Fix to_bjdata() silently truncating out-of-range _ArrayData_ elements

write_bjdata_ndarray() validated that each _ArrayData_ element matched
the number kind (integer vs. float) named by _ArrayType_, but not its
range. An element that did not fit the target C++ type (e.g. 256 for
"uint8") was silently wrapped by the static_cast used to write it, or,
for "single", silently overflowed to infinity.

Range-check each element against the type named by _ArrayType_ before
writing it, reusing the existing fallback path that already encodes
the annotated object as a plain object for other invalid-annotation
cases in this function.

Fixes #5403.

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

docs/mkdocs/docs/api/basic_json/swap.md

@@ -34,14 +34,10 @@ void swap(typename binary_t::container_type& other);
 ```
 
 1. Exchanges the contents of the JSON value with those of `other`. Does not invoke any move, copy, or swap operations on
-   individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. If macro
-   [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
-   [`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
+   individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. 
 2. Exchanges the contents of the JSON value from `left` with those of `right`. Does not invoke any move, copy, or swap
    operations on individual elements. All iterators and references remain valid. The past-the-end iterator is
-   invalidated. Implemented as a friend function callable via ADL. If macro
-   [`JSON_DIAGNOSTIC_POSITIONS`](../macros/json_diagnostic_positions.md) is defined to `#!cpp 1`, the
-   [`start_pos()`](start_pos.md)/[`end_pos()`](end_pos.md) diagnostic positions are exchanged along with the value.
+   invalidated. Implemented as a friend function callable via ADL.
 3. Exchanges the contents of a JSON array with those of `other`. Does not invoke any move, copy, or swap operations on
    individual elements. All iterators and references remain valid. The past-the-end iterator is invalidated. 
 4. Exchanges the contents of a JSON object with those of `other`. Does not invoke any move, copy, or swap operations on

include/nlohmann/detail/output/binary_writer.hpp

@@ -1647,6 +1647,20 @@ 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
     */
@@ -1731,6 +1745,60 @@ 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);

include/nlohmann/json.hpp

@@ -3547,11 +3547,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         std::swap(m_data.m_type, other.m_data.m_type);
         std::swap(m_data.m_value, other.m_data.m_value);
 
-#if JSON_DIAGNOSTIC_POSITIONS
-        std::swap(start_position, other.start_position);
-        std::swap(end_position, other.end_position);
-#endif
-
         set_parents();
         other.set_parents();
         assert_invariant();

single_include/nlohmann/json.hpp

@@ -18655,6 +18655,20 @@ 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
     */
@@ -18739,6 +18753,60 @@ 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);
@@ -24975,11 +25043,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         std::swap(m_data.m_type, other.m_data.m_type);
         std::swap(m_data.m_value, other.m_data.m_value);
 
-#if JSON_DIAGNOSTIC_POSITIONS
-        std::swap(start_position, other.start_position);
-        std::swap(end_position, other.end_position);
-#endif
-
         set_parents();
         other.set_parents();
         assert_invariant();

tests/src/unit-bjdata.cpp

@@ -2776,6 +2776,53 @@ 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}));
+            }
         }
     }
 

tests/src/unit-class_parser_diagnostic_positions.cpp

@@ -1955,80 +1955,3 @@ TEST_CASE("parser class")
         }
     }
 }
-
-TEST_CASE("diagnostic positions: value lifetime")
-{
-    SECTION("copy constructor copies positions, recursively")
-    {
-        const std::string s = R"({"a":1,"b":[1,2,3]})";
-        const json a = json::parse(s);
-        const json b = a; // NOLINT(performance-unnecessary-copy-initialization)
-
-        CHECK(b.start_pos() == a.start_pos());
-        CHECK(b.end_pos() == a.end_pos());
-        CHECK(b["b"].start_pos() == a["b"].start_pos());
-        CHECK(b["b"].end_pos() == a["b"].end_pos());
-    }
-
-    SECTION("move constructor resets the moved-from value to npos")
-    {
-        const std::string s = R"({"a":1,"b":[1,2,3]})";
-        json a = json::parse(s);
-        const auto a_start = a.start_pos();
-        const auto a_end = a.end_pos();
-
-        const json b(std::move(a));
-
-        CHECK(b.start_pos() == a_start);
-        CHECK(b.end_pos() == a_end);
-
-        CHECK(a.start_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
-        CHECK(a.end_pos() == std::string::npos); // NOLINT(bugprone-use-after-move,clang-analyzer-cplusplus.Move)
-    }
-
-    SECTION("swap() exchanges positions along with the values")
-    {
-        // basic_json::swap() (and the friend swap() that forwards to it) used
-        // to swap only m_data.m_type/m_data.m_value, leaving
-        // start_position/end_position untouched -- unlike copy-assignment's
-        // operator=(basic_json), which swaps positions as part of its
-        // copy-and-swap implementation. After swap(a, b), each value ended up
-        // with the *other* value's content but its *own* original position.
-        // This is now fixed so that swap() is consistent with copy-assignment.
-        json a = json::parse(R"({"a":1})");
-        json b = json::parse(R"([1,2,3,4,5])");
-        const auto a_start = a.start_pos();
-        const auto a_end = a.end_pos();
-        const auto b_start = b.start_pos();
-        const auto b_end = b.end_pos();
-        // lengths (and thus end positions) differ, which is enough to tell
-        // after the swap whether positions actually moved with the values
-        CHECK(a_end != b_end);
-
-        using std::swap;
-        swap(a, b);
-
-        CHECK(a == json::parse(R"([1,2,3,4,5])"));
-        CHECK(b == json::parse(R"({"a":1})"));
-
-        CHECK(a.start_pos() == b_start);
-        CHECK(a.end_pos() == b_end);
-        CHECK(b.start_pos() == a_start);
-        CHECK(b.end_pos() == a_end);
-
-        // member swap() behaves the same as the free function
-        json c = json::parse(R"({"a":1})");
-        json d = json::parse(R"([1,2,3,4,5])");
-        const auto c_start = c.start_pos();
-        const auto c_end = c.end_pos();
-        const auto d_start = d.start_pos();
-        const auto d_end = d.end_pos();
-
-        c.swap(d);
-
-        CHECK(c.start_pos() == d_start);
-        CHECK(c.end_pos() == d_end);
-        CHECK(d.start_pos() == c_start);
-        CHECK(d.end_pos() == c_end);
-    }
-}