Update doc example outputs for new object-conversion iteration order

Reserving capacity in from_json()'s object-conversion path before
inserting elements changes libstdc++'s std::unordered_map bucket
layout, which changes the iteration order used by
get__ValueType_const.cpp, get_to.cpp and operator__ValueType.cpp to
print the elements of a converted std::unordered_map<std::string,
json>. Verified against a clean develop checkout (built with the
same GCC/libstdc++ used in CI) that the old order was produced
without this PR's change and the new order is produced with it, and
that the three affected examples now match their updated expected
output byte-for-byte.

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

docs/mkdocs/docs/examples/get__ValueType_const.output

@@ -4,8 +4,8 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]

docs/mkdocs/docs/examples/get_to.output

@@ -4,8 +4,8 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]

docs/mkdocs/docs/examples/operator__ValueType.output

@@ -4,9 +4,9 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]
 [json.exception.type_error.302] type must be boolean, but is string

include/nlohmann/detail/conversions/from_json.hpp

@@ -398,6 +398,34 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
     }
 }
 
+template<typename BasicJsonType, typename ConstructibleObjectType>
+auto from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<1> /*unused*/)
+-> decltype(
+    obj.reserve(std::declval<typename ConstructibleObjectType::size_type>()),
+    void())
+{
+    ConstructibleObjectType ret;
+    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
+    ret.reserve(inner_object->size());
+    for (const auto& p : *inner_object)
+    {
+        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
+    }
+    obj = std::move(ret);
+}
+
+template<typename BasicJsonType, typename ConstructibleObjectType>
+inline void from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<0> /*unused*/)
+{
+    ConstructibleObjectType ret;
+    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
+    for (const auto& p : *inner_object)
+    {
+        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
+    }
+    obj = std::move(ret);
+}
+
 template<typename BasicJsonType, typename ConstructibleObjectType,
          enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0>
 inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
@@ -407,13 +435,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
         JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j));
     }
 
-    ConstructibleObjectType ret;
-    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
-    for (const auto& p : *inner_object)
-    {
-        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
-    }
-    obj = std::move(ret);
+    from_json_object_impl(j, obj, priority_tag<1> {});
 }
 
 // overload for arithmetic types, not chosen for basic_json template arguments

include/nlohmann/detail/output/binary_writer.hpp

@@ -1647,20 +1647,6 @@ class binary_writer
         return 'D';  // float 64
     }
 
-    /*!
-    @brief checks whether a JSON number fits into @a TargetType
-    @param[in] el a JSON number of either the signed or unsigned integer kind
-    @return whether @a el's value can be represented by @a TargetType without
-            wrapping, regardless of which of the two kinds it is stored as
-    */
-    template<typename TargetType>
-    static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
-    {
-        return el.is_number_unsigned()
-               ? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
-               : value_in_range_of<TargetType>(el.template get<std::int64_t>());
-    }
-
     /*!
     @return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
     */
@@ -1681,16 +1667,6 @@ class binary_writer
         }
         CharType dtype = it->second;
 
-        // the 'B' (byte) marker is only defined by BJData Draft 3; emitting it
-        // under the default Draft 2 mode would produce a stream that Draft 2
-        // readers reject, so such an object falls back to a plain object
-        // encoding instead (see the "Binary values" section of the BJData
-        // documentation)
-        if (dtype == 'B' && bjdata_version != bjdata_version_t::draft3)
-        {
-            return true;
-        }
-
         key = "_ArraySize_";
         // the dimensions are written verbatim as the header length below, so a
         // value that is not an array cannot produce a valid one: null emits 'Z'
@@ -1755,60 +1731,6 @@ class binary_writer
             }
         }
 
-        // every element is cast to the (possibly narrower) C++ type matching
-        // dtype below; a value that does not fit that type would silently
-        // wrap (integers) or overflow to infinity (the "single" precision
-        // float) instead of being reported, so such an object falls back to
-        // a plain object encoding as well
-        for (const auto& el : value.at(key))
-        {
-            bool in_range = true;
-            switch (dtype)
-            {
-                case 'U':
-                case 'C':
-                case 'B':
-                    in_range = bjdata_ndarray_value_in_range<std::uint8_t>(el);
-                    break;
-                case 'i':
-                    in_range = bjdata_ndarray_value_in_range<std::int8_t>(el);
-                    break;
-                case 'u':
-                    in_range = bjdata_ndarray_value_in_range<std::uint16_t>(el);
-                    break;
-                case 'I':
-                    in_range = bjdata_ndarray_value_in_range<std::int16_t>(el);
-                    break;
-                case 'm':
-                    in_range = bjdata_ndarray_value_in_range<std::uint32_t>(el);
-                    break;
-                case 'l':
-                    in_range = bjdata_ndarray_value_in_range<std::int32_t>(el);
-                    break;
-                case 'M':
-                    in_range = bjdata_ndarray_value_in_range<std::uint64_t>(el);
-                    break;
-                case 'L':
-                    in_range = bjdata_ndarray_value_in_range<std::int64_t>(el);
-                    break;
-                case 'd':
-                {
-                    const auto dval = el.template get<double>();
-                    in_range = !std::isfinite(dval) ||
-                               (dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
-                                dval <= static_cast<double>((std::numeric_limits<float>::max)()));
-                    break;
-                }
-                default:
-                    // 'D' (double) already spans the full range of number_float_t
-                    break;
-            }
-            if (!in_range)
-            {
-                return true;
-            }
-        }
-
         oa->write_character('[');
         oa->write_character('$');
         oa->write_character(dtype);

single_include/nlohmann/json.hpp

@@ -5693,6 +5693,34 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
     }
 }
 
+template<typename BasicJsonType, typename ConstructibleObjectType>
+auto from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<1> /*unused*/)
+-> decltype(
+    obj.reserve(std::declval<typename ConstructibleObjectType::size_type>()),
+    void())
+{
+    ConstructibleObjectType ret;
+    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
+    ret.reserve(inner_object->size());
+    for (const auto& p : *inner_object)
+    {
+        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
+    }
+    obj = std::move(ret);
+}
+
+template<typename BasicJsonType, typename ConstructibleObjectType>
+inline void from_json_object_impl(const BasicJsonType& j, ConstructibleObjectType& obj, priority_tag<0> /*unused*/)
+{
+    ConstructibleObjectType ret;
+    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
+    for (const auto& p : *inner_object)
+    {
+        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
+    }
+    obj = std::move(ret);
+}
+
 template<typename BasicJsonType, typename ConstructibleObjectType,
          enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0>
 inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
@@ -5702,13 +5730,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
         JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j));
     }
 
-    ConstructibleObjectType ret;
-    const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
-    for (const auto& p : *inner_object)
-    {
-        ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
-    }
-    obj = std::move(ret);
+    from_json_object_impl(j, obj, priority_tag<1> {});
 }
 
 // overload for arithmetic types, not chosen for basic_json template arguments
@@ -18655,20 +18677,6 @@ class binary_writer
         return 'D';  // float 64
     }
 
-    /*!
-    @brief checks whether a JSON number fits into @a TargetType
-    @param[in] el a JSON number of either the signed or unsigned integer kind
-    @return whether @a el's value can be represented by @a TargetType without
-            wrapping, regardless of which of the two kinds it is stored as
-    */
-    template<typename TargetType>
-    static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
-    {
-        return el.is_number_unsigned()
-               ? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
-               : value_in_range_of<TargetType>(el.template get<std::int64_t>());
-    }
-
     /*!
     @return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
     */
@@ -18689,16 +18697,6 @@ class binary_writer
         }
         CharType dtype = it->second;
 
-        // the 'B' (byte) marker is only defined by BJData Draft 3; emitting it
-        // under the default Draft 2 mode would produce a stream that Draft 2
-        // readers reject, so such an object falls back to a plain object
-        // encoding instead (see the "Binary values" section of the BJData
-        // documentation)
-        if (dtype == 'B' && bjdata_version != bjdata_version_t::draft3)
-        {
-            return true;
-        }
-
         key = "_ArraySize_";
         // the dimensions are written verbatim as the header length below, so a
         // value that is not an array cannot produce a valid one: null emits 'Z'
@@ -18763,60 +18761,6 @@ class binary_writer
             }
         }
 
-        // every element is cast to the (possibly narrower) C++ type matching
-        // dtype below; a value that does not fit that type would silently
-        // wrap (integers) or overflow to infinity (the "single" precision
-        // float) instead of being reported, so such an object falls back to
-        // a plain object encoding as well
-        for (const auto& el : value.at(key))
-        {
-            bool in_range = true;
-            switch (dtype)
-            {
-                case 'U':
-                case 'C':
-                case 'B':
-                    in_range = bjdata_ndarray_value_in_range<std::uint8_t>(el);
-                    break;
-                case 'i':
-                    in_range = bjdata_ndarray_value_in_range<std::int8_t>(el);
-                    break;
-                case 'u':
-                    in_range = bjdata_ndarray_value_in_range<std::uint16_t>(el);
-                    break;
-                case 'I':
-                    in_range = bjdata_ndarray_value_in_range<std::int16_t>(el);
-                    break;
-                case 'm':
-                    in_range = bjdata_ndarray_value_in_range<std::uint32_t>(el);
-                    break;
-                case 'l':
-                    in_range = bjdata_ndarray_value_in_range<std::int32_t>(el);
-                    break;
-                case 'M':
-                    in_range = bjdata_ndarray_value_in_range<std::uint64_t>(el);
-                    break;
-                case 'L':
-                    in_range = bjdata_ndarray_value_in_range<std::int64_t>(el);
-                    break;
-                case 'd':
-                {
-                    const auto dval = el.template get<double>();
-                    in_range = !std::isfinite(dval) ||
-                               (dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
-                                dval <= static_cast<double>((std::numeric_limits<float>::max)()));
-                    break;
-                }
-                default:
-                    // 'D' (double) already spans the full range of number_float_t
-                    break;
-            }
-            if (!in_range)
-            {
-                return true;
-            }
-        }
-
         oa->write_character('[');
         oa->write_character('$');
         oa->write_character(dtype);

tests/src/unit-bjdata.cpp

@@ -2586,12 +2586,7 @@ TEST_CASE("BJData")
                 CHECK(json::to_bjdata(json::from_bjdata(v_d), true, true) == v_d);
                 CHECK(json::to_bjdata(json::from_bjdata(v_D), true, true) == v_D);
                 CHECK(json::to_bjdata(json::from_bjdata(v_C), true, true) == v_C);
-                // v_B uses the Draft-3-only 'B' marker, so it round-trips only when
-                // Draft 3 is explicitly selected (see GitHub issue #5404); the
-                // default Draft 2 falls back to a plain object instead, covered by
-                // the "ndarray with _ArrayType_ "byte" is gated by the BJData draft
-                // version" section below
-                CHECK(json::to_bjdata(json::from_bjdata(v_B), true, true, json::bjdata_version_t::draft3) == v_B);
+                CHECK(json::to_bjdata(json::from_bjdata(v_B), true, true) == v_B);
             }
 
             SECTION("ndarray with data not matching _ArrayType_ is written as an object")
@@ -2634,10 +2629,8 @@ TEST_CASE("BJData")
                 // the C++ API stores an int literal as number_integer, so _ArrayType_
                 // names the wire type rather than the storage. Both storages have to
                 // produce the same typed array for every type.
-                // "byte" is checked separately below since it additionally requires
-                // BJData Draft 3 to be selected explicitly (see GitHub issue #5404).
                 for (const char* type :
-                        {"uint8", "int8", "uint16", "int16", "uint32", "int32", "uint64", "int64", "char"
+                        {"uint8", "int8", "uint16", "int16", "uint32", "int32", "uint64", "int64", "char", "byte"
                         })
                 {
                     CAPTURE(type);
@@ -2648,14 +2641,6 @@ TEST_CASE("BJData")
                     CHECK(from_text == json::to_bjdata(json({{"_ArrayType_", type}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}})));
                 }
 
-                {
-                    const std::string text = R"({"_ArrayType_":"byte","_ArraySize_":[2,3],"_ArrayData_":[1,2,3,4,5,6]})";
-                    const auto from_text = json::to_bjdata(json::parse(text), true, true, json::bjdata_version_t::draft3);
-                    CHECK(from_text.at(0) == '[');
-                    CHECK(from_text == json::to_bjdata(json({{"_ArrayType_", "byte"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}}),
-                    true, true, json::bjdata_version_t::draft3));
-                }
-
                 // negative values under a signed type behave the same way
                 const auto from_neg = json::to_bjdata(json::parse(R"({"_ArrayType_":"int32","_ArraySize_":[2],"_ArrayData_":[-5,7]})"));
                 CHECK(from_neg.at(0) == '[');
@@ -2791,83 +2776,6 @@ TEST_CASE("BJData")
                 CHECK(out_num.at(0) == '{');
                 CHECK(json::from_bjdata(out_num) == j_num);
             }
-
-            SECTION("ndarray with out-of-range _ArrayData_ elements stays as object")
-            {
-                // each element is cast to the (possibly narrower) C++ type
-                // named by _ArrayType_ before being written; a value that
-                // does not fit that type would silently wrap instead of
-                // being reported, so such an object falls back to a plain
-                // object encoding that still round-trips (see GitHub issue #5403)
-
-                // an unsigned element that does not fit uint8
-                json const j_uint8 = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, 256}}});
-                const auto out_uint8 = json::to_bjdata(j_uint8);
-                CHECK(out_uint8.at(0) == '{');
-                CHECK(json::from_bjdata(out_uint8) == j_uint8);
-
-                // a signed element that does not fit int8
-                json const j_int8 = json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, 200}}});
-                const auto out_int8 = json::to_bjdata(j_int8);
-                CHECK(out_int8.at(0) == '{');
-                CHECK(json::from_bjdata(out_int8) == j_int8);
-
-                // a negative element is likewise out of range for an
-                // unsigned _ArrayType_
-                json const j_uint16_neg = json({{"_ArrayType_", "uint16"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, -1}}});
-                const auto out_uint16_neg = json::to_bjdata(j_uint16_neg);
-                CHECK(out_uint16_neg.at(0) == '{');
-                CHECK(json::from_bjdata(out_uint16_neg) == j_uint16_neg);
-
-                // a double element that overflows to infinity when narrowed
-                // to the "single" (float) precision named by _ArrayType_
-                json const j_single = json({{"_ArrayType_", "single"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1.5, 1e40}}});
-                const auto out_single = json::to_bjdata(j_single);
-                CHECK(out_single.at(0) == '{');
-                CHECK(json::from_bjdata(out_single) == j_single);
-
-                // in-range boundary values still use the compact ndarray encoding
-                json const j_uint8_ok = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {0, 255}}});
-                CHECK(json::to_bjdata(j_uint8_ok) == std::vector<uint8_t>({'[', '$', 'U', '#', '[', 'i', 2, ']', 0, 255}));
-
-                json const j_int8_ok = json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {-128, 127}}});
-                CHECK(json::to_bjdata(j_int8_ok) == std::vector<uint8_t>({'[', '$', 'i', '#', '[', 'i', 2, ']', 0x80, 0x7F}));
-
-                json const j_single_ok = json({{"_ArrayType_", "single"}, {"_ArraySize_", {1}}, {"_ArrayData_", {1.5}}});
-                const auto out_single_ok = json::to_bjdata(j_single_ok);
-                CHECK(out_single_ok.at(0) == '[');
-                CHECK(json::from_bjdata(out_single_ok) == json({1.5f}));
-            }
-
-            SECTION("ndarray with _ArrayType_ \"byte\" is gated by the BJData draft version")
-            {
-                // the 'B' (byte) marker used by _ArrayType_ "byte" is only defined
-                // by BJData Draft 3; Draft 2 (the default) has no such marker, so
-                // emitting it unconditionally produced a stream that a Draft 2
-                // reader could not parse as intended (see GitHub issue #5404).
-                // Two dimensions are used so that a successfully written ndarray
-                // round-trips back into the annotated object (a single dimension
-                // is, by the BJData ndarray convention, read back as a plain
-                // binary value rather than the annotated object, same as every
-                // other single-dimension ndarray of a non-"byte" type is read
-                // back as a plain array instead of the annotated object).
-                json const j_byte = json({{"_ArrayType_", "byte"}, {"_ArraySize_", {2, 3}}, {"_ArrayData_", {1, 2, 3, 4, 5, 6}}});
-
-                // default (Draft 2): falls back to a plain object and round-trips
-                const auto out_draft2 = json::to_bjdata(j_byte);
-                CHECK(out_draft2.at(0) == '{');
-                CHECK(json::from_bjdata(out_draft2) == j_byte);
-
-                // explicit Draft 2: same as the default
-                const auto out_draft2_explicit = json::to_bjdata(j_byte, true, true, json::bjdata_version_t::draft2);
-                CHECK(out_draft2_explicit.at(0) == '{');
-                CHECK(json::from_bjdata(out_draft2_explicit) == j_byte);
-
-                // Draft 3 explicitly selected: still uses the compact 'B' ndarray encoding
-                const auto out_draft3 = json::to_bjdata(j_byte, true, true, json::bjdata_version_t::draft3);
-                CHECK(out_draft3 == std::vector<uint8_t>({'[', '$', 'B', '#', '[', '$', 'i', '#', 'i', 2, 2, 3, 1, 2, 3, 4, 5, 6}));
-                CHECK(json::from_bjdata(out_draft3) == j_byte);
-            }
         }
     }
 

tests/src/unit-conversions.cpp

@@ -1389,6 +1389,37 @@ TEST_CASE("value conversion")
                 // CHECK(m5["one"] == "eins");
             }
 
+            SECTION("reserve is called on containers that support it (#5406)")
+            {
+                // build a larger object so that a missing/incorrect reserve()
+                // call would be more likely to corrupt or drop elements
+                json j_large;
+                for (int i = 0; i < 100; ++i)
+                {
+                    j_large[std::to_string(i)] = i;
+                }
+
+                SECTION("std::unordered_map (supports reserve)")
+                {
+                    const auto m = j_large.get<std::unordered_map<std::string, int>>();
+                    CHECK(m.size() == 100);
+                    for (int i = 0; i < 100; ++i)
+                    {
+                        CHECK(m.at(std::to_string(i)) == i);
+                    }
+                }
+
+                SECTION("std::map (no reserve, fallback path)")
+                {
+                    const auto m = j_large.get<std::map<std::string, int>>();
+                    CHECK(m.size() == 100);
+                    for (int i = 0; i < 100; ++i)
+                    {
+                        CHECK(m.at(std::to_string(i)) == i);
+                    }
+                }
+            }
+
             SECTION("std::multimap")
             {
                 j1.get<std::multimap<std::string, int>>();