Support BSON uint64 de/serialization (#4590)

* Support BSON uint64 de/serialization

Signed-off-by: Michael Valladolid <mikevalladolid@gmail.com>

* Treat 0x11 as uint64 and not timestamp specific

Signed-off-by: Michael Valladolid <mikevalladolid@gmail.com>

---------

Signed-off-by: Michael Valladolid <mikevalladolid@gmail.com>

docs/mkdocs/docs/features/binary_formats/bson.md

@@ -23,7 +23,7 @@ The library uses the following mapping from JSON values types to BSON types:
 | number_integer  | 2147483648..9223372036854775807           | int64     | 0x12   |
 | number_unsigned | 0..2147483647                             | int32     | 0x10   |
 | number_unsigned | 2147483648..9223372036854775807           | int64     | 0x12   |
-| number_unsigned | 9223372036854775808..18446744073709551615 | --        | --     |
+| number_unsigned | 9223372036854775808..18446744073709551615 | uint64    | 0x11   |
 | number_float    | *any value*                               | double    | 0x01   |
 | string          | *any value*                               | string    | 0x02   |
 | array           | *any value*                               | document  | 0x04   |
@@ -73,7 +73,7 @@ The library maps BSON record types to JSON value types as follows:
 | Symbol                | 0x0E             | *unsupported*   |
 | JavaScript Code       | 0x0F             | *unsupported*   |
 | int32                 | 0x10             | number_integer  |
-| Timestamp             | 0x11             | *unsupported*   |
+| uint64(Timestamp)     | 0x11             | number_unsigned |
 | 128-bit decimal float | 0x13             | *unsupported*   |
 | Max Key               | 0x7F             | *unsupported*   |
 | Min Key               | 0xFF             | *unsupported*   |
@@ -94,3 +94,8 @@ The library maps BSON record types to JSON value types as follows:
     ```json
     --8<-- "examples/from_bson.output"
     ```
+
+!!! note "Handling of BSON type 0x11"
+
+    BSON type 0x11 is used to represent uint64 numbers. This library treats these values purely as uint64 numbers 
+    and does not parse them into date-related formats.

docs/mkdocs/docs/home/exceptions.md

@@ -839,7 +839,7 @@ A parsed number could not be stored as without changing it to NaN or INF.
 
 ### json.exception.out_of_range.407
 
-UBJSON and BSON only support integer numbers up to 9223372036854775807.
+UBJSON only support integer numbers up to 9223372036854775807.
 
 !!! failure "Example message"
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -328,6 +328,12 @@ class binary_reader
                 return get_number<std::int64_t, true>(input_format_t::bson, value) && sax->number_integer(value);
             }
 
+            case 0x11: // uint64
+            {
+                std::uint64_t value{};
+                return get_number<std::uint64_t, true>(input_format_t::bson, value) && sax->number_unsigned(value);
+            }
+
             default: // anything else not supported (yet)
             {
                 std::array<char, 3> cr{{}};

include/nlohmann/detail/output/binary_writer.hpp

@@ -1097,7 +1097,8 @@ class binary_writer
         }
         else
         {
-            JSON_THROW(out_of_range::create(407, concat("integer number ", std::to_string(j.m_data.m_value.number_unsigned), " cannot be represented by BSON as it does not fit int64"), &j));
+            write_bson_entry_header(name, 0x11 /* uint64 */);
+            write_number<std::uint64_t>(static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned), true);
         }
     }
 

single_include/nlohmann/json.hpp

@@ -10006,6 +10006,12 @@ class binary_reader
                 return get_number<std::int64_t, true>(input_format_t::bson, value) && sax->number_integer(value);
             }
 
+            case 0x11: // uint64
+            {
+                std::uint64_t value{};
+                return get_number<std::uint64_t, true>(input_format_t::bson, value) && sax->number_unsigned(value);
+            }
+
             default: // anything else not supported (yet)
             {
                 std::array<char, 3> cr{{}};
@@ -16733,7 +16739,8 @@ class binary_writer
         }
         else
         {
-            JSON_THROW(out_of_range::create(407, concat("integer number ", std::to_string(j.m_data.m_value.number_unsigned), " cannot be represented by BSON as it does not fit int64"), &j));
+            write_bson_entry_header(name, 0x11 /* uint64 */);
+            write_number<std::uint64_t>(static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned), true);
         }
     }
 

tests/src/unit-bson.cpp

@@ -331,7 +331,6 @@ TEST_CASE("BSON")
 
         SECTION("non-empty object with unsigned integer (64-bit) member")
         {
-            // directly encoding uint64 is not supported in bson (only for timestamp values)
             json const j =
             {
                 { "entry", std::uint64_t{0x1234567804030201} }
@@ -531,7 +530,6 @@ TEST_CASE("BSON")
 
         SECTION("Some more complex document")
         {
-            // directly encoding uint64 is not supported in bson (only for timestamp values)
             json const j =
             {
                 {"double", 42.5},
@@ -1164,10 +1162,7 @@ TEST_CASE("BSON numerical data")
                 std::vector<std::uint64_t> const numbers
                 {
                     static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()) + 1ULL,
-                    10000000000000000000ULL,
+                    0xffffffffffffffff,
-                    18000000000000000000ULL,
-                    (std::numeric_limits<std::uint64_t>::max)() - 1ULL,
-                    (std::numeric_limits<std::uint64_t>::max)(),
                 };
 
                 for (const auto i : numbers)
@@ -1184,7 +1179,7 @@ TEST_CASE("BSON numerical data")
                     std::vector<std::uint8_t> const expected_bson =
                     {
                         0x14u, 0x00u, 0x00u, 0x00u, // size (little endian)
-                        0x12u, /// entry: int64
+                        0x11u, /// entry: uint64
                         'e', 'n', 't', 'r', 'y', '\x00',
                         static_cast<std::uint8_t>((iu >> (8u * 0u)) & 0xffu),
                         static_cast<std::uint8_t>((iu >> (8u * 1u)) & 0xffu),
@@ -1197,12 +1192,15 @@ TEST_CASE("BSON numerical data")
                         0x00u // end marker
                     };
 
-                    CHECK_THROWS_AS(json::to_bson(j), json::out_of_range&);
+                    const auto bson = json::to_bson(j);
-#if JSON_DIAGNOSTICS
+                    CHECK(bson == expected_bson);
-                    CHECK_THROWS_WITH_STD_STR(json::to_bson(j), "[json.exception.out_of_range.407] (/entry) integer number " + std::to_string(i) + " cannot be represented by BSON as it does not fit int64");
+
-#else
+                    auto j_roundtrip = json::from_bson(bson);
-                    CHECK_THROWS_WITH_STD_STR(json::to_bson(j), "[json.exception.out_of_range.407] integer number " + std::to_string(i) + " cannot be represented by BSON as it does not fit int64");
+
-#endif
+                    CHECK(j.at("entry").is_number_unsigned());
+                    CHECK(j_roundtrip.at("entry").is_number_unsigned());
+                    CHECK(j_roundtrip == j);
+                    CHECK(json::from_bson(bson, true, false) == j);
                 }
             }