Look up the locale decimal point at conversion time, not lexer construction (#5597)

* Look up the locale decimal point at conversion time, not lexer construction The lexer read localeconv()->decimal_point once in its constructor and wrote that character into token_buffer in place of '.'. The strtod fallback then used the locale current at conversion time, so an LC_NUMERIC change in between (parser callback, SAX handler, another thread) truncated the value in release builds and fired the endptr assertion in debug builds. token_buffer now always holds '.'. Only the strtof/strtod/strtold fallback depends on the locale: it looks up the decimal point right before the call, restores '.' afterwards, and repeats the conversion if the locale changed in between. As a side effect, std::from_chars and Clinger's fast path now also apply under locales whose decimal point is not '.'. Fixes #5198 Signed-off-by: Niels Lohmann <mail@nlohmann.me> * Stop the strtod retry loop when the decimal point is unchanged convert_float_locale_aware() repeated the conversion until strtod consumed the whole token, assuming an early stop can only mean a locale change. Under a locale whose decimal point is not a single character (e.g. the two-byte U+066B of ar_EG.UTF-8, ar_SA.UTF-8, or fa_IR.UTF-8, all available on macOS), the in-place substitution can never succeed, so parsing any float that reaches the strtod fallback (for example 3.14159265358979323846 at C++11) hung forever. Before this branch, the same input was truncated. Retry only if the decimal point changed since the previous attempt; otherwise keep the value strtod parsed so far, as before. Add a test that parses such numbers under a multi-byte decimal point locale; it hangs without this change. Signed-off-by: Niels Lohmann <mail@nlohmann.me> * Fix -Weffc++ errors in the #5198 locale test GCC's -Weffc++ (an error in ci_test_gcc and ci_test_standards_gcc) rejected LocaleSwitchingSax: it has a pointer data member but does not declare its copy operations, and its vectors are not initialized in the member initializer list. Store the locale name as a std::string and give the vectors brace initializers, like SaxEventLogger in unit-deserialization.cpp. Signed-off-by: Niels Lohmann <mail@nlohmann.me> --------- Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-10-01 20:20:32 +00:00 · 2026-09-28 17:56:11 +02:00
parent 9e1a09eec0
commit fc03b9912e
5 changed files with 379 additions and 105 deletions
@@ -666,7 +666,7 @@ TEST_CASE("parse_float_fast declines what it cannot convert exactly")
    // always safe: the caller then falls back to a slower, exact conversion.
    const auto fast = [](const std::string & s, double & out)
    {
-        return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), '.', out);
+        return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), out);
    };
    double out = 0;

@@ -12,7 +12,12 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;

+#include <array>
 #include <clocale>
+#include <map>
+#include <string>
+#include <utility>
+#include <vector>

 struct ParserImpl final: public nlohmann::json_sax<json>
 {
@@ -175,3 +180,208 @@ TEST_CASE("locale-dependent test (LC_NUMERIC=de_DE)")
        MESSAGE("locale de_DE is not usable");
    }
 }
+
+namespace
+{
+// records the numbers of a flat array and switches LC_NUMERIC to the given
+// locale once the array opens - after the lexer was constructed, but before
+// any number in the array is lexed
+struct LocaleSwitchingSax final: public nlohmann::json_sax<json>
+{
+    explicit LocaleSwitchingSax(const char* switch_to)
+        : locale_after_open(switch_to)
+    {}
+
+    bool null() override
+    {
+        return true;
+    }
+    bool boolean(bool /*val*/) override
+    {
+        return true;
+    }
+    bool number_integer(json::number_integer_t /*val*/) override
+    {
+        return true;
+    }
+    bool number_unsigned(json::number_unsigned_t /*val*/) override
+    {
+        return true;
+    }
+    bool number_float(json::number_float_t val, const json::string_t& s) override
+    {
+        values.push_back(val);
+        strings.push_back(s);
+        return true;
+    }
+    bool string(json::string_t& /*val*/) override
+    {
+        return true;
+    }
+    bool binary(json::binary_t& /*val*/) override
+    {
+        return true;
+    }
+    bool start_object(std::size_t /*val*/) override
+    {
+        return true;
+    }
+    bool key(json::string_t& /*val*/) override
+    {
+        return true;
+    }
+    bool end_object() override
+    {
+        return true;
+    }
+    bool start_array(std::size_t /*val*/) override
+    {
+        switched = std::setlocale(LC_NUMERIC, locale_after_open.c_str()) != nullptr;
+        return true;
+    }
+    bool end_array() override
+    {
+        return true;
+    }
+    bool parse_error(std::size_t /*val*/, const std::string& /*val*/, const nlohmann::detail::exception& /*val*/) override
+    {
+        return false;
+    }
+
+    std::string locale_after_open;
+    bool switched = false;
+    std::vector<json::number_float_t> values {}; // NOLINT(readability-redundant-member-init)
+    std::vector<json::string_t> strings {}; // NOLINT(readability-redundant-member-init)
+};
+} // namespace
+
+TEST_CASE("locale changes between lexer construction and number conversion (#5198)")
+{
+    // The numbers are chosen so that the conversion also takes the strtod
+    // fallback, which honors the locale that is current at conversion time:
+    // too many significant digits for Clinger's fast path, an underflow that
+    // std::from_chars rejects, and a plain value.
+    const std::vector<std::string> numbers = {"3.14159265358979323846", "1.5e-400", "12.34", "-0.000123456789012345678"};
+    std::string text = "[";
+    for (const auto& n : numbers)
+    {
+        text += (text.size() == 1 ? "" : ",") + n;
+    }
+    text += "]";
+
+    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
+
+    // reference values, parsed without a locale switch
+    REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
+    const json expected = json::parse(text);
+    const long_double_json expected_ld = long_double_json::parse(text);
+
+    const std::array<std::pair<const char*, const char*>, 2> transitions =
+    {
+        {
+            {"C", "de_DE"},
+            {"de_DE", "C"}
+        }
+    };
+
+    for (const auto& transition : transitions)
+    {
+        CAPTURE(transition.first);
+        CAPTURE(transition.second);
+
+        if (std::setlocale(LC_NUMERIC, transition.first) == nullptr)
+        {
+            MESSAGE("locale is not usable");
+            continue;
+        }
+
+        // SAX parsing
+        {
+            LocaleSwitchingSax sax(transition.second);
+            CHECK(json::sax_parse(text, &sax));
+            if (sax.switched)
+            {
+                CHECK(sax.values == expected.get<std::vector<json::number_float_t>>());
+                CHECK(sax.strings == numbers);
+            }
+        }
+
+        // DOM parsing with a callback
+        {
+            bool switched = false;
+            const auto cb = [&](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
+            {
+                if (event == json::parse_event_t::array_start)
+                {
+                    switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
+                }
+                return true;
+            };
+            const json j = json::parse(text, cb);
+            if (switched)
+            {
+                CHECK(j == expected);
+            }
+        }
+
+        // a long double goes through std::strtold unless std::from_chars supports it
+        {
+            bool switched = false;
+            const auto cb = [&](int /*depth*/, long_double_json::parse_event_t event, long_double_json& /*parsed*/)
+            {
+                if (event == long_double_json::parse_event_t::array_start)
+                {
+                    switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
+                }
+                return true;
+            };
+            const long_double_json j = long_double_json::parse(text, cb);
+            if (switched)
+            {
+                CHECK(j == expected_ld);
+            }
+        }
+    }
+
+    std::setlocale(LC_NUMERIC, "C");
+}
+
+TEST_CASE("locale with a multi-byte decimal point")
+{
+    // Some locales use a decimal point that is not a single character, e.g.
+    // U+066B ARABIC DECIMAL SEPARATOR (two bytes in UTF-8). It cannot be
+    // substituted in place for '.', so the strtod fallback stops early. The
+    // conversion must still terminate rather than retry forever.
+    const std::array<const char*, 6> names = {{"ar_EG.UTF-8", "ar_SA.UTF-8", "fa_IR.UTF-8", "ps_AF.UTF-8", "ar_EG", "fa_IR"}};
+    bool tested = false;
+    for (const char* name : names)
+    {
+        if (std::setlocale(LC_NUMERIC, name) == nullptr)
+        {
+            continue;
+        }
+        const std::string decimal_point = std::localeconv()->decimal_point;
+        if (decimal_point.size() < 2)
+        {
+            continue;
+        }
+        CAPTURE(name);
+        tested = true;
+
+        // too many significant digits for Clinger's fast path, and an underflow
+        // that std::from_chars rejects: both reach the strtod fallback
+        json j;
+        CHECK_NOTHROW(j = json::parse("[3.14159265358979323846, 1.5e-400, -0.000123456789012345678]"));
+        CHECK(j.is_array());
+        CHECK(json::accept("3.14159265358979323846"));
+
+        // a value the locale-independent paths convert is not affected
+        CHECK(json::parse("12.5") == 12.5);
+    }
+    if (!tested)
+    {
+        MESSAGE("no locale with a multi-byte decimal point is usable");
+    }
+
+    std::setlocale(LC_NUMERIC, "C");
+}