🚶 fix format

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

.github/dependabot.yml

@@ -4,6 +4,8 @@ updates:
     directory: /
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7
     groups:
       codeql-action:
         patterns:
@@ -13,23 +15,33 @@ updates:
     directory: /docs/mkdocs
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: pip
     directory: /tools/astyle
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: pip
     directory: /tools/generate_natvis
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: pip
     directory: /tools/serve_header
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7
 
   - package-ecosystem: pip
     directory: /cmake/requirements
     schedule:
       interval: daily
+    cooldown:
+      default-days: 7

.github/workflows/semgrep.yml

@@ -49,7 +49,7 @@ jobs:
       # SEMGREP_APP_TOKEN is still passed through so registry auth works if a
       # token is ever added.
       - name: Install Semgrep
-        run: python3 -m pip install --user semgrep
+        run: python3 -m pip install --user semgrep==1.168.0
 
       # `semgrep scan --sarif` always exits 0 even with findings; continue-on-error
       # is a safety net so the SARIF upload still runs if the scan itself errors.

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

@@ -82,7 +82,13 @@ basic_json(basic_json&& other) noexcept;
 4. This is a constructor for existing `basic_json` types. It does not hijack copy/move constructors, since the parameter
    has different template arguments than the current ones.
 
-    The constructor tries to convert the internal `m_value` of the parameter.
+    The constructor tries to convert the internal `m_value` of the parameter. Each member value (object, array, string,
+    etc.) is serialized via the corresponding `to_json()` overload. For objects and strings, the conversion requires
+    that the *target* `basic_json` type's `object_t::key_type` (or `string_t`) be directly constructible from the
+    *source* type's corresponding member type via `is_constructible`. If this requirement is not met, the conversion
+    does not fail to compile; instead, it silently falls back to the array-conversion path, which represents objects
+    as arrays of `[key, value]` pairs and strings as arrays of character codes. This is a known limitation tracked in
+    [issue #3425](https://github.com/nlohmann/json/issues/3425).
 
 5. Creates a JSON value of type array or object from the passed initializer list `init`. In case `type_deduction` is
    `#!cpp true` (default), the type of the JSON value to be created is deducted from the initializer list `init`
@@ -147,6 +153,11 @@ basic_json(basic_json&& other) noexcept;
     - `BasicJsonType` is a `basic_json` type.
     - `BasicJsonType` has different template arguments than `basic_json_t`.
     
+    **Note:** For cross-`basic_json` conversions to produce correct results, the target `basic_json`'s
+    `object_t::key_type` and `string_t` must be directly constructible from the source `basic_json`'s
+    corresponding types. See the description of overload (4) above for details on what happens when
+    this requirement is not met.
+
 `U`:
 :   `uncvref_t<CompatibleType>`
 

docs/mkdocs/docs/api/basic_json/object_t.md

@@ -93,6 +93,15 @@ alphabetical order as `std::map` with `std::less` is used by default. Please not
 [RFC 8259](https://tools.ietf.org/html/rfc8259), because any order implements the specified "unordered" nature of JSON
 objects.
 
+#### Cross-`basic_json` conversion requirements
+
+When converting an object from one `basic_json` specialization to another via the
+[converting constructor](basic_json.md#overload-4), the target `object_t`'s `key_type` must be
+directly constructible from the source `basic_json`'s `string_t` type (or more generally, from the
+source object's key type). If this requirement is not met, the conversion does not fail; instead,
+the object is silently converted as an array of key-value pairs, which is incorrect. See
+[issue #3425](https://github.com/nlohmann/json/issues/3425) for details and an example.
+
 ## Examples
 
 ??? example

docs/mkdocs/docs/api/basic_json/std_hash.md

@@ -6,9 +6,18 @@ namespace std {
 }
 ```
 
-Return a hash value for a JSON object. The hash function tries to rely on `std::hash` where possible. Furthermore, the
+Return a hash value for a JSON object. The hash function tries to rely on `std::hash` where possible. To satisfy the
-type of the JSON value is taken into account to have different hash values for `#!json null`, `#!cpp 0`, `#!cpp 0U`, and
+`std::hash` contract, numeric JSON values that compare equal must hash to the same value. This means:
-`#!cpp false`, etc.
+
+- `json(42)`, `json(42u)`, and `json(42.0)` all hash to the same value
+- `json(0)`, `json(0u)`, and `json(0.0)` all hash to the same value
+
+Different types hash differently for non-numeric types (e.g., `#!json null`, `#!cpp false`, and strings all have distinct hashes).
+
+**Edge case:** For very large integers outside the exact representable range of the floating-point type (beyond ~2^53 for
+typical `double`), the hash values for integer and floating-point values may differ, even if the floating-point value
+was obtained by casting the integer (due to precision loss). This is a documented limitation arising from how the
+comparison operator normalizes numeric types.
 
 ## Examples
 

docs/mkdocs/docs/api/basic_json/string_t.md

@@ -45,6 +45,15 @@ This implementation is interoperable as it does compare strings code unit by cod
 String values are stored as pointers in a `basic_json` type. That is, for any access to string values, a pointer of type
 `string_t*` must be dereferenced.
 
+#### Cross-`basic_json` conversion requirements
+
+When converting a string value from one `basic_json` specialization to another via the
+[converting constructor](basic_json.md#overload-4), the target `string_t` must be directly
+constructible from the source `basic_json`'s `string_t` type. If this requirement is not met, the
+conversion does not fail; instead, the string is silently converted as an array of character codes,
+which is incorrect. See [issue #3425](https://github.com/nlohmann/json/issues/3425) for details
+and an example.
+
 ## Examples
 
 ??? example

docs/mkdocs/docs/examples/std_hash.cpp

@@ -11,6 +11,7 @@ int main()
               << "hash(false) = " << std::hash<json> {}(json(false)) << '\n'
               << "hash(0) = " << std::hash<json> {}(json(0)) << '\n'
               << "hash(0U) = " << std::hash<json> {}(json(0U)) << '\n'
+              << "hash(0.0) = " << std::hash<json> {}(json(0.0)) << '\n'
               << "hash(\"\") = " << std::hash<json> {}(json("")) << '\n'
               << "hash({}) = " << std::hash<json> {}(json::object()) << '\n'
               << "hash([]) = " << std::hash<json> {}(json::array()) << '\n'

docs/mkdocs/docs/examples/std_hash.output

@@ -1,8 +1,9 @@
 hash(null) = 2654435769
 hash(false) = 2654436030
-hash(0) = 2654436095
+hash(0) = 2654436221
-hash(0U) = 2654436156
+hash(0U) = 2654436221
-hash("") = 6142509191626859748
+hash(0.0) = 2654436221
+hash("") = 11160318156688833227
 hash({}) = 2654435832
 hash([]) = 2654435899
-hash({"hello": "world"}) = 4469488738203676328
+hash({"hello": "world"}) = 3701319991624763853

docs/mkdocs/docs/robots.txt

@@ -0,0 +1,4 @@
+User-agent: *
+Allow: /
+
+Sitemap: https://json.nlohmann.me/sitemap.xml

docs/mkdocs/hooks/copy_markdown_source.py

@@ -0,0 +1,25 @@
+"""Copy each documentation page's Markdown source into the built site."""
+
+# Creates a `<path>.md` sibling of each HTML output (for example,
+# `features/comments/` becomes `features/comments.md`) so agents and tools can
+# fetch the raw Markdown directly instead of parsing rendered HTML.
+
+import os
+import shutil
+
+_pages = []
+
+
+def on_files(files, config):
+    global _pages
+    _pages = [f for f in files if f.is_documentation_page()]
+    return files
+
+
+def on_post_build(config):
+    site_dir = config["site_dir"]
+    for file in _pages:
+        url = file.url.rstrip("/")
+        target = os.path.join(site_dir, (url or "index") + ".md")
+        os.makedirs(os.path.dirname(target), exist_ok=True)
+        shutil.copyfile(file.abs_src_path, target)

docs/mkdocs/mkdocs.yml

@@ -367,6 +367,9 @@ markdown_extensions:
       auto_append:
         - ../includes/glossary.md
 
+hooks:
+  - hooks/copy_markdown_source.py
+
 plugins:
   - search:
       separator: '[\s\-\.]'
@@ -389,6 +392,33 @@ plugins:
         - https://nlohmann.github.io/json/*
         - mailto:*
   - privacy
+  - llmstxt:
+      markdown_description: >
+        JSON for Modern C++ is a C++11 header-only library implementing a JSON
+        value type with an STL-like API, JSON Pointer/Patch, CBOR/MessagePack/
+        BSON/UBJSON/BJData binary format support, and a SAX-style parser interface.
+      sections:
+        Home:
+          - index.md
+          - home/*.md
+        Features:
+          - features/*.md
+          - features/binary_formats/*.md
+          - features/element_access/*.md
+          - features/parsing/*.md
+          - features/types/*.md
+        Integration:
+          - integration/*.md
+        API Documentation:
+          - api/*.md
+          - api/basic_json/*.md
+          - api/adl_serializer/*.md
+          - api/byte_container_with_subtype/*.md
+          - api/json_pointer/*.md
+          - api/json_sax/*.md
+          - api/macros/*.md
+        Community:
+          - community/*.md
 
 extra_css:
   - css/custom.css

docs/mkdocs/requirements.txt

@@ -7,5 +7,6 @@ mkdocs-material-extensions==1.3.1                   # extensions
 mkdocs-minify-plugin==0.8.0                         # plugin "minify"
 mkdocs-redirects==1.2.3                             # plugin "redirects"
 mkdocs-htmlproofer-plugin==1.5.0                    # plugin "htmlproofer"
+mkdocs-llmstxt==0.5.0                               # plugin "llmstxt"
 
 PyYAML==6.0.3                                       # linter

include/nlohmann/detail/hash.hpp

@@ -11,6 +11,8 @@
 #include <cstdint> // uint8_t
 #include <cstddef> // size_t
 #include <functional> // hash
+#include <limits> // numeric_limits
+#include <cmath> // isfinite
 
 #include <nlohmann/detail/abi_macros.hpp>
 #include <nlohmann/detail/value_t.hpp>
@@ -26,12 +28,66 @@ inline std::size_t combine(std::size_t seed, std::size_t h) noexcept
     return seed;
 }
 
+// Check if a number_integer_t value is exactly representable as number_float_t
+// Returns true if static_cast<number_integer_t>(static_cast<number_float_t>(val)) == val
+template<typename BasicJsonType>
+inline bool is_exactly_representable_as_float(typename BasicJsonType::number_integer_t val) noexcept
+{
+    using number_integer_t = typename BasicJsonType::number_integer_t;
+    using number_float_t = typename BasicJsonType::number_float_t;
+
+    // If the float type's mantissa covers the integer type's entire range, all values round-trip
+    constexpr int float_digits = std::numeric_limits<number_float_t>::digits;
+    constexpr int int_digits = std::numeric_limits<number_integer_t>::digits;
+
+    if (float_digits >= int_digits)
+    {
+        return true;
+    }
+
+    // For values outside float's exact range, they don't round-trip
+    // The safe way to check: compute the max magnitude that round-trips
+    // Using unsigned arithmetic to avoid UB with negating INT_MIN
+
+    // Max magnitude representable exactly: 2^(digits-1) - 1 for signed, 2^digits - 1 for unsigned range
+    // But we're checking a signed value, so use 2^digits as the threshold
+    constexpr auto max_exact = static_cast<number_integer_t>(1) << (float_digits - 1);
+
+    // Check absolute value against this threshold
+    if (val >= 0)
+    {
+        if (val >= max_exact)
+        {
+            return false;
+        }
+    }
+    else
+    {
+        // For negative values, check via unsigned wrapping arithmetic
+        // -val in unsigned domain; if it wraps, the value is too negative
+        auto unsigned_abs = static_cast<typename BasicJsonType::number_unsigned_t>(-val);
+        if (unsigned_abs >= static_cast<typename BasicJsonType::number_unsigned_t>(max_exact))
+        {
+            return false;
+        }
+    }
+
+    // For values within the exact range, verify the round-trip
+    const auto f = static_cast<number_float_t>(val);
+    return std::isfinite(f) && static_cast<number_integer_t>(f) == val;
+}
+
 /*!
 @brief hash a JSON value
 
 The hash function tries to rely on std::hash where possible. Furthermore, the
 type of the JSON value is taken into account to have different hash values for
-null, 0, 0U, and false, etc.
+most types. However, numeric types (number_integer, number_unsigned, number_float)
+are hashed to satisfy the std::hash contract: if two json values compare equal,
+they must have equal hash values. This means json(42), json(42u), and json(42.0)
+all hash to the same value (since they compare equal). For large integer values
+outside the exact representable range of the float type, integer values are hashed
+in their own domain to avoid precision loss.
 
 @tparam BasicJsonType basic_json specialization
 @param j JSON value to hash
@@ -90,20 +146,47 @@ std::size_t hash(const BasicJsonType& j)
 
         case BasicJsonType::value_t::number_integer:
         {
-            const auto h = std::hash<number_integer_t> {}(j.template get<number_integer_t>());
+            const auto v = j.template get<number_integer_t>();
-            return combine(type, h);
+            // Use a shared numeric type tag so all numeric types that are equal hash the same
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+
+            if (is_exactly_representable_as_float<BasicJsonType>(v))
+            {
+                const auto h = std::hash<number_float_t> {}(static_cast<number_float_t>(v));
+                return combine(numeric_type, h);
+            }
+            else
+            {
+                const auto h = std::hash<number_integer_t> {}(v);
+                return combine(numeric_type, h);
+            }
         }
 
         case BasicJsonType::value_t::number_unsigned:
         {
-            const auto h = std::hash<number_unsigned_t> {}(j.template get<number_unsigned_t>());
+            const auto v = j.template get<number_unsigned_t>();
-            return combine(type, h);
+            // Normalize to signed (matching operator== behavior for U-vs-I comparison)
+            const auto v_as_signed = static_cast<number_integer_t>(v);
+            // Use a shared numeric type tag so all numeric types that are equal hash the same
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+
+            if (is_exactly_representable_as_float<BasicJsonType>(v_as_signed))
+            {
+                const auto h = std::hash<number_float_t> {}(static_cast<number_float_t>(v_as_signed));
+                return combine(numeric_type, h);
+            }
+            else
+            {
+                const auto h = std::hash<number_integer_t> {}(v_as_signed);
+                return combine(numeric_type, h);
+            }
         }
 
         case BasicJsonType::value_t::number_float:
         {
             const auto h = std::hash<number_float_t> {}(j.template get<number_float_t>());
-            return combine(type, h);
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+            return combine(numeric_type, h);
         }
 
         case BasicJsonType::value_t::binary:

include/nlohmann/detail/output/serializer.hpp

@@ -465,18 +465,12 @@ class serializer
                             {
                                 if (codepoint <= 0xFFFF)
                                 {
-                                    // NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
-                                    static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 7, "\\u%04x",
-                                                                      static_cast<std::uint16_t>(codepoint)));
-                                    bytes += 6;
                                 }
                                 else
                                 {
-                                    // NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
-                                    static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 13, "\\u%04x\\u%04x",
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
-                                                                      static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)),
-                                                                      static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu))));
-                                    bytes += 12;
                                 }
                             }
                             else
@@ -683,6 +677,32 @@ class serializer
         return result;
     }
 
+    /*!
+     * @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
+     *
+     * Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
+     * string escaping hot path. It writes exactly six characters ('\\', 'u' and
+     * four hex digits) at position @a pos of @a string_buffer via a nibble
+     * lookup table, avoiding the format-string parsing and locale machinery of
+     * `snprintf`. Advances @a pos by the number of bytes written (6).
+     *
+     * @param[in] pos       position in @a string_buffer to write at; there must
+     *                      be at least 6 bytes of headroom
+     * @param[in] codeunit  16-bit value to encode
+     */
+    void write_u_escape(std::size_t& pos, std::uint16_t codeunit) noexcept
+    {
+        JSON_ASSERT(string_buffer.size() - pos >= 6);
+        constexpr const char* nibble_to_hex = "0123456789abcdef";
+        string_buffer[pos + 0] = '\\';
+        string_buffer[pos + 1] = 'u';
+        string_buffer[pos + 2] = nibble_to_hex[(codeunit >> 12u) & 0x0Fu];
+        string_buffer[pos + 3] = nibble_to_hex[(codeunit >> 8u) & 0x0Fu];
+        string_buffer[pos + 4] = nibble_to_hex[(codeunit >> 4u) & 0x0Fu];
+        string_buffer[pos + 5] = nibble_to_hex[codeunit & 0x0Fu];
+        pos += 6;
+    }
+
     // templates to avoid warnings about useless casts
     template <typename NumberType, enable_if_t<std::is_signed<NumberType>::value, int> = 0>
     bool is_negative_number(NumberType x)

single_include/nlohmann/json.hpp

@@ -6677,6 +6677,8 @@ NLOHMANN_JSON_NAMESPACE_END
 #include <cstdint> // uint8_t
 #include <cstddef> // size_t
 #include <functional> // hash
+#include <limits> // numeric_limits
+#include <cmath> // isfinite
 
 // #include <nlohmann/detail/abi_macros.hpp>
 
@@ -6694,12 +6696,66 @@ inline std::size_t combine(std::size_t seed, std::size_t h) noexcept
     return seed;
 }
 
+// Check if a number_integer_t value is exactly representable as number_float_t
+// Returns true if static_cast<number_integer_t>(static_cast<number_float_t>(val)) == val
+template<typename BasicJsonType>
+inline bool is_exactly_representable_as_float(typename BasicJsonType::number_integer_t val) noexcept
+{
+    using number_integer_t = typename BasicJsonType::number_integer_t;
+    using number_float_t = typename BasicJsonType::number_float_t;
+
+    // If the float type's mantissa covers the integer type's entire range, all values round-trip
+    constexpr int float_digits = std::numeric_limits<number_float_t>::digits;
+    constexpr int int_digits = std::numeric_limits<number_integer_t>::digits;
+
+    if (float_digits >= int_digits)
+    {
+        return true;
+    }
+
+    // For values outside float's exact range, they don't round-trip
+    // The safe way to check: compute the max magnitude that round-trips
+    // Using unsigned arithmetic to avoid UB with negating INT_MIN
+
+    // Max magnitude representable exactly: 2^(digits-1) - 1 for signed, 2^digits - 1 for unsigned range
+    // But we're checking a signed value, so use 2^digits as the threshold
+    constexpr auto max_exact = static_cast<number_integer_t>(1) << (float_digits - 1);
+
+    // Check absolute value against this threshold
+    if (val >= 0)
+    {
+        if (val >= max_exact)
+        {
+            return false;
+        }
+    }
+    else
+    {
+        // For negative values, check via unsigned wrapping arithmetic
+        // -val in unsigned domain; if it wraps, the value is too negative
+        auto unsigned_abs = static_cast<typename BasicJsonType::number_unsigned_t>(-val);
+        if (unsigned_abs >= static_cast<typename BasicJsonType::number_unsigned_t>(max_exact))
+        {
+            return false;
+        }
+    }
+
+    // For values within the exact range, verify the round-trip
+    const auto f = static_cast<number_float_t>(val);
+    return std::isfinite(f) && static_cast<number_integer_t>(f) == val;
+}
+
 /*!
 @brief hash a JSON value
 
 The hash function tries to rely on std::hash where possible. Furthermore, the
 type of the JSON value is taken into account to have different hash values for
-null, 0, 0U, and false, etc.
+most types. However, numeric types (number_integer, number_unsigned, number_float)
+are hashed to satisfy the std::hash contract: if two json values compare equal,
+they must have equal hash values. This means json(42), json(42u), and json(42.0)
+all hash to the same value (since they compare equal). For large integer values
+outside the exact representable range of the float type, integer values are hashed
+in their own domain to avoid precision loss.
 
 @tparam BasicJsonType basic_json specialization
 @param j JSON value to hash
@@ -6758,20 +6814,47 @@ std::size_t hash(const BasicJsonType& j)
 
         case BasicJsonType::value_t::number_integer:
         {
-            const auto h = std::hash<number_integer_t> {}(j.template get<number_integer_t>());
+            const auto v = j.template get<number_integer_t>();
-            return combine(type, h);
+            // Use a shared numeric type tag so all numeric types that are equal hash the same
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+
+            if (is_exactly_representable_as_float<BasicJsonType>(v))
+            {
+                const auto h = std::hash<number_float_t> {}(static_cast<number_float_t>(v));
+                return combine(numeric_type, h);
+            }
+            else
+            {
+                const auto h = std::hash<number_integer_t> {}(v);
+                return combine(numeric_type, h);
+            }
         }
 
         case BasicJsonType::value_t::number_unsigned:
         {
-            const auto h = std::hash<number_unsigned_t> {}(j.template get<number_unsigned_t>());
+            const auto v = j.template get<number_unsigned_t>();
-            return combine(type, h);
+            // Normalize to signed (matching operator== behavior for U-vs-I comparison)
+            const auto v_as_signed = static_cast<number_integer_t>(v);
+            // Use a shared numeric type tag so all numeric types that are equal hash the same
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+
+            if (is_exactly_representable_as_float<BasicJsonType>(v_as_signed))
+            {
+                const auto h = std::hash<number_float_t> {}(static_cast<number_float_t>(v_as_signed));
+                return combine(numeric_type, h);
+            }
+            else
+            {
+                const auto h = std::hash<number_integer_t> {}(v_as_signed);
+                return combine(numeric_type, h);
+            }
         }
 
         case BasicJsonType::value_t::number_float:
         {
             const auto h = std::hash<number_float_t> {}(j.template get<number_float_t>());
-            return combine(type, h);
+            const auto numeric_type = static_cast<std::size_t>(BasicJsonType::value_t::number_float);
+            return combine(numeric_type, h);
         }
 
         case BasicJsonType::value_t::binary:
@@ -19962,18 +20045,12 @@ class serializer
                             {
                                 if (codepoint <= 0xFFFF)
                                 {
-                                    // NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
-                                    static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 7, "\\u%04x",
-                                                                      static_cast<std::uint16_t>(codepoint)));
-                                    bytes += 6;
                                 }
                                 else
                                 {
-                                    // NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
-                                    static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 13, "\\u%04x\\u%04x",
+                                    write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
-                                                                      static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)),
-                                                                      static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu))));
-                                    bytes += 12;
                                 }
                             }
                             else
@@ -20180,6 +20257,32 @@ class serializer
         return result;
     }
 
+    /*!
+     * @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
+     *
+     * Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
+     * string escaping hot path. It writes exactly six characters ('\\', 'u' and
+     * four hex digits) at position @a pos of @a string_buffer via a nibble
+     * lookup table, avoiding the format-string parsing and locale machinery of
+     * `snprintf`. Advances @a pos by the number of bytes written (6).
+     *
+     * @param[in] pos       position in @a string_buffer to write at; there must
+     *                      be at least 6 bytes of headroom
+     * @param[in] codeunit  16-bit value to encode
+     */
+    void write_u_escape(std::size_t& pos, std::uint16_t codeunit) noexcept
+    {
+        JSON_ASSERT(string_buffer.size() - pos >= 6);
+        constexpr const char* nibble_to_hex = "0123456789abcdef";
+        string_buffer[pos + 0] = '\\';
+        string_buffer[pos + 1] = 'u';
+        string_buffer[pos + 2] = nibble_to_hex[(codeunit >> 12u) & 0x0Fu];
+        string_buffer[pos + 3] = nibble_to_hex[(codeunit >> 8u) & 0x0Fu];
+        string_buffer[pos + 4] = nibble_to_hex[(codeunit >> 4u) & 0x0Fu];
+        string_buffer[pos + 5] = nibble_to_hex[codeunit & 0x0Fu];
+        pos += 6;
+    }
+
     // templates to avoid warnings about useless casts
     template <typename NumberType, enable_if_t<std::is_signed<NumberType>::value, int> = 0>
     bool is_negative_number(NumberType x)

tests/src/unit-algorithms.cpp

@@ -232,6 +232,9 @@ TEST_CASE("algorithms")
             // only the first four elements are expected to be sorted, the rest are
             // unspecified by the standard
             const json expected({nullptr, false, true, 3});
+            // std::equal below only bounds-checks the first range; assert the
+            // second range is at least as long to rule out an over-read (CWE-126)
+            CHECK(std::distance(begin(expected), end(expected)) >= 4);
             CHECK(std::equal(j.begin(), j.begin() + 4, begin(expected)));
         }
     }

tests/src/unit-alt-string.cpp

@@ -322,14 +322,12 @@ TEST_CASE("alternative string type")
 
     SECTION("JSON pointer")
     {
-        // conversion from json to alt_json fails to compile (see #3425);
+        // Direct conversion from a json literal to alt_json is not supported due to issue #3425:
-        // attempted fix(*) produces: [[['b','a','r'],['b','a','z']]] (with each char being an integer)
+        // alt_json's string_t (alt_string) is not directly constructible from std::string, so the
-        // (*) disable implicit conversion for json_refs of any basic_json type
+        // cross-basic_json conversion falls back to the array-conversion path, incorrectly representing
-        // alt_json j = R"(
+        // objects as arrays of [key, value] pairs and strings as arrays of character codes.
-        // {
+        // See https://github.com/nlohmann/json/issues/3425 for details.
-        //     "foo": ["bar", "baz"]
+        // Workaround: use alt_json::parse() instead of implicit conversion.
-        // }
-        // )"_json;
         auto j = alt_json::parse(R"({"foo": ["bar", "baz"]})");
 
         CHECK(j.at(alt_json::json_pointer("/foo/0")) == j["foo"][0]);

tests/src/unit-convenience.cpp

@@ -168,6 +168,32 @@ TEST_CASE("convenience functions")
         CHECK_THROWS_WITH_AS(check_escaped("\xC2"), "[json.exception.type_error.316] incomplete UTF-8 string; last byte: 0xC2", json::type_error&);
     }
 
+    SECTION("string escape with ensure_ascii")
+    {
+        // control characters are escaped regardless of ensure_ascii
+        check_escaped("\x01", "\\u0001", true);
+        check_escaped("\x1f", "\\u001f", true);
+
+        // non-ASCII code points in the Basic Multilingual Plane are emitted as
+        // a single lowercase \uXXXX escape (exercises every nibble position)
+        check_escaped("\xC2\x80", "\\u0080", true);         // U+0080
+        check_escaped("\xC3\xBF", "\\u00ff", true);         // U+00FF (ÿ)
+        check_escaped("\xDF\xBF", "\\u07ff", true);         // U+07FF
+        check_escaped("\xE4\xBD\xA0", "\\u4f60", true);     // U+4F60 (你)
+        check_escaped("\xEA\xAF\x8D", "\\uabcd", true);     // U+ABCD
+        check_escaped("\xEF\xBF\xBD", "\\ufffd", true);     // U+FFFD (replacement char, all-f nibbles)
+
+        // code points outside the BMP are emitted as a UTF-16 surrogate pair
+        // of two lowercase \uXXXX escapes
+        check_escaped("\xF0\x90\x80\x80", "\\ud800\\udc00", true); // U+10000 (lowest astral)
+        check_escaped("\xF0\x9F\x98\x80", "\\ud83d\\ude00", true); // U+1F600 (😀)
+        check_escaped("\xF4\x8F\xBF\xBF", "\\udbff\\udfff", true); // U+10FFFF (highest code point)
+
+        // with ensure_ascii disabled, non-ASCII input is passed through verbatim
+        check_escaped("\xE4\xBD\xA0", "\xE4\xBD\xA0", false);
+        check_escaped("\xF0\x9F\x98\x80", "\xF0\x9F\x98\x80", false);
+    }
+
     SECTION("string concat")
     {
         using nlohmann::detail::concat;

tests/src/unit-hash.cpp

@@ -35,10 +35,10 @@ TEST_CASE("hash<nlohmann::json>")
 
     // number
     hashes.insert(std::hash<json> {}(json(0)));
-    hashes.insert(std::hash<json> {}(json(static_cast<unsigned>(0))));
+    hashes.insert(std::hash<json> {}(json(static_cast<unsigned>(0)))); // now same hash as json(0)
+    hashes.insert(std::hash<json> {}(json(0.0)));                       // now same hash as json(0)
 
     hashes.insert(std::hash<json> {}(json(-1)));
-    hashes.insert(std::hash<json> {}(json(0.0)));
     hashes.insert(std::hash<json> {}(json(42.23)));
 
     // array
@@ -60,7 +60,16 @@ TEST_CASE("hash<nlohmann::json>")
     // discarded
     hashes.insert(std::hash<json> {}(json(json::value_t::discarded)));
 
-    CHECK(hashes.size() == 21);
+    // Note: json(0), json(0U), and json(0.0) now hash to the same value
+    // (to satisfy the std::hash contract: equal values must hash equally)
+    // So we expect 19 distinct hashes instead of 21
+    CHECK(hashes.size() == 19);
+
+    // Verify the std::hash contract: equal values must hash equally
+    CHECK(std::hash<json> {}(json(0)) == std::hash<json> {}(json(static_cast<unsigned>(0))));
+    CHECK(std::hash<json> {}(json(0)) == std::hash<json> {}(json(0.0)));
+    CHECK(std::hash<json> {}(json(42)) == std::hash<json> {}(json(42u)));
+    CHECK(std::hash<json> {}(json(42)) == std::hash<json> {}(json(42.0)));
 }
 
 TEST_CASE("hash<nlohmann::ordered_json>")
@@ -84,10 +93,10 @@ TEST_CASE("hash<nlohmann::ordered_json>")
 
     // number
     hashes.insert(std::hash<ordered_json> {}(ordered_json(0)));
-    hashes.insert(std::hash<ordered_json> {}(ordered_json(static_cast<unsigned>(0))));
+    hashes.insert(std::hash<ordered_json> {}(ordered_json(static_cast<unsigned>(0)))); // now same hash as ordered_json(0)
+    hashes.insert(std::hash<ordered_json> {}(ordered_json(0.0)));                       // now same hash as ordered_json(0)
 
     hashes.insert(std::hash<ordered_json> {}(ordered_json(-1)));
-    hashes.insert(std::hash<ordered_json> {}(ordered_json(0.0)));
     hashes.insert(std::hash<ordered_json> {}(ordered_json(42.23)));
 
     // array
@@ -109,5 +118,12 @@ TEST_CASE("hash<nlohmann::ordered_json>")
     // discarded
     hashes.insert(std::hash<ordered_json> {}(ordered_json(ordered_json::value_t::discarded)));
 
-    CHECK(hashes.size() == 21);
+    // Note: ordered_json(0), ordered_json(0U), and ordered_json(0.0) now hash to the same value
+    CHECK(hashes.size() == 19);
+
+    // Verify the std::hash contract for ordered_json as well
+    CHECK(std::hash<ordered_json> {}(ordered_json(0)) == std::hash<ordered_json> {}(ordered_json(static_cast<unsigned>(0))));
+    CHECK(std::hash<ordered_json> {}(ordered_json(0)) == std::hash<ordered_json> {}(ordered_json(0.0)));
+    CHECK(std::hash<ordered_json> {}(ordered_json(42)) == std::hash<ordered_json> {}(ordered_json(42u)));
+    CHECK(std::hash<ordered_json> {}(ordered_json(42)) == std::hash<ordered_json> {}(ordered_json(42.0)));
 }