Merge branch 'develop' into claude/binary-reader-narrow-numbers

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

tests/src/unit-cbor.cpp

@@ -1830,10 +1830,51 @@ TEST_CASE("CBOR")
         SECTION("invalid string in map")
         {
             json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
             CHECK(json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01}), true, false).is_discarded());
         }
 
+        SECTION("non-string key (see #2766 and #3381)")
+        {
+            // only text strings map to JSON object keys; any other key is
+            // rejected with a message naming its type
+            const std::vector<std::pair<std::vector<std::uint8_t>, std::string>> cases =
+            {
+                {{0xA1, 0x01, 0x01}, "an unsigned integer; last byte: 0x01"},
+                {{0xA1, 0x20, 0x01}, "a negative integer; last byte: 0x20"},
+                {{0xA1, 0x41, 0x61, 0x01}, "a byte string; last byte: 0x41"},
+                {{0xA1, 0x80, 0x01}, "an array; last byte: 0x80"},
+                {{0xA1, 0xA0, 0x01}, "a map; last byte: 0xA0"},
+                {{0xA1, 0xC0, 0x61, 0x61, 0x01}, "a tag; last byte: 0xC0"},
+                {{0xA1, 0xF4, 0x01}, "a boolean; last byte: 0xF4"},
+                {{0xA1, 0xF5, 0x01}, "a boolean; last byte: 0xF5"},
+                {{0xA1, 0xF6, 0x01}, "null; last byte: 0xF6"},
+                {{0xA1, 0xF7, 0x01}, "undefined; last byte: 0xF7"},
+                {{0xA1, 0xF9, 0x3C, 0x00, 0x01}, "a floating-point number; last byte: 0xF9"},
+                {{0xA1, 0xFA, 0x3F, 0x80, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFA"},
+                {{0xA1, 0xFB, 0x3F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFB"},
+                {{0xA1, 0xE0, 0x01}, "a simple value; last byte: 0xE0"},
+                {{0xA1, 0xF8, 0x20, 0x01}, "a simple value; last byte: 0xF8"},
+                // indefinite-length map
+                {{0xBF, 0x01, 0x01, 0xFF}, "an unsigned integer; last byte: 0x01"},
+            };
+
+            for (const auto& c : cases)
+            {
+                CAPTURE(c.first)
+                const std::string expected = "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found " + c.second;
+                json _;
+                CHECK_THROWS_WITH_AS(_ = json::from_cbor(c.first), expected.c_str(), json::parse_error&);
+                CHECK(json::from_cbor(c.first, true, false).is_discarded());
+            }
+
+            // a key of major type 3 with a reserved length is still reported as
+            // a malformed string, and a missing key as the end of input
+            json _;
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x7C, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C", json::parse_error&);
+        }
+
         SECTION("invalid UTF-8 in string (see #5529)")
         {
             // a two-character text string (major type 3) whose bytes are not
@@ -2284,7 +2325,7 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
     SECTION("a break marker outside an indefinite-length string is not a string")
     {
         // 0xFF only closes a string that was opened; on its own it is not one
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
     }
 }
 

tests/src/unit-class_lexer.cpp

@@ -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;
 

tests/src/unit-locale-cpp.cpp

@@ -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*/) noexcept
+            {
+                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*/) noexcept
+            {
+                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);
+            }
+        }
+    }
+
+    CHECK(std::setlocale(LC_NUMERIC, "C") != nullptr);
+}
+
+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");
+    }
+
+    CHECK(std::setlocale(LC_NUMERIC, "C") != nullptr);
+}

tests/src/unit-msgpack.cpp

@@ -1551,10 +1551,69 @@ TEST_CASE("MessagePack")
         SECTION("invalid string in map")
         {
             json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack string: expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0xFF", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found an integer; last byte: 0xFF", json::parse_error&);
             CHECK(json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01}), true, false).is_discarded());
         }
 
+        SECTION("non-string key (see #3381)")
+        {
+            // only strings map to JSON object keys; any other key is rejected
+            // with a message naming its type
+            const std::vector<std::pair<std::vector<std::uint8_t>, std::string>> cases =
+            {
+                {{0x81, 0xC0, 0x01}, "nil; last byte: 0xC0"},
+                {{0x81, 0xC2, 0x01}, "a boolean; last byte: 0xC2"},
+                {{0x81, 0xC3, 0x01}, "a boolean; last byte: 0xC3"},
+                {{0x81, 0xCA, 0x3F, 0x80, 0x00, 0x00, 0x01}, "a float; last byte: 0xCA"},
+                {{0x81, 0xCB, 0x3F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "a float; last byte: 0xCB"},
+                {{0x81, 0xC4, 0x00, 0x01}, "a bin; last byte: 0xC4"},
+                {{0x81, 0xC5, 0x00, 0x00, 0x01}, "a bin; last byte: 0xC5"},
+                {{0x81, 0xC6, 0x00, 0x00, 0x00, 0x00, 0x01}, "a bin; last byte: 0xC6"},
+                {{0x81, 0xC7, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC7"},
+                {{0x81, 0xC8, 0x00, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC8"},
+                {{0x81, 0xC9, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC9"},
+                {{0x81, 0xD4, 0x01, 0x00, 0x01}, "an ext; last byte: 0xD4"},
+                {{0x81, 0xD5, 0x01, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD5"},
+                {{0x81, 0xD6, 0x01, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD6"},
+                {{0x81, 0xD7, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD7"},
+                {{0x81, 0xD8, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD8"},
+                {{0x81, 0xCC, 0x01, 0x01}, "an integer; last byte: 0xCC"},
+                {{0x81, 0xCD, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCD"},
+                {{0x81, 0xCE, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCE"},
+                {{0x81, 0xCF, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCF"},
+                {{0x81, 0xD0, 0x01, 0x01}, "an integer; last byte: 0xD0"},
+                {{0x81, 0xD1, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD1"},
+                {{0x81, 0xD2, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD2"},
+                {{0x81, 0xD3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD3"},
+                {{0x81, 0x00, 0x01}, "an integer; last byte: 0x00"},
+                {{0x81, 0x7F, 0x01}, "an integer; last byte: 0x7F"},
+                {{0x81, 0xE0, 0x01}, "an integer; last byte: 0xE0"},
+                {{0x81, 0x80, 0x01}, "a map; last byte: 0x80"},
+                {{0x81, 0x8F, 0x01}, "a map; last byte: 0x8F"},
+                {{0x81, 0xDE, 0x00, 0x00, 0x01}, "a map; last byte: 0xDE"},
+                {{0x81, 0xDF, 0x00, 0x00, 0x00, 0x00, 0x01}, "a map; last byte: 0xDF"},
+                {{0x81, 0x90, 0x01}, "an array; last byte: 0x90"},
+                {{0x81, 0x9F, 0x01}, "an array; last byte: 0x9F"},
+                {{0x81, 0xDC, 0x00, 0x00, 0x01}, "an array; last byte: 0xDC"},
+                {{0x81, 0xDD, 0x00, 0x00, 0x00, 0x00, 0x01}, "an array; last byte: 0xDD"},
+            };
+
+            for (const auto& c : cases)
+            {
+                CAPTURE(c.first)
+                const std::string expected = "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found " + c.second;
+                json _;
+                CHECK_THROWS_WITH_AS(_ = json::from_msgpack(c.first), expected.c_str(), json::parse_error&);
+                CHECK(json::from_msgpack(c.first, true, false).is_discarded());
+            }
+
+            json _;
+            // the unused byte 0xC1 is still reported as a malformed string
+            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xC1, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack string: expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0xC1", json::parse_error&);
+            // a missing key is still reported as the end of input
+            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing MessagePack string: unexpected end of input", json::parse_error&);
+        }
+
         SECTION("invalid UTF-8 in string (see #5529)")
         {
             // a fixstr of length 2 (0xA0 | 2) whose bytes are not valid UTF-8

tests/src/unit-regression1.cpp

@@ -1018,7 +1018,7 @@ TEST_CASE("regression tests 1")
         };
 
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x98", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found an array; last byte: 0x98", json::parse_error&);
 
         // related test case: nonempty UTF-8 string (indefinite length)
         std::vector<uint8_t> const vec1 {0x7f, 0x61, 0x61};
@@ -1065,7 +1065,7 @@ TEST_CASE("regression tests 1")
         };
 
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec1), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xB4", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec1), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR object key: only string keys are supported, but found a map; last byte: 0xB4", json::parse_error&);
 
         // related test case: double-precision
         std::vector<uint8_t> const vec2
@@ -1077,7 +1077,7 @@ TEST_CASE("regression tests 1")
             0x96, 0x96, 0xb4, 0xb4, 0xfa, 0x94, 0x94, 0x61,
             0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0xfb
         };
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec2), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xB4", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec2), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR object key: only string keys are supported, but found a map; last byte: 0xB4", json::parse_error&);
     }
 
     SECTION("issue #452 - Heap-buffer-overflow (OSS-Fuzz issue 585)")