endif
 
+#include <atomic>
+#include <clocale>
 #include <cstdio>
 #include <list>
+#include <thread>
 #include <type_traits>
 #include <utility>
 
@@ -1239,6 +1242,44 @@ TEST_CASE("regression tests 2")
         CHECK(j == json({2, 4, 6}));
     }
 #endif
+
+    SECTION("issue #5198 - TOCTOU race between lexer construction and locale changes causes float truncation")
+    {
+        std::atomic<bool> stop_requested{};
+        std::thread switcher([&stop_requested]
+        {
+            bool german = true;
+            const std::string initial_locale = std::setlocale(LC_NUMERIC, nullptr);
+
+            while (!stop_requested)
+            {
+                const bool setlocale_res = std::setlocale(LC_NUMERIC, german ? "de_DE.UTF-8" : "C");
+                WARN_MESSAGE(setlocale_res,
+                             "Setting locale failed, probably because de_DE.UTF-8 is not installed. "
+                             "This test was skipped as it would be inconclusive.");
+                if (!setlocale_res)
+                {
+                    stop_requested = true;
+                }
+                german = !german;
+            }
+
+            (void)std::setlocale(LC_NUMERIC, initial_locale.c_str()); // restore original locale
+        });
+
+        for (std::size_t i = 0; i < 10000 && !stop_requested; ++i)
+        {
+            const json j = json::parse("{\"val\": 99.123456789}");
+            const double parsed = j.value("val", 0.0);
+            if (!CHECK(parsed == 99.123456789))
+            {
+                break;
+            }
+        }
+
+        stop_requested = true;
+        switcher.join();
+    }
 }
 
 TEST_CASE_TEMPLATE("issue #4798 - nlohmann::json::to_msgpack() encode float NaN as double", T, double, float) // NOLINT(readability-math-missing-parentheses, bugprone-throwing-static-initialization)