Handle numbers that do not fit narrow number types in the binary readers

With custom number types narrower than the values in a binary document,
for example basic_json<..., std::int32_t, std::uint32_t, float>, every
binary reader (CBOR, MessagePack, UBJSON, BJData, BSON, BON8) passed the
decoded number to the SAX interface with an implicit conversion: the
integer 5000000000 silently became 705032704, and a finite double such as
1e300 became infinity. The lexer handles the same values in JSON text: an
integer that fits neither integer type is stored as number_float_t, and a
finite number that overflows number_float_t is rejected with
out_of_range.406.

Pass every number read from binary input through three helpers that
apply the lexer's rules:
- emit_signed(): number_integer_t, else number_unsigned_t for a
  non-negative value, else number_float_t
- emit_unsigned(): number_unsigned_t, else number_float_t
- emit_float(): out_of_range.406 if a finite value overflows
  number_float_t; infinity and NaN are passed on

For consistency, a CBOR negative integer below the range of
number_integer_t is now stored as number_float_t, like a too small
integer in JSON text, instead of being rejected with parse_error.112.
With the default number types, this is the only change in behavior.

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

tests/src/unit-binary_formats.cpp

@@ -11,7 +11,12 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
+#include <cmath>
 #include <fstream>
+#include <limits>
+#include <map>
+#include <string>
+#include <vector>
 #include "make_test_data_available.hpp"
 
 TEST_CASE("Binary Formats" * doctest::skip())
@@ -224,3 +229,114 @@ TEST_CASE("Binary Formats" * doctest::skip())
         CHECK((100.0 * double(ubjson_3_size) / double(json_size)) == Approx(89.450));
     }
 }
+
+TEST_CASE("Binary formats with narrow number types")
+{
+    // Numbers that do not fit the number types are handled like the lexer
+    // handles them in JSON text: an integer that fits neither integer type is
+    // stored as a floating-point number, and a finite floating-point number
+    // that overflows number_float_t is rejected with out_of_range.406.
+    using narrow_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int32_t, std::uint32_t, float>;
+    using bytes = std::vector<std::uint8_t>;
+
+    struct binary_format
+    {
+        const char* name;
+        bytes (*encode)(const json&);
+        narrow_json (*decode)(const bytes&, bool);
+    };
+
+    const std::vector<binary_format> formats =
+    {
+        {
+            "CBOR", [](const json & j) { return json::to_cbor(j); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                return narrow_json::from_cbor(v, true, allow_exceptions);
+            }
+        },
+        {
+            "MessagePack", [](const json & j) { return json::to_msgpack(j); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                return narrow_json::from_msgpack(v, true, allow_exceptions);
+            }
+        },
+        {
+            "UBJSON", [](const json & j) { return json::to_ubjson(j); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                return narrow_json::from_ubjson(v, true, allow_exceptions);
+            }
+        },
+        {
+            "BJData", [](const json & j) { return json::to_bjdata(j); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                return narrow_json::from_bjdata(v, true, allow_exceptions);
+            }
+        },
+        {
+            // BSON can only store numbers as object members
+            "BSON", [](const json & j) { return json::to_bson(json{{"a", j}}); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                const auto result = narrow_json::from_bson(v, true, allow_exceptions);
+                return result.is_discarded() ? result : result.at("a");
+            }
+        },
+        {
+            "BON8", [](const json & j) { return json::to_bon8(j); },
+            [](const bytes & v, bool allow_exceptions)
+            {
+                return narrow_json::from_bon8(v, true, allow_exceptions);
+            }
+        },
+    };
+
+    for (const auto& format : formats)
+    {
+        const std::string name = format.name;
+        INFO("format := ", name);
+        const auto roundtrip = [&format](const json & j)
+        {
+            return format.decode(format.encode(j), true);
+        };
+
+        // integers that fit keep their type
+        CHECK(roundtrip(json(-5)).is_number_integer());
+        CHECK(roundtrip(json(-5)).get<std::int32_t>() == -5);
+        CHECK(roundtrip(json(3000000000u)).is_number_unsigned());
+        CHECK(roundtrip(json(3000000000u)).get<std::uint32_t>() == 3000000000u);
+
+        // integers that fit neither integer type are stored as float
+        CHECK(roundtrip(json(5000000000u)).is_number_float());
+        CHECK(roundtrip(json(5000000000u)).get<float>() == 5000000000.0f);
+        if (name != "BON8") // BON8 cannot encode integers above INT64_MAX
+        {
+            CHECK(roundtrip(json(10000000000000000000u)).is_number_float());
+            CHECK(roundtrip(json(10000000000000000000u)).get<float>() == 10000000000000000000.0f);
+        }
+        CHECK(roundtrip(json(-3000000000)).is_number_float());
+        CHECK(roundtrip(json(-3000000000)).get<float>() == -3000000000.0f);
+        CHECK(roundtrip(json(-5000000000)).is_number_float());
+        CHECK(roundtrip(json(-5000000000)).get<float>() == -5000000000.0f);
+
+        // floating-point numbers that fit
+        CHECK(roundtrip(json(1.5)).get<float>() == 1.5f);
+        const auto just_above_max = std::nextafter(static_cast<double>((std::numeric_limits<float>::max)()),
+                                    std::numeric_limits<double>::infinity());
+        CHECK(roundtrip(json(just_above_max)).get<float>() == (std::numeric_limits<float>::max)());
+
+        // infinity and NaN are passed on
+        CHECK(std::isinf(roundtrip(json(std::numeric_limits<double>::infinity())).get<float>()));
+        CHECK(std::isnan(roundtrip(json(std::numeric_limits<double>::quiet_NaN())).get<float>()));
+
+        // finite floating-point numbers that overflow number_float_t are rejected
+        const std::string message = "[json.exception.out_of_range.406] syntax error while parsing " + name
+                                    + " value: number overflow";
+        CHECK_THROWS_WITH_AS(roundtrip(json(1e300)), message.c_str(), narrow_json::out_of_range&);
+        CHECK_THROWS_WITH_AS(roundtrip(json(-1e300)), message.c_str(), narrow_json::out_of_range&);
+        CHECK(format.decode(format.encode(json(1e300)), false).is_discarded());
+    }
+}

tests/src/unit-cbor.cpp

@@ -3146,7 +3146,8 @@ TEST_CASE("Tagged values")
         // CBOR encodes negative integers as: result = -1 - n
         // For type 0x3B, n is an 8-byte uint64_t. Valid range for n with
         // the default int64_t is [0, INT64_MAX], producing results in [INT64_MIN, -1].
-        // When n > INT64_MAX, the result exceeds int64_t range and is rejected.
+        // When n > INT64_MAX, the result exceeds int64_t range and is stored
+        // as a floating-point number, as the lexer does for JSON text.
 
         SECTION("n = 0 is valid (result = -1)")
         {
@@ -3167,33 +3168,34 @@ TEST_CASE("Tagged values")
             CHECK(result.get<int64_t>() == (std::numeric_limits<int64_t>::min)());
         }
 
-        SECTION("n = INT64_MAX + 1 is rejected (overflow)")
+        SECTION("n = INT64_MAX + 1 is stored as float")
         {
             // n = INT64_MAX + 1 (0x8000000000000000)
-            // result = -1 - n = -9223372036854775809, which exceeds int64_t range
+            // result = -1 - n = -9223372036854775809, which exceeds int64_t range;
+            // the nearest double is -9223372036854775808.0
             const std::vector<uint8_t> input = {0x3B, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(input),
-                                 "[json.exception.parse_error.112] parse error at byte 9: syntax error while parsing CBOR value: negative integer overflow",
-                                 json::parse_error);
+            const auto result = json::from_cbor(input);
+            CHECK(result.is_number_float());
+            CHECK(result.get<double>() == -9223372036854775808.0);
+            CHECK(result == json::parse("-9223372036854775809"));
         }
 
-        SECTION("n = UINT64_MAX is rejected (overflow)")
+        SECTION("n = UINT64_MAX is stored as float")
         {
             // n = UINT64_MAX (0xFFFFFFFFFFFFFFFF)
             // result = -1 - n = -18446744073709551616, which exceeds int64_t range
             const std::vector<uint8_t> input = {0x3B, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(input),
-                                 "[json.exception.parse_error.112] parse error at byte 9: syntax error while parsing CBOR value: negative integer overflow",
-                                 json::parse_error);
+            const auto result = json::from_cbor(input);
+            CHECK(result.is_number_float());
+            CHECK(result.get<double>() == -18446744073709551616.0);
+            CHECK(result == json::parse("-18446744073709551616"));
         }
 
-        SECTION("overflow with allow_exceptions=false returns discarded")
+        SECTION("overflow with allow_exceptions=false is not an error")
         {
             const std::vector<uint8_t> input = {0x3B, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
             const auto result = json::from_cbor(input, true, false);
-            CHECK(result.is_discarded());
+            CHECK(result.is_number_float());
         }
     }