Amalgamate (#5891)

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

.github/workflows/codeql-analysis.yml

@@ -38,14 +38,14 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/init@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
       with:
         languages: c-cpp
 
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/autobuild@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+      uses: github/codeql-action/analyze@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0

.github/workflows/flawfinder.yml

@@ -47,6 +47,6 @@ jobs:
           output: 'flawfinder_results.sarif'
 
       - name: Upload analysis results to GitHub Security tab
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: ${{github.workspace}}/flawfinder_results.sarif

.github/workflows/json_view_benchmarks.yml

@@ -54,7 +54,7 @@ jobs:
     timeout-minutes: 60
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        uses: step-security/harden-runner@ccd8616d44fd3846e67624a50d5aad6d37bf2d25 # v2.22.1
         with:
           egress-policy: audit
 
@@ -78,7 +78,7 @@ jobs:
       - name: Summary
         run: cat tests/benchmarks/json_view/results/*.md >> "$GITHUB_STEP_SUMMARY"
 
-      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+      - uses: actions/upload-artifact@cf430e030ddbb5b0abf93d22962f4752f3646cd9 # v7.0.2
         with:
           name: json_view-benchmarks-${{ matrix.runner }}-${{ inputs.compiler || 'g++' }}
           path: tests/benchmarks/json_view/results/

.github/workflows/scorecards.yml

@@ -80,6 +80,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: results.sarif

.github/workflows/semgrep.yml

@@ -65,7 +65,7 @@ jobs:
 
       # Upload SARIF file generated in previous step
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@24c54180a607b1449ed407dd24f251e4e9147c8d # v4.38.3
+        uses: github/codeql-action/upload-sarif@6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee # v4.39.0
         with:
           sarif_file: semgrep.sarif
         if: always()

docs/docset/generate_docset.py

@@ -341,13 +341,14 @@ def download(url, docs) -> str:
         raise ValueError(f'not an http(s) URL: {url}')
     req = urllib.request.Request(u.geturl(), headers={'User-Agent': USER_AGENT})
     # (the scheme is checked above)
+    # nosemgrep: python.lang.security.audit.dynamic-urllib-use-detected.dynamic-urllib-use-detected
     with urllib.request.urlopen(req, timeout=20) as r:  # nosec B310
         data = r.read()
         ctype = r.headers.get_content_type()
     path = urllib.parse.unquote(u.path).lstrip('/')
     ext = os.path.splitext(path)[1]
     if u.query or not ext or path.endswith('/'):
-        digest = hashlib.sha1(url.encode(), usedforsecurity=False).hexdigest()[:12]
+        digest = hashlib.sha256(url.encode()).hexdigest()[:12]
         path = os.path.join(os.path.dirname(path), digest + CONTENT_TYPE_EXT.get(ctype, ext or '.bin'))
     rel = os.path.normpath(os.path.join('assets', 'external', u.hostname, path))
     out = os.path.join(docs, rel)

docs/mkdocs/docs/home/architecture.md

@@ -339,6 +339,11 @@ The `serializer` (used by [`dump`](../api/basic_json/dump.md) and [`operator<<`]
 - `output_stream_adapter` writes to a `std::ostream`.
 - `output_string_adapter` appends to a string.
 
+The `binary_writer` does not call an adapter for every byte. The `to_*` functions that return a `std::vector` write
+into the vector through a sink (`output_vector_sink`) that is not virtual. The functions that take an output adapter
+write through a sink (`output_adapter_sink`) that collects the output in a buffer of one kibibyte and passes it to the
+adapter in blocks, so that the adapter is called (and a stream locked) once per block instead of once per value.
+
 ## Value conversion
 
 Values are converted from and to other types with the `JSONSerializer` template parameter. The default,

docs/mkdocs/scripts/mermaid/package-lock.json

@@ -6,7 +6,7 @@
     "": {
       "name": "check-mermaid",
       "dependencies": {
-        "jsdom": "30.1.2",
+        "jsdom": "30.1.3",
         "mermaid": "11.17.2"
       }
     },
@@ -40,9 +40,9 @@
       }
     },
     "node_modules/@asamuzakjp/dom-selector": {
-      "version": "9.2.4",
-      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-9.2.4.tgz",
-      "integrity": "sha512-YnVzxDxLaqL0t7Q4wfcgHZjg55Wm6y5EaO7Bhu3q9J7wq/8iw3PhsnWiOQhYekx4VexnbkgWpTT6n+QIV7kczw==",
+      "version": "10.0.3",
+      "resolved": "https://registry.npmjs.org/@asamuzakjp/dom-selector/-/dom-selector-10.0.3.tgz",
+      "integrity": "sha512-3+777rEPsOOjoy5/sRmIzHnoRDaLpm3XWY2dmWn/N7f/XwDG0bcpnFaKL3X9FYJUbNwLmpcJC1bUYexJRxsFlw==",
       "license": "MIT",
       "dependencies": {
         "bidi-js": "^1.1.0",
@@ -1202,13 +1202,13 @@
       "license": "MIT"
     },
     "node_modules/jsdom": {
-      "version": "30.1.2",
-      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.2.tgz",
-      "integrity": "sha512-0FFE/jE1rppmVfUrJUgxqXjcwolZYIGtAgj1pTussMhNZxIxi7W/PvfWaMNroGi2B36X1IKHbexpZ9DhkoOPiQ==",
+      "version": "30.1.3",
+      "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-30.1.3.tgz",
+      "integrity": "sha512-hQMUPvRgN7KxsfIytDQji7bimuJeRQa6Qo5+iuiZQk5CafeRxLIA10/cG5YCBFNpD9RO3oqIiN4CO1Y44kxqXg==",
       "license": "MIT",
       "dependencies": {
         "@asamuzakjp/css-color": "^7.1.3",
-        "@asamuzakjp/dom-selector": "^9.2.4",
+        "@asamuzakjp/dom-selector": "^10.0.3",
         "@bramus/specificity": "^2.4.2",
         "@csstools/css-syntax-patches-for-csstree": "^1.1.15",
         "@exodus/bytes": "^1.16.0",
@@ -1221,7 +1221,7 @@
         "parse5": "^8.0.1",
         "saxes": "^6.0.0",
         "tough-cookie": "^6.0.2",
-        "undici": "^8.11.2",
+        "undici": "^8.12.1",
         "w3c-xmlserializer": "^6.0.0",
         "webidl-conversions": "^8.0.1",
         "whatwg-mimetype": "^5.0.0",
@@ -1521,9 +1521,9 @@
       }
     },
     "node_modules/undici": {
-      "version": "8.11.2",
-      "resolved": "https://registry.npmjs.org/undici/-/undici-8.11.2.tgz",
-      "integrity": "sha512-u4UB2/IrKdU6lFxumHmmo1a3fCQO5tzQllRorfoRS63txhrB7xTpSn1PftwC4qEHkOaqP95fCWW4lJzwErwzhQ==",
+      "version": "8.12.2",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-8.12.2.tgz",
+      "integrity": "sha512-XtuDWVdqTLr3NAxm2ly9/hU6kUsJOgGh1RASzMBbsw6aWCOaQzHdW+QQDfdERjfJ2V5vL5pRPa4RetO9UfivDg==",
       "license": "MIT",
       "engines": {
         "node": ">=22.19.0"

docs/mkdocs/scripts/mermaid/package.json

@@ -4,7 +4,7 @@
   "description": "Validate the Mermaid diagrams of the documentation (see check_mermaid.mjs)",
   "type": "module",
   "dependencies": {
-    "jsdom": "30.1.2",
+    "jsdom": "30.1.3",
     "mermaid": "11.17.2"
   }
 }

include/nlohmann/detail/conversions/from_json.hpp

@@ -69,12 +69,10 @@ void from_json(const BasicJsonType& j, std::optional<T>& opt)
 }
 #endif // JSON_HAS_CPP_17
 
-// overloads for basic_json template parameters
-template < typename BasicJsonType, typename ArithmeticType,
-           enable_if_t < std::is_arithmetic<ArithmeticType>::value&&
-                         !std::is_same<ArithmeticType, typename BasicJsonType::boolean_t>::value,
-                         int > = 0 >
-void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
+// read a number value of any of the three number types into val;
+// returns false (leaving val untouched) if j is not a number
+template<typename BasicJsonType, typename ArithmeticType>
+bool get_number_value(const BasicJsonType& j, ArithmeticType& val)
 {
     switch (static_cast<value_t>(j))
     {
@@ -85,17 +83,17 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
             const auto* ptr = j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>();
             JSON_ASSERT(ptr != nullptr);
             val = static_cast<ArithmeticType>(*ptr);
-            break;
+            return true;
         }
         case value_t::number_integer:
         {
             val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_integer_t*>());
-            break;
+            return true;
         }
         case value_t::number_float:
         {
             val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_float_t*>());
-            break;
+            return true;
         }
 
         case value_t::null:
@@ -106,7 +104,20 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_must_be("number", j);
+            return false;
+    }
+}
+
+// overloads for basic_json template parameters
+template < typename BasicJsonType, typename ArithmeticType,
+           enable_if_t < std::is_arithmetic<ArithmeticType>::value&&
+                         !std::is_same<ArithmeticType, typename BasicJsonType::boolean_t>::value,
+                         int > = 0 >
+void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
+{
+    if (JSON_HEDLEY_UNLIKELY(!get_number_value(j, val)))
+    {
+        throw_type_must_be("number", j);
     }
 }
 
@@ -256,18 +267,18 @@ auto from_json_array_impl(const BasicJsonType& j, std::array<T, N>& arr,
     }
 }
 
-// reserve() is called through this pair (modeled on from_json_object_reserve)
-// so from_json_array_impl below has a single body for both ConstructibleArrayType
-// that support reserve() and those that don't.
-template<typename ConstructibleArrayType>
-auto from_json_array_reserve(ConstructibleArrayType& arr, typename ConstructibleArrayType::size_type size, priority_tag<1> /*unused*/)
--> decltype(arr.reserve(size), void())
+// reserve() is called through this pair (used for arrays and objects alike)
+// so from_json_array_impl and the object from_json have a single body for both
+// containers that support reserve() and those that don't.
+template<typename ConstructibleContainerType>
+auto reserve_if_possible(ConstructibleContainerType& c, typename ConstructibleContainerType::size_type size, priority_tag<1> /*unused*/)
+-> decltype(c.reserve(size), void())
 {
-    arr.reserve(size);
+    c.reserve(size);
 }
 
-template<typename ConstructibleArrayType>
-void from_json_array_reserve(ConstructibleArrayType& /*arr*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
+template<typename ConstructibleContainerType>
+void reserve_if_possible(ConstructibleContainerType& /*c*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
 {}
 
 // append through push_back() where available; containers without it (such as
@@ -297,7 +308,7 @@ auto from_json_array_impl(const BasicJsonType& j, ConstructibleArrayType& arr, p
 {
     ConstructibleArrayType ret;
     const auto* inner_array = j.template get_ptr<const typename BasicJsonType::array_t*>();
-    from_json_array_reserve(ret, inner_array->size(), priority_tag<1> {});
+    reserve_if_possible(ret, inner_array->size(), priority_tag<1> {});
     for (const auto& elem : *inner_array)
     {
         // get<BasicJsonType>() returns *this, this won't call a from_json
@@ -378,17 +389,6 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
     }
 }
 
-template<typename ConstructibleObjectType>
-auto from_json_object_reserve(ConstructibleObjectType& obj, typename ConstructibleObjectType::size_type size, priority_tag<1> /*unused*/)
--> decltype(obj.reserve(size), void())
-{
-    obj.reserve(size);
-}
-
-template<typename ConstructibleObjectType>
-inline void from_json_object_reserve(ConstructibleObjectType& /*obj*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
-{}
-
 // the keys of the source are sorted for the usual object types, so hinting the
 // end makes every insertion constant-time (for containers that order their keys
 // the same way); containers without emplace_hint() (such as ordered_map) fall
@@ -417,7 +417,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
 
     ConstructibleObjectType ret;
     const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
-    from_json_object_reserve(ret, inner_object->size(), priority_tag<1> {});
+    reserve_if_possible(ret, inner_object->size(), priority_tag<1> {});
     for (const auto& p : *inner_object)
     {
         from_json_object_emplace(ret, p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>(), priority_tag<1> {});
@@ -437,6 +437,10 @@ template < typename BasicJsonType, typename ArithmeticType,
                int > = 0 >
 inline void from_json(const BasicJsonType& j, ArithmeticType& val)
 {
+    // the number cases repeat get_number_value() on purpose: calling it here
+    // changes the inlining of get<T>() in the std::array conversion, which then
+    // runs 2.4x slower (GetArray benchmark, #5891); unlike get_arithmetic_value(),
+    // a boolean is accepted
     switch (static_cast<value_t>(j))
     {
         case value_t::number_unsigned:

include/nlohmann/detail/exceptions.hpp

@@ -66,6 +66,7 @@ enum class exception_id : int
     invalid_string_or_size = 113, ///< a binary input contains an invalid string or size specification
     bson_unsupported_type = 114, ///< a BSON record type is not supported
     invalid_high_precision_number = 115, ///< a UBJSON/BJData high-precision number cannot be parsed
+    invalid_document_image = 116, ///< json_document::load() rejects an image
     // invalid_iterator
     iterators_incompatible = 201, ///< the iterators of a range belong to different values
     iterator_from_other_value = 202, ///< an iterator does not belong to the value it is used with
@@ -100,6 +101,8 @@ enum class exception_id : int
     invalid_utf8 = 316, ///< dump() finds a string that is not valid UTF-8
     type_not_serializable = 317, ///< a value cannot be serialized to the requested binary format
     enum_key_duplicate = 318, ///< an enum-keyed map has two keys that serialize to the same string
+    document_binary_value = 319, ///< a binary value is stored in a json_document
+    document_image_unsupported = 320, ///< a json_document image cannot be saved or loaded (discarded document, big-endian target)
     discarded_value_used = 321, ///< a discarded value is used
     // out_of_range
     array_index_out_of_range = 401, ///< an array index is out of range
@@ -117,6 +120,7 @@ enum class exception_id : int
     patch_remove_parent_not_container = 413, ///< the parent of a JSON Patch 'remove' target is not a container
     patch_move_into_child = 414, ///< a JSON Patch 'move' moves a value into one of its children
     subtype_out_of_range = 415, ///< a binary subtype does not fit into one byte
+    document_too_large = 416, ///< a json_document input, its edit storage, or an image reaches the 32-bit (4 GiB) limit
     // other_error
     internal_error = 500, ///< unreachable code was reached
     patch_test_failed = 501, ///< a JSON Patch 'test' operation failed
@@ -146,6 +150,13 @@ class exception : public std::exception
         return concat("[json.exception.", ename, '.', std::to_string(id_), "] ");
     }
 
+    /// build the message "[json.exception.<ename>.<id>] <diagnostics><what_arg>"
+    template<typename BasicJsonContext>
+    static std::string what_impl(const std::string& ename, int id_, const std::string& what_arg, BasicJsonContext context)
+    {
+        return concat(name(ename, id_), diagnostics(context), what_arg);
+    }
+
     static std::string diagnostics(std::nullptr_t /*leaf_element*/)
     {
         return "";
@@ -158,48 +169,33 @@ class exception : public std::exception
         std::vector<std::string> tokens;
         for (const auto* current = leaf_element; current != nullptr && current->m_parent != nullptr; current = current->m_parent)
         {
-            switch (current->m_parent->type())
+            const auto* parent = current->m_parent;
+            if (parent->is_array())
             {
-                case value_t::array:
+                for (std::size_t i = 0; i < parent->m_data.m_value.array->size(); ++i)
                 {
-                    for (std::size_t i = 0; i < current->m_parent->m_data.m_value.array->size(); ++i)
+                    if (&parent->m_data.m_value.array->operator[](i) == current)
                     {
-                        if (&current->m_parent->m_data.m_value.array->operator[](i) == current)
-                        {
-                            tokens.emplace_back(std::to_string(i));
-                            break;
-                        }
+                        tokens.emplace_back(std::to_string(i));
+                        break;
                     }
-                    break;
                 }
-
-                case value_t::object:
-                {
-                    for (const auto& element : *current->m_parent->m_data.m_value.object)
-                    {
-                        if (&element.second == current)
-                        {
-                            // data() is null-terminated, so a key containing
-                            // a null byte is cut short here rather than
-                            // truncating the whole message at what()
-                            tokens.emplace_back(element.first.data());
-                            break;
-                        }
-                    }
-                    break;
-                }
-
-                case value_t::null: // LCOV_EXCL_LINE
-                case value_t::string: // LCOV_EXCL_LINE
-                case value_t::boolean: // LCOV_EXCL_LINE
-                case value_t::number_integer: // LCOV_EXCL_LINE
-                case value_t::number_unsigned: // LCOV_EXCL_LINE
-                case value_t::number_float: // LCOV_EXCL_LINE
-                case value_t::binary: // LCOV_EXCL_LINE
-                case value_t::discarded: // LCOV_EXCL_LINE
-                default:   // LCOV_EXCL_LINE
-                    break; // LCOV_EXCL_LINE
             }
+            else if (parent->is_object())
+            {
+                for (const auto& element : *parent->m_data.m_value.object)
+                {
+                    if (&element.second == current)
+                    {
+                        // data() is null-terminated, so a key containing
+                        // a null byte is cut short here rather than
+                        // truncating the whole message at what()
+                        tokens.emplace_back(element.first.data());
+                        break;
+                    }
+                }
+            }
+            // all other parent types (primitives) contribute no token
         }
 
         if (tokens.empty())
@@ -315,7 +311,7 @@ class invalid_iterator : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static invalid_iterator create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("invalid_iterator", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("invalid_iterator", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -339,7 +335,7 @@ class type_error : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static type_error create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("type_error", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("type_error", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -362,7 +358,7 @@ class out_of_range : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static out_of_range create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("out_of_range", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("out_of_range", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 
@@ -385,7 +381,7 @@ class other_error : public exception
     template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
     static other_error create(int id_, const std::string& what_arg, BasicJsonContext context)
     {
-        const std::string w = concat(exception::name("other_error", id_), exception::diagnostics(context), what_arg);
+        const std::string w = exception::what_impl("other_error", id_, what_arg, context);
         return {id_, w.c_str()};
     }
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -293,6 +293,40 @@ class binary_reader
         return is_object ? sax->end_object() : sax->end_array();
     }
 
+    /*!
+    @brief close the innermost open container and report whether that
+           completed the value being read
+
+    The value begun by the driver is complete once its container is not
+    inside another one.
+
+    @param[out] value_complete  whether no container is left open
+    @return whether the SAX parser accepted the end event
+    */
+    bool leave_container_and_check(bool& value_complete)
+    {
+        if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+        {
+            return false;
+        }
+        value_complete = container_stack.empty();
+        return true;
+    }
+
+    /*!
+    @brief read an object key and pass it to the SAX parser
+
+    @tparam GetKey  member function that reads the key into a string
+    @param[in,out] key  string the key is read into; cleared first
+    @return whether reading the key and the SAX event succeeded
+    */
+    template<bool (binary_reader::*GetKey)(string_t&)>
+    bool read_object_key(string_t& key)
+    {
+        key.clear();
+        return (this->*GetKey)(key) && sax->key(key);
+    }
+
     //////////
     // BSON //
     //////////
@@ -1064,6 +1098,34 @@ class binary_reader
         return last_byte_error(exception_id::invalid_string_or_size, concat("indefinite-length ", type_name, " is not allowed inside indefinite-length ", type_name, "; last byte: 0x", get_token_string()), context);
     }
 
+    /*!
+    @brief report an object key that is not a string
+
+    @param[in] found  description of what was found instead of a string key
+    @return false
+    */
+    bool unsupported_key_type(const char* found) const
+    {
+        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+    }
+
+    /*!
+    @brief read the length of a CBOR string or byte array and then its bytes
+
+    @tparam NumberType    the type of the length field
+    @tparam ContainerType the destination container (string_t or binary_t)
+    @param[in] context  further context information (for diagnostics)
+    @param[out] result  container the bytes are appended to
+
+    @return whether reading completed
+    */
+    template<typename NumberType, typename ContainerType>
+    bool get_cbor_sized_bytes(const char* context, ContainerType& result)
+    {
+        NumberType len{};
+        return get_number(len) && get_bytes(len, context, result);
+    }
+
     /*!
     @brief reads a definite-length CBOR string
 
@@ -1114,26 +1176,22 @@ class binary_reader
 
             case 0x78: // UTF-8 string (one-byte uint8_t for n follows)
             {
-                std::uint8_t len{};
-                return get_number(len) && get_string(len, result);
+                return get_cbor_sized_bytes<std::uint8_t>("string", result);
             }
 
             case 0x79: // UTF-8 string (two-byte uint16_t for n follow)
             {
-                std::uint16_t len{};
-                return get_number(len) && get_string(len, result);
+                return get_cbor_sized_bytes<std::uint16_t>("string", result);
             }
 
             case 0x7A: // UTF-8 string (four-byte uint32_t for n follow)
             {
-                std::uint32_t len{};
-                return get_number(len) && get_string(len, result);
+                return get_cbor_sized_bytes<std::uint32_t>("string", result);
             }
 
             case 0x7B: // UTF-8 string (eight-byte uint64_t for n follow)
             {
-                std::uint64_t len{};
-                return get_number(len) && get_string(len, result);
+                return get_cbor_sized_bytes<std::uint64_t>("string", result);
             }
 
             default:
@@ -1268,7 +1326,7 @@ class binary_reader
                 break;
         }
 
-        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+        return unsupported_key_type(found);
     }
 
     /*!
@@ -1321,30 +1379,22 @@ class binary_reader
 
             case 0x58: // Binary data (one-byte uint8_t for n follows)
             {
-                std::uint8_t len{};
-                return get_number(len) &&
-                       get_binary(len, result);
+                return get_cbor_sized_bytes<std::uint8_t>("binary", result);
             }
 
             case 0x59: // Binary data (two-byte uint16_t for n follow)
             {
-                std::uint16_t len{};
-                return get_number(len) &&
-                       get_binary(len, result);
+                return get_cbor_sized_bytes<std::uint16_t>("binary", result);
             }
 
             case 0x5A: // Binary data (four-byte uint32_t for n follow)
             {
-                std::uint32_t len{};
-                return get_number(len) &&
-                       get_binary(len, result);
+                return get_cbor_sized_bytes<std::uint32_t>("binary", result);
             }
 
             case 0x5B: // Binary data (eight-byte uint64_t for n follow)
             {
-                std::uint64_t len{};
-                return get_number(len) &&
-                       get_binary(len, result);
+                return get_cbor_sized_bytes<std::uint64_t>("binary", result);
             }
 
             default:
@@ -1559,12 +1609,12 @@ class binary_reader
 
                 if (at_end)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
-                    if (container_stack.empty())
+                    if (value_complete)
                     {
                         return true;
                     }
@@ -1573,8 +1623,7 @@ class binary_reader
 
                 if (top.is_object)
                 {
-                    key.clear();
-                    if (JSON_HEDLEY_UNLIKELY(!get_cbor_object_key(key) || !sax->key(key)))
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_cbor_object_key>(key)))
                     {
                         return false;
                     }
@@ -2045,20 +2094,17 @@ class binary_reader
 
             case 0xD9: // str 8
             {
-                std::uint8_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint8_t>(result, context);
             }
 
             case 0xDA: // str 16
             {
-                std::uint16_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint16_t>(result, context);
             }
 
             case 0xDB: // str 32
             {
-                std::uint32_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint32_t>(result, context);
             }
 
             default:
@@ -2155,7 +2201,7 @@ class binary_reader
                 break;
         }
 
-        return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
+        return unsupported_key_type(found);
     }
 
     /*!
@@ -2300,12 +2346,12 @@ class binary_reader
 
                 if (container_stack.back().remaining == 0)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
-                    if (container_stack.empty())
+                    if (value_complete)
                     {
                         return true;
                     }
@@ -2318,8 +2364,7 @@ class binary_reader
                 if (is_object)
                 {
                     get();
-                    key.clear();
-                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_object_key(key) || !sax->key(key)))
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_msgpack_object_key>(key)))
                     {
                         return false;
                     }
@@ -2503,8 +2548,7 @@ class binary_reader
         {
             case 'U':
             {
-                std::uint8_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint8_t>(result, context);
             }
 
             case 'i':
@@ -2537,8 +2581,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint16_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint16_t>(result, context);
             }
 
             case 'm':
@@ -2547,8 +2590,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint32_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint32_t>(result, context);
             }
 
             case 'M':
@@ -2557,8 +2599,7 @@ class binary_reader
                 {
                     break;
                 }
-                std::uint64_t len{};
-                return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+                return get_string_with_length<std::uint64_t>(result, context);
             }
 
             default:
@@ -3374,12 +3415,12 @@ class binary_reader
 
                 if (at_end)
                 {
-                    if (JSON_HEDLEY_UNLIKELY(!leave_container()))
+                    bool value_complete = false;
+                    if (JSON_HEDLEY_UNLIKELY(!leave_container_and_check(value_complete)))
                     {
                         return false;
                     }
-                    // the value begun here is complete once its container is
-                    if (container_stack.empty())
+                    if (value_complete)
                     {
                         return true;
                     }
@@ -3388,8 +3429,7 @@ class binary_reader
 
                 if (top.is_object)
                 {
-                    key.clear();
-                    if (JSON_HEDLEY_UNLIKELY(!get_bon8_key(key) || !sax->key(key)))
+                    if (JSON_HEDLEY_UNLIKELY(!read_object_key<&binary_reader::get_bon8_key>(key)))
                     {
                         return false;
                     }
@@ -4129,6 +4169,22 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief read a length of type @a NumberType, then a string of that many bytes
+
+    @tparam NumberType  the type of the length field
+    @param[out] result  string the bytes are appended to
+    @param[in] context  further context information (for diagnostics)
+
+    @return whether reading and validating the string succeeded
+    */
+    template<typename NumberType>
+    bool get_string_with_length(string_t& result, const char* context)
+    {
+        NumberType len{};
+        return get_number(len) && get_string(len, result) && check_string_utf8(result, context);
+    }
+
     /*!
     @brief create a byte array by reading bytes from the input
 
@@ -4338,37 +4394,7 @@ class binary_reader
                                   const std::string& context) const
     {
         std::string error_msg = "syntax error while parsing ";
-
-        switch (input_format)
-        {
-            case input_format_t::cbor:
-                error_msg += "CBOR";
-                break;
-
-            case input_format_t::msgpack:
-                error_msg += "MessagePack";
-                break;
-
-            case input_format_t::ubjson:
-                error_msg += "UBJSON";
-                break;
-
-            case input_format_t::bson:
-                error_msg += "BSON";
-                break;
-
-            case input_format_t::bjdata:
-                error_msg += "BJData";
-                break;
-
-            case input_format_t::bon8:
-                error_msg += "BON8";
-                break;
-
-            case input_format_t::json: // LCOV_EXCL_LINE
-            default:            // LCOV_EXCL_LINE
-                JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
-        }
+        error_msg += input_format_name(input_format);
 
         return concat(error_msg, ' ', context, ": ", detail);
     }

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,17 +8,18 @@
 
 #pragma once
 
-#include <algorithm> // count, find, min
+#include <algorithm> // count, find, max, min
 #include <array> // array
 #include <cstddef> // size_t
 #include <cstdint> // uint32_t
 #include <cstring> // strlen
 #include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
 #include <limits> // numeric_limits
+#include <memory> // unique_ptr
 #include <streambuf> // streambuf
 #include <string> // string, char_traits
 #include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
-#include <utility> // pair, declval
+#include <utility> // declval, move, pair
 #include <vector> // vector
 
 #ifndef JSON_NO_IO
@@ -66,12 +67,118 @@ namespace detail
 /// the supported input formats
 enum class input_format_t { json, cbor, msgpack, ubjson, bson, bjdata, bon8 };
 
+/// @return the name of a binary input format, as used in exception messages
+inline const char* input_format_name(const input_format_t format) noexcept
+{
+    switch (format)
+    {
+        case input_format_t::cbor:
+            return "CBOR";
+        case input_format_t::msgpack:
+            return "MessagePack";
+        case input_format_t::ubjson:
+            return "UBJSON";
+        case input_format_t::bson:
+            return "BSON";
+        case input_format_t::bjdata:
+            return "BJData";
+        case input_format_t::bon8:
+            return "BON8";
+        case input_format_t::json: // LCOV_EXCL_LINE
+        default:            // LCOV_EXCL_LINE
+            JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
+            return ""; // LCOV_EXCL_LINE
+    }
+}
+
+/// @return the message of the parse_error thrown or reported for an empty input
+inline const char* empty_input_message() noexcept
+{
+    return "attempting to parse an empty input; check that your input string or stream contains the expected JSON";
+}
+
 ////////////////////
 // input adapters //
 ////////////////////
 
 #ifndef JSON_NO_IO
 /*!
+A growable array of characters for the part of a token that an input adapter
+copied out of its window: unlike std::vector<char>::push_back(), appending a
+character takes no reference to a local, and is a few instructions when there
+is room.
+*/
+class token_carry_buffer
+{
+  public:
+    token_carry_buffer() = default;
+    token_carry_buffer(const token_carry_buffer&) = delete;
+    token_carry_buffer& operator=(const token_carry_buffer&) = delete;
+    token_carry_buffer(token_carry_buffer&& rhs) noexcept
+        : m_data(std::move(rhs.m_data)), m_end(rhs.m_end), m_capacity_end(rhs.m_capacity_end)
+    {
+        rhs.m_end = rhs.m_capacity_end = nullptr;
+    }
+    token_carry_buffer& operator=(token_carry_buffer&&) = delete;
+    ~token_carry_buffer() = default;
+
+    void clear() noexcept
+    {
+        m_end = m_data.get();
+    }
+
+    void push_back(char c)
+    {
+        if (JSON_HEDLEY_UNLIKELY(m_end == m_capacity_end))
+        {
+            grow(1);
+        }
+        *m_end++ = c;
+    }
+
+    void append(const char* first, const char* last)
+    {
+        const auto n = static_cast<std::size_t>(last - first);
+        const auto room = static_cast<std::size_t>(m_capacity_end - m_end);
+        if (n > room)
+        {
+            grow(n);
+        }
+        if (n != 0)
+        {
+            std::memcpy(m_end, first, n);
+        }
+        m_end += n;
+    }
+
+    /// replace the contents of @a out
+    void copy_to(std::vector<char>& out) const
+    {
+        out.assign(m_data.get(), m_end);
+    }
+
+  private:
+    /// make room for @a extra more characters
+    JSON_HEDLEY_NEVER_INLINE void grow(std::size_t extra)
+    {
+        const auto size = static_cast<std::size_t>(m_end - m_data.get());
+        const auto capacity = static_cast<std::size_t>(m_capacity_end - m_data.get());
+        const std::size_t new_capacity = (std::max)(capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity, size + extra);
+        std::unique_ptr<char[]> data(new char[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+        if (size != 0)
+        {
+            std::memcpy(data.get(), m_data.get(), size);
+        }
+        m_data = std::move(data);
+        m_end = m_data.get() + size;
+        m_capacity_end = m_data.get() + new_capacity;
+    }
+
+    std::unique_ptr<char[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
+    char* m_end = nullptr;
+    char* m_capacity_end = nullptr;
+};
+/*!
 Input adapter for stdio file access. This adapter read only 1 byte and do not use any
  buffer. This adapter is a very low level adapter.
 */
@@ -209,6 +316,7 @@ class input_stream_adapter
         , token_segment(rhs.token_segment)
         , current_in_get_area(rhs.current_in_get_area)
         , tracking_token(rhs.tracking_token)
+        , no_get_area(rhs.no_get_area)
 #endif
     {
         rhs.is = nullptr;
@@ -295,37 +403,20 @@ class input_stream_adapter
     std::char_traits<char>::int_type get_character()
     {
 #if !JSON_DISABLE_STREAM_BULK_SCAN
-        // sbumpc() refills the get area if it is exhausted
-        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
-        if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            save_token_segment();
-        }
-#endif
-
-        auto res = sb->sbumpc();
-        // set eof manually, as we don't use the istream interface.
-        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
-        {
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-            current_in_get_area = false;
-#endif
-            is->clear(is->rdstate() | std::ios::eofbit);
-        }
-#if !JSON_DISABLE_STREAM_BULK_SCAN
-        else if (JSON_HEDLEY_UNLIKELY(refill))
-        {
-            // the consumed character is at gptr() - 1, unless the streambuf
-            // has no get area and returned it from uflow()
-            const char* const next = streambuf_access::get_ptr(sb);
-            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
-        }
-        else
+        // the character is in the get area: step over it, as sbumpc() does
+        const char* const next = streambuf_access::get_ptr(sb);
+        if (JSON_HEDLEY_LIKELY(next != streambuf_access::get_end(sb)))
         {
             current_in_get_area = true;
+            streambuf_access::bump(sb, 1);
+            return std::char_traits<char>::to_int_type(*next);
+        }
+        if (no_get_area)
+        {
+            return get_character_no_get_area();
         }
 #endif
-        return res;
+        return get_character_slow();
     }
 #endif
 
@@ -334,6 +425,18 @@ class input_stream_adapter
     {
 #if JSON_PRECISE_STREAM_POSITION
         commit_lookahead();
+#endif
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // the elements are in the get area: copy them, as sgetn() does, but
+        // without the virtual call
+        const char* const first = streambuf_access::get_ptr(sb);
+        const auto available = static_cast<std::size_t>(streambuf_access::get_end(sb) - first);
+        if (JSON_HEDLEY_LIKELY(count * sizeof(T) <= available && count * sizeof(T) <= static_cast<std::size_t>((std::numeric_limits<int>::max)())))
+        {
+            std::memcpy(dest, first, count * sizeof(T));
+            streambuf_access::bump(sb, static_cast<int>(count * sizeof(T)));
+            return count * sizeof(T);
+        }
 #endif
         auto res = static_cast<std::size_t>(sb->sgetn(reinterpret_cast<char*>(dest), static_cast<std::streamsize>(count * sizeof(T))));
         if (JSON_HEDLEY_UNLIKELY(res < count * sizeof(T)))
@@ -421,7 +524,7 @@ class input_stream_adapter
     // last one if @a drop_last.
     void copy_token(std::vector<char>& out, bool drop_last) const
     {
-        out = token_carry;
+        token_carry.copy_to(out);
         if (token_segment != nullptr)
         {
             out.insert(out.end(), token_segment, current_end());
@@ -434,6 +537,47 @@ class input_stream_adapter
 #endif
 
   private:
+#if !JSON_PRECISE_STREAM_POSITION
+    // the get area is exhausted, or there is none
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+    JSON_HEDLEY_NEVER_INLINE
+#endif
+    std::char_traits<char>::int_type get_character_slow()
+    {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        // sbumpc() refills the get area if it is exhausted
+        const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
+        if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            save_token_segment();
+        }
+#endif
+
+        auto res = sb->sbumpc();
+        // set eof manually, as we don't use the istream interface.
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
+        {
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+            current_in_get_area = false;
+#endif
+            is->clear(is->rdstate() | std::ios::eofbit);
+        }
+#if !JSON_DISABLE_STREAM_BULK_SCAN
+        else if (JSON_HEDLEY_UNLIKELY(refill))
+        {
+            // the consumed character is at gptr() - 1, unless the streambuf
+            // has no get area and returned it from uflow()
+            const char* const next = streambuf_access::get_ptr(sb);
+            after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
+        }
+        else
+        {
+            current_in_get_area = true;
+        }
+#endif
+        return res;
+    }
+#endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     // Reads the protected get-area pointers of any std::streambuf. Naming the
     // members through a derived class makes forming the member pointers
@@ -457,6 +601,11 @@ class input_stream_adapter
         {
             (s->*(&streambuf_access::gbump))(n);
         }
+        // sbumpc() for an exhausted get area
+        static std::streambuf::int_type next_character(std::streambuf* s)
+        {
+            return (s->*(&streambuf_access::uflow))();
+        }
     };
 
     // one past the character last returned by get_character(), if that is in
@@ -477,16 +626,53 @@ class input_stream_adapter
     {
         if (token_segment != nullptr)
         {
-            token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
+            token_carry.append(token_segment, streambuf_access::get_end(sb));
             token_segment = nullptr;
         }
     }
 
+#if !JSON_PRECISE_STREAM_POSITION
+    // The streambuf has no get area (e.g., std::cin synchronized with stdio):
+    // every character comes from uflow(), and the token is kept by value.
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area()
+    {
+        // the get area is exhausted, so this is what sbumpc() does
+        const auto res = streambuf_access::next_character(sb);
+        if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof() || streambuf_access::get_end(sb) != nullptr))
+        {
+            return get_character_no_get_area_other(res);
+        }
+        // current_in_get_area is false: only the first character of a get
+        // area, or the end of the input, is read here
+        if (tracking_token)
+        {
+            token_carry.push_back(std::char_traits<char>::to_char_type(res));
+        }
+        return res;
+    }
+
+    // @a res came from uflow() of a streambuf without a get area: it is the
+    // end of the input, or the streambuf has a get area now
+    JSON_HEDLEY_NEVER_INLINE std::char_traits<char>::int_type get_character_no_get_area_other(std::char_traits<char>::int_type res)
+    {
+        if (res == std::char_traits<char>::eof())
+        {
+            current_in_get_area = false;
+            is->clear(is->rdstate() | std::ios::eofbit);
+            return res;
+        }
+        // the consumed character is at gptr() - 1
+        after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_begin(sb));
+        return res;
+    }
+#endif
+
     // character @a c was just read into a new get area (@a in_get_area) or
     // returned without one
     void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
     {
         current_in_get_area = in_get_area;
+        no_get_area = !in_get_area;
         if (!tracking_token)
         {
             return;
@@ -525,13 +711,16 @@ class input_stream_adapter
 #endif
 #if !JSON_DISABLE_STREAM_BULK_SCAN
     /// the part of the current token that was in earlier get areas
-    std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
+    token_carry_buffer token_carry{}; // NOLINT(readability-redundant-member-init)
     /// start of the current token's part in the get area, or nullptr
     const char* token_segment = nullptr;
     /// whether the character last returned by get_character() is in the get area
     bool current_in_get_area = false;
     /// whether a token is tracked at all; the binary readers never start one
     bool tracking_token = false;
+    /// whether the streambuf had no get area when it was last asked for a
+    /// character
+    bool no_get_area = false;
 #endif
 };
 #endif  // JSON_NO_IO
@@ -1109,7 +1298,7 @@ inline file_input_adapter input_adapter(std::FILE* file)
 {
     if (file == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     return file_input_adapter(file);
 }
@@ -1118,7 +1307,7 @@ inline input_stream_adapter input_adapter(std::istream& stream)
 {
     if (stream.rdbuf() == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     return input_stream_adapter(stream);
 }
@@ -1143,7 +1332,7 @@ contiguous_bytes_input_adapter input_adapter(CharT b)
 {
     if (b == nullptr)
     {
-        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
+        JSON_THROW(parse_error::create(exception_id::syntax_error, 0, empty_input_message(), nullptr));
     }
     auto length = std::strlen(reinterpret_cast<const char*>(b));
     const auto* ptr = reinterpret_cast<const char*>(b);

include/nlohmann/detail/input/json_sax.hpp

@@ -315,6 +315,52 @@ struct diagnostic_positions
 };
 #endif
 
+/*!
+@brief error state shared by the DOM-building SAX parsers
+
+Holds whether a parse error occurred and whether errors are thrown, and
+implements the parse_error() and is_errored() members of the SAX interface for
+json_sax_dom_parser and json_sax_dom_callback_parser.
+*/
+class json_sax_dom_error_state
+{
+  public:
+    explicit json_sax_dom_error_state(const bool allow_exceptions_) noexcept
+        : allow_exceptions(allow_exceptions_)
+    {}
+
+    // make class move-only
+    json_sax_dom_error_state(const json_sax_dom_error_state&) = delete;
+    json_sax_dom_error_state(json_sax_dom_error_state&&) = default; // NOLINT(hicpp-noexcept-move,performance-noexcept-move-constructor)
+    json_sax_dom_error_state& operator=(const json_sax_dom_error_state&) = delete;
+    json_sax_dom_error_state& operator=(json_sax_dom_error_state&&) = delete; // the const member prevents assignment
+    ~json_sax_dom_error_state() = default;
+
+    template<class Exception>
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
+                     const Exception& ex)
+    {
+        errored = true;
+        static_cast<void>(ex);
+        if (allow_exceptions)
+        {
+            JSON_THROW(ex);
+        }
+        return false;
+    }
+
+    constexpr bool is_errored() const
+    {
+        return errored;
+    }
+
+  private:
+    /// whether a syntax error occurred
+    bool errored = false;
+    /// whether to throw exceptions in case of errors
+    const bool allow_exceptions = true;
+};
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -329,7 +375,7 @@ constructor contains the parsed value.
 @tparam BasicJsonType  the JSON type
 */
 template<typename BasicJsonType, typename InputAdapterType>
-class json_sax_dom_parser
+class json_sax_dom_parser : public json_sax_dom_error_state
 {
   public:
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -345,7 +391,7 @@ class json_sax_dom_parser
     @param[in] allow_exceptions_  whether parse errors yield exceptions
     */
     explicit json_sax_dom_parser(BasicJsonType& r, const bool allow_exceptions_ = true, lexer_t* lexer_ = nullptr)
-        : root(r), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
+        : json_sax_dom_error_state(allow_exceptions_), root(r), m_lexer_ref(lexer_)
     {}
 
     // make class move-only
@@ -474,24 +520,6 @@ class json_sax_dom_parser
         return true;
     }
 
-    template<class Exception>
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
-                     const Exception& ex)
-    {
-        errored = true;
-        static_cast<void>(ex);
-        if (allow_exceptions)
-        {
-            JSON_THROW(ex);
-        }
-        return false;
-    }
-
-    constexpr bool is_errored() const
-    {
-        return errored;
-    }
-
   private:
 
     /*!
@@ -545,16 +573,12 @@ class json_sax_dom_parser
     std::vector<BasicJsonType*> ref_stack {};
     /// helper to hold the reference for the next object element
     BasicJsonType* object_element = nullptr;
-    /// whether a syntax error occurred
-    bool errored = false;
-    /// whether to throw exceptions in case of errors
-    const bool allow_exceptions = true;
     /// the lexer reference to obtain the current position
     lexer_t* m_lexer_ref = nullptr;
 };
 
 template<typename BasicJsonType, typename InputAdapterType>
-class json_sax_dom_callback_parser
+class json_sax_dom_callback_parser : public json_sax_dom_error_state
 {
   public:
     using number_integer_t = typename BasicJsonType::number_integer_t;
@@ -570,7 +594,7 @@ class json_sax_dom_callback_parser
                                  parser_callback_t cb,
                                  const bool allow_exceptions_ = true,
                                  lexer_t* lexer_ = nullptr)
-        : root(r), callback(std::move(cb)), allow_exceptions(allow_exceptions_), m_lexer_ref(lexer_)
+        : json_sax_dom_error_state(allow_exceptions_), root(r), callback(std::move(cb)), m_lexer_ref(lexer_)
     {
         keep_stack.push_back(true);
     }
@@ -837,24 +861,6 @@ class json_sax_dom_callback_parser
         return true;
     }
 
-    template<class Exception>
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/,
-                     const Exception& ex)
-    {
-        errored = true;
-        static_cast<void>(ex);
-        if (allow_exceptions)
-        {
-            JSON_THROW(ex);
-        }
-        return false;
-    }
-
-    constexpr bool is_errored() const
-    {
-        return errored;
-    }
-
   private:
 
     /// if there is a pending duplicate-key stash entry for this exact slot,
@@ -1096,12 +1102,8 @@ class json_sax_dom_callback_parser
     /// value is later rejected by the callback, instead of erasing the
     /// member entirely
     std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
-    /// whether a syntax error occurred
-    bool errored = false;
     /// callback function
     const parser_callback_t callback = nullptr;
-    /// whether to throw exceptions in case of errors
-    const bool allow_exceptions = true;
     /// a discarded value for the callback
     BasicJsonType discarded = BasicJsonType::value_t::discarded;
     /// the lexer reference to obtain the current position

include/nlohmann/detail/input/lexer.hpp

@@ -656,194 +656,74 @@ class lexer : public lexer_base<BasicJsonType>
 
                 // invalid control characters
                 case 0x00:
-                {
-                    error_message = "invalid string: control character U+0000 (NUL) must be escaped to \\u0000";
-                    return token_type::parse_error;
-                }
-
                 case 0x01:
-                {
-                    error_message = "invalid string: control character U+0001 (SOH) must be escaped to \\u0001";
-                    return token_type::parse_error;
-                }
-
                 case 0x02:
-                {
-                    error_message = "invalid string: control character U+0002 (STX) must be escaped to \\u0002";
-                    return token_type::parse_error;
-                }
-
                 case 0x03:
-                {
-                    error_message = "invalid string: control character U+0003 (ETX) must be escaped to \\u0003";
-                    return token_type::parse_error;
-                }
-
                 case 0x04:
-                {
-                    error_message = "invalid string: control character U+0004 (EOT) must be escaped to \\u0004";
-                    return token_type::parse_error;
-                }
-
                 case 0x05:
-                {
-                    error_message = "invalid string: control character U+0005 (ENQ) must be escaped to \\u0005";
-                    return token_type::parse_error;
-                }
-
                 case 0x06:
-                {
-                    error_message = "invalid string: control character U+0006 (ACK) must be escaped to \\u0006";
-                    return token_type::parse_error;
-                }
-
                 case 0x07:
-                {
-                    error_message = "invalid string: control character U+0007 (BEL) must be escaped to \\u0007";
-                    return token_type::parse_error;
-                }
-
                 case 0x08:
-                {
-                    error_message = "invalid string: control character U+0008 (BS) must be escaped to \\u0008 or \\b";
-                    return token_type::parse_error;
-                }
-
                 case 0x09:
-                {
-                    error_message = "invalid string: control character U+0009 (HT) must be escaped to \\u0009 or \\t";
-                    return token_type::parse_error;
-                }
-
                 case 0x0A:
-                {
-                    error_message = "invalid string: control character U+000A (LF) must be escaped to \\u000A or \\n";
-                    return token_type::parse_error;
-                }
-
                 case 0x0B:
-                {
-                    error_message = "invalid string: control character U+000B (VT) must be escaped to \\u000B";
-                    return token_type::parse_error;
-                }
-
                 case 0x0C:
-                {
-                    error_message = "invalid string: control character U+000C (FF) must be escaped to \\u000C or \\f";
-                    return token_type::parse_error;
-                }
-
                 case 0x0D:
-                {
-                    error_message = "invalid string: control character U+000D (CR) must be escaped to \\u000D or \\r";
-                    return token_type::parse_error;
-                }
-
                 case 0x0E:
-                {
-                    error_message = "invalid string: control character U+000E (SO) must be escaped to \\u000E";
-                    return token_type::parse_error;
-                }
-
                 case 0x0F:
-                {
-                    error_message = "invalid string: control character U+000F (SI) must be escaped to \\u000F";
-                    return token_type::parse_error;
-                }
-
                 case 0x10:
-                {
-                    error_message = "invalid string: control character U+0010 (DLE) must be escaped to \\u0010";
-                    return token_type::parse_error;
-                }
-
                 case 0x11:
-                {
-                    error_message = "invalid string: control character U+0011 (DC1) must be escaped to \\u0011";
-                    return token_type::parse_error;
-                }
-
                 case 0x12:
-                {
-                    error_message = "invalid string: control character U+0012 (DC2) must be escaped to \\u0012";
-                    return token_type::parse_error;
-                }
-
                 case 0x13:
-                {
-                    error_message = "invalid string: control character U+0013 (DC3) must be escaped to \\u0013";
-                    return token_type::parse_error;
-                }
-
                 case 0x14:
-                {
-                    error_message = "invalid string: control character U+0014 (DC4) must be escaped to \\u0014";
-                    return token_type::parse_error;
-                }
-
                 case 0x15:
-                {
-                    error_message = "invalid string: control character U+0015 (NAK) must be escaped to \\u0015";
-                    return token_type::parse_error;
-                }
-
                 case 0x16:
-                {
-                    error_message = "invalid string: control character U+0016 (SYN) must be escaped to \\u0016";
-                    return token_type::parse_error;
-                }
-
                 case 0x17:
-                {
-                    error_message = "invalid string: control character U+0017 (ETB) must be escaped to \\u0017";
-                    return token_type::parse_error;
-                }
-
                 case 0x18:
-                {
-                    error_message = "invalid string: control character U+0018 (CAN) must be escaped to \\u0018";
-                    return token_type::parse_error;
-                }
-
                 case 0x19:
-                {
-                    error_message = "invalid string: control character U+0019 (EM) must be escaped to \\u0019";
-                    return token_type::parse_error;
-                }
-
                 case 0x1A:
-                {
-                    error_message = "invalid string: control character U+001A (SUB) must be escaped to \\u001A";
-                    return token_type::parse_error;
-                }
-
                 case 0x1B:
-                {
-                    error_message = "invalid string: control character U+001B (ESC) must be escaped to \\u001B";
-                    return token_type::parse_error;
-                }
-
                 case 0x1C:
-                {
-                    error_message = "invalid string: control character U+001C (FS) must be escaped to \\u001C";
-                    return token_type::parse_error;
-                }
-
                 case 0x1D:
-                {
-                    error_message = "invalid string: control character U+001D (GS) must be escaped to \\u001D";
-                    return token_type::parse_error;
-                }
-
                 case 0x1E:
-                {
-                    error_message = "invalid string: control character U+001E (RS) must be escaped to \\u001E";
-                    return token_type::parse_error;
-                }
-
                 case 0x1F:
                 {
-                    error_message = "invalid string: control character U+001F (US) must be escaped to \\u001F";
+                    static const char* const control_character_messages[32] = // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
+                    {
+                        "invalid string: control character U+0000 (NUL) must be escaped to \\u0000",
+                        "invalid string: control character U+0001 (SOH) must be escaped to \\u0001",
+                        "invalid string: control character U+0002 (STX) must be escaped to \\u0002",
+                        "invalid string: control character U+0003 (ETX) must be escaped to \\u0003",
+                        "invalid string: control character U+0004 (EOT) must be escaped to \\u0004",
+                        "invalid string: control character U+0005 (ENQ) must be escaped to \\u0005",
+                        "invalid string: control character U+0006 (ACK) must be escaped to \\u0006",
+                        "invalid string: control character U+0007 (BEL) must be escaped to \\u0007",
+                        "invalid string: control character U+0008 (BS) must be escaped to \\u0008 or \\b",
+                        "invalid string: control character U+0009 (HT) must be escaped to \\u0009 or \\t",
+                        "invalid string: control character U+000A (LF) must be escaped to \\u000A or \\n",
+                        "invalid string: control character U+000B (VT) must be escaped to \\u000B",
+                        "invalid string: control character U+000C (FF) must be escaped to \\u000C or \\f",
+                        "invalid string: control character U+000D (CR) must be escaped to \\u000D or \\r",
+                        "invalid string: control character U+000E (SO) must be escaped to \\u000E",
+                        "invalid string: control character U+000F (SI) must be escaped to \\u000F",
+                        "invalid string: control character U+0010 (DLE) must be escaped to \\u0010",
+                        "invalid string: control character U+0011 (DC1) must be escaped to \\u0011",
+                        "invalid string: control character U+0012 (DC2) must be escaped to \\u0012",
+                        "invalid string: control character U+0013 (DC3) must be escaped to \\u0013",
+                        "invalid string: control character U+0014 (DC4) must be escaped to \\u0014",
+                        "invalid string: control character U+0015 (NAK) must be escaped to \\u0015",
+                        "invalid string: control character U+0016 (SYN) must be escaped to \\u0016",
+                        "invalid string: control character U+0017 (ETB) must be escaped to \\u0017",
+                        "invalid string: control character U+0018 (CAN) must be escaped to \\u0018",
+                        "invalid string: control character U+0019 (EM) must be escaped to \\u0019",
+                        "invalid string: control character U+001A (SUB) must be escaped to \\u001A",
+                        "invalid string: control character U+001B (ESC) must be escaped to \\u001B",
+                        "invalid string: control character U+001C (FS) must be escaped to \\u001C",
+                        "invalid string: control character U+001D (GS) must be escaped to \\u001D",
+                        "invalid string: control character U+001E (RS) must be escaped to \\u001E",
+                        "invalid string: control character U+001F (US) must be escaped to \\u001F"
+                    };
+                    error_message = control_character_messages[static_cast<std::size_t>(current)];
                     return token_type::parse_error;
                 }
 

include/nlohmann/detail/input/parser.hpp

@@ -165,20 +165,7 @@ class parser
 
         if (result)
         {
-            if (strict)
-            {
-                // strict mode: next byte must be EOF
-                if (get_token() != token_type::end_of_input)
-                {
-                    return syntax_error(*sax, exception_message(token_type::end_of_input, "value"));
-                }
-            }
-            else
-            {
-                // the caller keeps using the input: position it right after
-                // the value by leaving the character that terminated it
-                m_lexer.release_lookahead();
-            }
+            return finish_input(*sax, strict);
         }
 
         return result;
@@ -202,6 +189,39 @@ class parser
         return m_lexer.get_string();
     }
 
+    /*!
+    @brief apply the end-of-input handling after a value was parsed
+
+    In strict mode, the next token must be the end of the input; otherwise
+    parse_error.101 is reported through @a sax. In non-strict mode, the
+    lookahead is released so the caller can keep reading the input right after
+    the parsed value.
+
+    @param[in,out] sax  the SAX parser to report an error to
+    @param[in] strict   whether to expect the last token to be EOF
+    @return true, or what @a sax returned for the error
+    */
+    template<typename SAX>
+    bool finish_input(SAX& sax, const bool strict)
+    {
+        if (strict)
+        {
+            // strict mode: next byte must be EOF
+            if (get_token() != token_type::end_of_input)
+            {
+                return syntax_error(sax, exception_message(token_type::end_of_input, "value"));
+            }
+        }
+        else
+        {
+            // the caller keeps using the input: position it right after
+            // the value by leaving the character that terminated it
+            m_lexer.release_lookahead();
+        }
+
+        return true;
+    }
+
     /*!
     @brief run a DOM SAX parser to completion and position the lexer
 
@@ -221,20 +241,7 @@ class parser
     {
         sax_parse_internal(&sdp);
 
-        if (strict)
-        {
-            // in strict mode, input must be completely read
-            if (get_token() != token_type::end_of_input)
-            {
-                syntax_error(sdp, exception_message(token_type::end_of_input, "value"));
-            }
-        }
-        else
-        {
-            // the caller keeps using the input: position it right after
-            // the value by leaving the character that terminated it
-            m_lexer.release_lookahead();
-        }
+        static_cast<void>(finish_input(sdp, strict));
 
         return !sdp.is_errored();
     }
@@ -404,7 +411,7 @@ class parser
                     {
                         if (JSON_HEDLEY_UNLIKELY(m_lexer.get_chars_read_total() == 1))
                         {
-                            return syntax_error(*sax, "attempting to parse an empty input; check that your input string or stream contains the expected JSON");
+                            return syntax_error(*sax, empty_input_message());
                         }
 
                         return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));

include/nlohmann/detail/input/string_scan.hpp

@@ -96,7 +96,7 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t find_string_special(const unsigned char* d
 // printable ASCII except '"' and '\\' - is emitted unchanged. Note this differs
 // from is_string_special() only in that 0x7F is also a stop (it is escaped as
 // \u007f under ensure_ascii).
-inline bool is_ascii_copyable(unsigned char c) noexcept
+constexpr bool is_ascii_copyable(unsigned char c) noexcept
 {
     return c >= 0x20u && c < 0x7Fu && c != '"' && c != '\\';
 }

include/nlohmann/detail/iterators/iter_impl.hpp

@@ -108,33 +108,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
-            {
-                m_it.object_iterator = typename object_t::iterator();
-                break;
-            }
-
-            case value_t::array:
-            {
-                m_it.array_iterator = typename array_t::iterator();
-                break;
-            }
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator = primitive_iterator_t();
-                break;
-            }
+            m_it.object_iterator = typename object_t::iterator();
+        }
+        else if (m_object->is_array())
+        {
+            m_it.array_iterator = typename array_t::iterator();
+        }
+        else
+        {
+            // primitive (is_primitive(), including discarded)
+            m_it.primitive_iterator = primitive_iterator_t();
         }
     }
 
@@ -249,33 +234,28 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
-            {
-                m_it.object_iterator = m_object->m_data.m_value.object->end();
-                break;
-            }
+            m_it.object_iterator = m_object->m_data.m_value.object->end();
+        }
+        else if (m_object->is_array())
+        {
+            m_it.array_iterator = m_object->m_data.m_value.array->end();
+        }
+        else
+        {
+            // primitive (is_primitive(), including discarded)
+            m_it.primitive_iterator.set_end();
+        }
+    }
 
-            case value_t::array:
-            {
-                m_it.array_iterator = m_object->m_data.m_value.array->end();
-                break;
-            }
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator.set_end();
-                break;
-            }
+    /// @throw invalid_iterator.212 if @a other points to another container
+    template<typename IterImpl>
+    JSON_HEDLEY_ALWAYS_INLINE void check_same_container(const IterImpl& other) const
+    {
+        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
+        {
+            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
         }
     }
 
@@ -424,10 +404,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     bool operator==(const IterImpl& other) const
     {
         // if objects are not the same, the comparison is undefined
-        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
-        {
-            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
-        }
+        check_same_container(other);
 
         // value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
         if (m_object == nullptr)
@@ -466,10 +443,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     bool operator<(const iter_impl& other) const
     {
         // if objects are not the same, the comparison is undefined
-        if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
-        {
-            throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
-        }
+        check_same_container(other);
 
         // value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
         if (m_object == nullptr)
@@ -478,25 +452,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
             return false;
         }
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
-                throw_literal<invalid_iterator>(exception_id::iterator_order_on_object, "cannot compare order of object iterators", m_object);
-
-            case value_t::array:
-                return (m_it.array_iterator < other.m_it.array_iterator);
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return (m_it.primitive_iterator < other.m_it.primitive_iterator);
+            throw_literal<invalid_iterator>(exception_id::iterator_order_on_object, "cannot compare order of object iterators", m_object);
         }
+
+        if (m_object->is_array())
+        {
+            return (m_it.array_iterator < other.m_it.array_iterator);
+        }
+
+        // primitive (is_primitive(), including discarded)
+        return (m_it.primitive_iterator < other.m_it.primitive_iterator);
     }
 
     /*!
@@ -534,30 +501,19 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
-                throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
+            throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
+        }
 
-            case value_t::array:
-            {
-                std::advance(m_it.array_iterator, i);
-                break;
-            }
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-            {
-                m_it.primitive_iterator += i;
-                break;
-            }
+        if (m_object->is_array())
+        {
+            std::advance(m_it.array_iterator, i);
+        }
+        else
+        {
+            // primitive (is_primitive(), including discarded)
+            m_it.primitive_iterator += i;
         }
 
         return *this;
@@ -613,25 +569,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
     {
         JSON_ASSERT(m_object != nullptr);
 
-        switch (m_object->m_data.m_type)
+        if (m_object->is_object())
         {
-            case value_t::object:
-                throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
-
-            case value_t::array:
-                return m_it.array_iterator - other.m_it.array_iterator;
-
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return m_it.primitive_iterator - other.m_it.primitive_iterator;
+            throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
         }
+
+        if (m_object->is_array())
+        {
+            return m_it.array_iterator - other.m_it.array_iterator;
+        }
+
+        // primitive (is_primitive(), including discarded)
+        return m_it.primitive_iterator - other.m_it.primitive_iterator;
     }
 
     /*!

include/nlohmann/detail/iterators/iteration_proxy.hpp

@@ -109,35 +109,25 @@ template<typename IteratorType> class iteration_proxy_value
     {
         JSON_ASSERT(anchor.m_object != nullptr);
 
-        switch (anchor.m_object->type())
+        if (anchor.m_object->is_array())
         {
             // use integer array index as key
-            case value_t::array:
+            if (array_index != array_index_last)
             {
-                if (array_index != array_index_last)
-                {
-                    int_to_string( array_index_str, array_index );
-                    array_index_last = array_index;
-                }
-                return array_index_str;
+                int_to_string( array_index_str, array_index );
+                array_index_last = array_index;
             }
-
-            // use key from the object
-            case value_t::object:
-                return anchor.key();
-
-            // use an empty key for all primitive types
-            case value_t::null:
-            case value_t::string:
-            case value_t::boolean:
-            case value_t::number_integer:
-            case value_t::number_unsigned:
-            case value_t::number_float:
-            case value_t::binary:
-            case value_t::discarded:
-            default:
-                return empty_str;
+            return array_index_str;
         }
+
+        if (anchor.m_object->is_object())
+        {
+            // use key from the object
+            return anchor.key();
+        }
+
+        // use an empty key for all primitive types
+        return empty_str;
     }
 
     /// return value of the iterator

include/nlohmann/detail/output/output_adapters.hpp

@@ -55,6 +55,66 @@ using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
 /// output_vector_sink also appends writes of at least this size with insert()
 constexpr std::size_t max_reserve_size = 256;
 
+/// @brief copy @a length characters, at most 32, without a call of memcpy()
+///
+/// Short strings are the typical payload of a binary value, and a call of
+/// memcpy() costs more than copying them. A copy of 16 to 32 characters is two
+/// possibly overlapping 16-byte copies, one of 8 to 15 two 8-byte copies, and
+/// so on down to a single character; each is a fixed-size load and store.
+/// Nothing outside of [src, src + length) is read or written.
+template<typename CharType>
+inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::true_type /*is_byte*/) noexcept
+{
+    JSON_ASSERT(length <= 32);
+    if (length >= 16)
+    {
+        std::array<char, 16> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 16> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 16);
+        std::memcpy(last.data(), src + (length - 16), 16);
+        std::memcpy(dst, first.data(), 16);
+        std::memcpy(dst + (length - 16), last.data(), 16);
+    }
+    else if (length >= 8)
+    {
+        std::array<char, 8> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 8> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 8);
+        std::memcpy(last.data(), src + (length - 8), 8);
+        std::memcpy(dst, first.data(), 8);
+        std::memcpy(dst + (length - 8), last.data(), 8);
+    }
+    else if (length >= 4)
+    {
+        std::array<char, 4> first; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::array<char, 4> last; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
+        std::memcpy(first.data(), src, 4);
+        std::memcpy(last.data(), src + (length - 4), 4);
+        std::memcpy(dst, first.data(), 4);
+        std::memcpy(dst + (length - 4), last.data(), 4);
+    }
+    else if (length != 0)
+    {
+        // 1 to 3: the first, the middle, and the last character
+        const CharType a = src[0];
+        const CharType b = src[length >> 1];
+        const CharType c = src[length - 1];
+        dst[0] = a;
+        dst[length >> 1] = b;
+        dst[length - 1] = c;
+    }
+}
+
+/// @brief copy @a length characters, of a character type wider than a byte
+template<typename CharType>
+inline void copy_short(CharType* dst, const CharType* src, const std::size_t length, std::false_type /*is_byte*/) noexcept
+{
+    std::memcpy(dst, src, length * sizeof(CharType));
+}
+
+/// the number of characters an empty vector is grown to by output_vector_sink
+constexpr std::size_t min_vector_sink_capacity = 64;
+
 /// @brief non-virtual output sink writing into a std::vector
 ///
 /// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
@@ -78,7 +138,7 @@ class output_vector_sink
 {
   public:
     explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
-        : v(&vec), position(vec.size())
+        : v(&vec), cursor(vec.data() + vec.size()), limit(cursor)
     {}
 
     output_vector_sink(const output_vector_sink&) = delete;
@@ -86,7 +146,7 @@ class output_vector_sink
     output_vector_sink& operator=(output_vector_sink&&) = delete;
 
     output_vector_sink(output_vector_sink&& other) noexcept
-        : v(other.v), position(other.position)
+        : v(other.v), cursor(other.cursor), limit(other.limit)
     {
         other.v = nullptr;
     }
@@ -95,7 +155,7 @@ class output_vector_sink
     {
         if (v != nullptr)
         {
-            v->resize(position);
+            v->resize(position());
         }
     }
 
@@ -104,11 +164,11 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        if (JSON_HEDLEY_UNLIKELY(position == v->size()))
+        if (JSON_HEDLEY_UNLIKELY(cursor == limit))
         {
             grow(1);
         }
-        (*v)[position++] = c;
+        *cursor++ = c;
     }
 
     // no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
@@ -117,7 +177,7 @@ class output_vector_sink
     JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
+        if (JSON_HEDLEY_UNLIKELY(space() < length))
         {
             if (length >= max_reserve_size)
             {
@@ -126,10 +186,15 @@ class output_vector_sink
             }
             grow(length);
         }
-        if (length != 0)
+        if (length <= 32)
         {
-            std::memcpy(v->data() + position, s, length * sizeof(CharType));
-            position += length;
+            copy_short(cursor, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
+            cursor += length;
+        }
+        else
+        {
+            std::memcpy(cursor, s, length * sizeof(CharType));
+            cursor += length;
         }
     }
 
@@ -144,21 +209,37 @@ class output_vector_sink
     CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
+        if (JSON_HEDLEY_UNLIKELY(space() < length))
         {
             grow(length);
         }
-        return v->data() + position;
+        return cursor;
     }
 
     /// keep the first @a length characters written to the space from reserve()
     JSON_HEDLEY_ALWAYS_INLINE
     void commit(const std::size_t length) noexcept
     {
-        position += length;
+        cursor += length;
     }
 
+    /// nothing to pass on: the characters are in the vector (see output_adapter_sink)
+    void flush() noexcept
+    {}
+
   private:
+    /// number of characters of *v written so far
+    std::size_t position() const noexcept
+    {
+        return static_cast<std::size_t>(cursor - v->data());
+    }
+
+    /// number of characters that fit the vector behind the write position
+    std::size_t space() const noexcept
+    {
+        return static_cast<std::size_t>(limit - cursor);
+    }
+
     /// make room for at least @a length more characters after the position;
     /// kept out of line so that the write functions stay small enough for
     /// GCC to inline them into the writer
@@ -166,12 +247,15 @@ class output_vector_sink
     void grow(const std::size_t length)
     {
         // use the capacity the vector already has, else at least double it;
-        // never less than 64 characters, so that a small value does not
+        // never less than min_vector_sink_capacity, so that a small value does not
         // reallocate for every few bytes
-        const std::size_t needed = position + length;
-        v->resize((std::max)(std::size_t{64}, needed <= v->capacity()
+        const std::size_t written = position();
+        const std::size_t needed = written + length;
+        v->resize((std::max)(min_vector_sink_capacity, needed <= v->capacity()
                              ? v->capacity()
                              : (std::max)(needed, v->capacity() * 2)));
+        cursor = v->data() + written;
+        limit = v->data() + v->size();
     }
 
     /// append @a length (at least max_reserve_size) characters that do not fit
@@ -181,20 +265,24 @@ class output_vector_sink
     JSON_HEDLEY_NEVER_INLINE
     void append(const CharType* s, const std::size_t length)
     {
-        v->resize(position);
-        if (v->capacity() - position < length)
+        const std::size_t written = position();
+        v->resize(written);
+        if (v->capacity() - written < length)
         {
             // grow geometrically, with room for the writes that follow, so
             // that the next grow() need not reallocate right away
-            v->reserve((std::max)(v->capacity() * 2, position + length + max_reserve_size));
+            v->reserve((std::max)(v->capacity() * 2, written + length + max_reserve_size));
         }
         v->insert(v->end(), s, s + length);
-        position = v->size();
+        cursor = v->data() + v->size();
+        limit = cursor;
     }
 
     std::vector<CharType, AllocatorType>* v;
-    /// number of characters of *v written so far
-    std::size_t position;
+    /// the write position: in *v, at the number of characters written so far
+    CharType* cursor;
+    /// the end of *v
+    CharType* limit;
 };
 
 /// output adapter for byte vectors
@@ -277,9 +365,17 @@ class output_string_adapter : public output_adapter_protocol<CharType>
 ///
 /// Wraps the polymorphic output_adapter_t so the same binary_writer template can
 /// also target arbitrary adapters (output streams, strings, user-provided
-/// adapters) via the `output_adapter`-based overloads. Each write still goes
-/// through one virtual call, exactly as before; only the concrete sinks above
-/// avoid it.
+/// adapters) via the `output_adapter`-based overloads.
+///
+/// A write through the adapter is a virtual call, and for a stream a call with
+/// a sentry on top, which costs more than encoding the few bytes of most values.
+/// The sink therefore collects what is written in a buffer and passes it on in
+/// one piece when it is full, a write is too large for it, or @ref flush is
+/// called. Everything written reaches the adapter in the same order and with
+/// the same bytes; the destructor passes on what is left, so that a write that
+/// throws leaves the adapter with exactly the bytes written before it. Only
+/// @ref flush can report an error of the adapter (the destructor must not
+/// throw), so it has to be called once the value is written.
 template<typename CharType>
 class output_adapter_sink
 {
@@ -290,36 +386,121 @@ class output_adapter_sink
         JSON_ASSERT(oa);
     }
 
+    output_adapter_sink(const output_adapter_sink&) = delete;
+    output_adapter_sink& operator=(const output_adapter_sink&) = delete;
+    output_adapter_sink& operator=(output_adapter_sink&&) = delete;
+
+    output_adapter_sink(output_adapter_sink&& other) noexcept
+        : oa(std::move(other.oa)), used(other.used)
+    {
+        std::memcpy(buffer.data(), other.buffer.data(), other.used * sizeof(CharType));
+        other.used = 0;
+    }
+
+    ~output_adapter_sink()
+    {
+        // a normal return has flushed already, so this is for a write that threw
+        if (used != 0)
+        {
+            JSON_TRY
+            {
+                flush();
+            }
+            JSON_CATCH(...)
+            {
+                // nothing can be done about an adapter that throws here
+            }
+        }
+    }
+
+    JSON_HEDLEY_ALWAYS_INLINE
     void write_character(CharType c)
     {
-        oa->write_character(c);
+        if (JSON_HEDLEY_UNLIKELY(used == buffer_size))
+        {
+            flush();
+        }
+        buffer[used++] = c;
     }
 
     // no JSON_HEDLEY_NON_NULL: forwards (null, 0) for empty payloads, exactly as
     // the type-erased path already did before this sink existed
+    JSON_HEDLEY_ALWAYS_INLINE
     void write_characters(const CharType* s, std::size_t length)
     {
-        oa->write_characters(s, length);
+        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
+        {
+            write_large(s, length);
+            return;
+        }
+        if (length <= 32)
+        {
+            copy_short(buffer.data() + used, s, length, std::integral_constant<bool, sizeof(CharType) == 1>());
+            used += length;
+        }
+        else
+        {
+            std::memcpy(buffer.data() + used, s, length * sizeof(CharType));
+            used += length;
+        }
     }
 
     /// space for writing up to @a length characters (see
     /// output_vector_sink::reserve)
-    CharType* reserve(const std::size_t length) noexcept
+    JSON_HEDLEY_ALWAYS_INLINE
+    CharType* reserve(const std::size_t length)
     {
         JSON_ASSERT(length <= max_reserve_size);
-        static_cast<void>(length);
-        return reserved.data();
+        if (JSON_HEDLEY_UNLIKELY(buffer_size - used < length))
+        {
+            flush();
+        }
+        return buffer.data() + used;
     }
 
-    /// write the first @a length characters written to the space from reserve()
-    void commit(const std::size_t length)
+    /// keep the first @a length characters written to the space from reserve()
+    JSON_HEDLEY_ALWAYS_INLINE
+    void commit(const std::size_t length) noexcept
     {
-        oa->write_characters(reserved.data(), length);
+        used += length;
+    }
+
+    /// pass everything written so far on to the adapter
+    void flush()
+    {
+        if (used != 0)
+        {
+            // reset first: the characters count as written even if the adapter throws
+            const std::size_t length = used;
+            used = 0;
+            oa->write_characters(buffer.data(), length);
+        }
     }
 
   private:
+    /// a write that does not fit the space left in the buffer
+    JSON_HEDLEY_NEVER_INLINE
+    void write_large(const CharType* s, const std::size_t length)
+    {
+        flush();
+        if (length >= buffer_size)
+        {
+            oa->write_characters(s, length);
+        }
+        else
+        {
+            std::memcpy(buffer.data(), s, length * sizeof(CharType));
+            used = length;
+        }
+    }
+
+    /// large enough for reserve() at any time
+    static constexpr std::size_t buffer_size = 4 * max_reserve_size;
+
     output_adapter_t<CharType> oa;
-    std::array<CharType, max_reserve_size> reserved{};
+    /// number of characters of @ref buffer not yet passed on
+    std::size_t used = 0;
+    std::array<CharType, buffer_size> buffer{};
 };
 
 /// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits

include/nlohmann/detail/string_utils.hpp

@@ -48,6 +48,24 @@ inline std::string hex_byte(const std::uint8_t byte)
     return result;
 }
 
+/*!
+@brief write a UTF-16 code unit as four lowercase hexadecimal digits
+
+The lowercase counterpart of hex_byte(), used for the `\\uXXXX` escapes of the
+serializers, whose output is lowercase. Writes exactly four characters to
+@a out and returns the pointer past them.
+*/
+JSON_HEDLEY_ALWAYS_INLINE char* hex4_lower(const std::uint16_t codeunit, char* out) noexcept
+{
+    constexpr const char* nibble_to_hex = "0123456789abcdef";
+    const unsigned int unit = codeunit;
+    out[0] = nibble_to_hex[(unit >> 12u) & 0x0Fu];
+    out[1] = nibble_to_hex[(unit >> 8u) & 0x0Fu];
+    out[2] = nibble_to_hex[(unit >> 4u) & 0x0Fu];
+    out[3] = nibble_to_hex[unit & 0x0Fu];
+    return out + 4;
+}
+
 ///////////////////
 // UTF-8 encoding //
 ///////////////////
@@ -103,6 +121,66 @@ void encode_utf8(std::uint32_t cp, const Out& out)
     }
 }
 
+/*!
+@brief the shape of a well-formed UTF-8 sequence, by its lead byte
+
+@a length is 1 for ASCII, 2 to 4 for a valid lead byte, and 0 for a byte that
+cannot start a well-formed sequence (a continuation byte, 0xC0, 0xC1, or 0xF5
+to 0xFF). For a multibyte sequence, the second byte must lie in
+[@a second_lo, @a second_hi], and every later byte in [0x80, 0xBF]
+(RFC 3629, section 4; Unicode Table 3-7). The narrower second-byte ranges
+exclude overlong forms (0xE0, 0xF0), surrogates (0xED), and code points
+beyond U+10FFFF (0xF4).
+*/
+struct utf8_sequence_shape
+{
+    std::uint8_t length;
+    std::uint8_t second_lo;
+    std::uint8_t second_hi;
+};
+
+/// @return the shape of a UTF-8 sequence starting with @a lead, see utf8_sequence_shape
+inline utf8_sequence_shape utf8_shape(const std::uint8_t lead) noexcept
+{
+    if (lead < 0x80u)
+    {
+        return {1, 0, 0};
+    }
+    if (lead < 0xC2u)
+    {
+        return {0, 0, 0};
+    }
+    if (lead <= 0xDFu)
+    {
+        return {2, 0x80u, 0xBFu};
+    }
+    if (lead == 0xE0u)
+    {
+        return {3, 0xA0u, 0xBFu};
+    }
+    if (lead == 0xEDu)
+    {
+        return {3, 0x80u, 0x9Fu};
+    }
+    if (lead <= 0xEFu)
+    {
+        return {3, 0x80u, 0xBFu};
+    }
+    if (lead == 0xF0u)
+    {
+        return {4, 0x90u, 0xBFu};
+    }
+    if (lead <= 0xF3u)
+    {
+        return {4, 0x80u, 0xBFu};
+    }
+    if (lead == 0xF4u)
+    {
+        return {4, 0x80u, 0x8Fu};
+    }
+    return {0, 0, 0};
+}
+
 ///////////////////
 // UTF-8 decoding //
 ///////////////////
@@ -118,7 +196,7 @@ This is a single-byte step of a "shift-based" UTF-8 decoder originally
 written by Björn Hoehrmann. See
 http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
 
-The library checks UTF-8 well-formedness (RFC 3629, section 4) in three
+The library checks UTF-8 well-formedness (RFC 3629, section 4) in five
 places, which differ in speed, diagnostics, and how they read the input:
 
 - decode() below: the serializer, to escape and, in strict mode, reject
@@ -132,10 +210,15 @@ places, which differ in speed, diagnostics, and how they read the input:
   bulk string scan, the bulk path of the BON8 reader, and the BON8 writer.
   They must accept exactly what the lexer's switch accepts.
 - the byte path of binary_reader::get_bon8_string(): BON8 input without bulk
-  access, and the bytes the bulk path leaves to it.
+  access, and the bytes the bulk path leaves to it. It keeps its own ranges:
+  taking them from utf8_shape() made BON8 decoding 2-3% slower (#5891).
+- check_utf8() in detail/view/edit.hpp: strings stored in an editable
+  json_document, with the index of the offending byte. It also uses
+  utf8_shape().
 
-All four must accept the same set of sequences, so a change to one needs a
-matching change to the others.
+All five must accept the same set of sequences, which the test "UTF-8
+validators accept the same sequences" in unit-class_lexer.cpp checks
+exhaustively against decode() and utf8_shape().
 
 @param[in,out] state  the current decoder state
 @param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)

include/nlohmann/detail/value_t.hpp

@@ -177,6 +177,35 @@ inline bool owns_memory(const value_t t) noexcept
     }
 }
 
+/*!
+@brief whether a value of the given type is neither an object nor an array
+
+Unlike basic_json::is_primitive(), this includes value_t::discarded: it names
+the types for which iterators, JSON Pointer resolution, and the serializer take
+the "single value" path. Every enumerator is listed so that -Wswitch-enum flags
+this function when a new type is added.
+*/
+inline bool is_primitive(const value_t t) noexcept
+{
+    switch (t)
+    {
+        case value_t::object:
+        case value_t::array:
+            return false;
+
+        case value_t::null:
+        case value_t::string:
+        case value_t::boolean:
+        case value_t::number_integer:
+        case value_t::number_unsigned:
+        case value_t::number_float:
+        case value_t::binary:
+        case value_t::discarded:
+        default:
+            return true;
+    }
+}
+
 
 /*!
 @brief compare an integer with a floating point number without precision loss

include/nlohmann/detail/view/edit.hpp

@@ -51,11 +51,6 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 inline void check_utf8(const char* s, std::size_t n)
 {
     const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const auto hex = [](unsigned char c)
-    {
-        constexpr const char* digits = "0123456789ABCDEF";
-        return std::string{digits[c >> 4u], digits[c & 0xFu]};
-    };
     for (std::size_t i = 0; i < n;)
     {
         const unsigned char c = p[i];
@@ -64,39 +59,22 @@ inline void check_utf8(const char* s, std::size_t n)
             ++i;
             continue;
         }
-        std::size_t len = 0;
-        unsigned char lo = 0x80;
-        unsigned char hi = 0xBF;
-        if (c >= 0xC2 && c <= 0xDF)
+        const utf8_sequence_shape shape = utf8_shape(c);
+        const std::size_t len = shape.length;
+        if (len == 0)
         {
-            len = 2;
-        }
-        else if (c >= 0xE0 && c <= 0xEF)
-        {
-            len = 3;
-            lo = c == 0xE0 ? 0xA0 : 0x80;
-            hi = c == 0xED ? 0x9F : 0xBF;
-        }
-        else if (c >= 0xF0 && c <= 0xF4)
-        {
-            len = 4;
-            lo = c == 0xF0 ? 0x90 : 0x80;
-            hi = c == 0xF4 ? 0x8F : 0xBF;
-        }
-        else
-        {
-            throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex(c)));
+            throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_byte(c)));
         }
         for (std::size_t k = 1; k < len; ++k)
         {
             if (i + k == n)
             {
-                throw_type_error(316, concat("incomplete UTF-8 string; last byte: 0x", hex(p[n - 1])));
+                throw_type_error(exception_id::invalid_utf8, concat("incomplete UTF-8 string; last byte: 0x", hex_byte(p[n - 1])));
             }
             const unsigned char b = p[i + k];
-            if (b < (k == 1 ? lo : 0x80) || b > (k == 1 ? hi : 0xBF))
+            if (b < (k == 1 ? shape.second_lo : 0x80) || b > (k == 1 ? shape.second_hi : 0xBF))
             {
-                throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex(b)));
+                throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex_byte(b)));
             }
         }
         i += len;
@@ -144,7 +122,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object) && o->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(305, "cannot use operator[] with a string argument with ", object.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", object.type_name());
         }
         check_utf8(key.data(), key.size());
         const encoded e = encode(std::forward<V>(value));
@@ -195,7 +173,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(305, "cannot use operator[] with a numeric argument with ", array.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", array.type_name());
         }
         check_index(idx, a->len);
         const encoded e = encode(std::forward<V>(value));
@@ -212,7 +190,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array) && a->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(308, "cannot use push_back() with ", array.type_name());
+            throw_type_error(exception_id::push_back_wrong_type, "cannot use push_back() with ", array.type_name());
         }
         const encoded e = encode(std::forward<V>(value));
         if (a->kind == static_cast<std::uint8_t>(value_t::null))
@@ -236,7 +214,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(309, "cannot use insert() with ", array.type_name());
+            throw_type_error(exception_id::insert_wrong_type, "cannot use insert() with ", array.type_name());
         }
         check_index(idx, a->len + 1);
         const encoded e = encode(std::forward<V>(value));
@@ -256,7 +234,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object))
         {
-            throw_type_error(307, "cannot use erase() with ", object.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", object.type_name());
         }
         for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
         {
@@ -274,7 +252,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(307, "cannot use erase() with ", array.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", array.type_name());
         }
         check_index(idx, a->len);
         node* const h = block_of(m_doc, a, 0);
@@ -297,7 +275,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_doc != &m_doc || v.m_node == nullptr))
         {
-            throw_invalid_iterator(202, "view does not belong to this document");
+            throw_invalid_iterator(exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         edit_state_of(m_doc);
         return const_cast<node*>(v.m_node); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
@@ -307,7 +285,7 @@ class editor
     {
         if (idx >= limit)
         {
-            throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+            throw_array_index_out_of_range(idx);
         }
     }
 
@@ -448,7 +426,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_node == nullptr))
         {
-            throw_type_error(302, "type must be a value, but is ", "discarded");
+            throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
         encoded r;
         if (!is_container(*v.m_node))
@@ -598,7 +576,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(len >= 0xFFFFFFFFu))
         {
-            throw_out_of_range(416, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::document_too_large, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
         }
         node n = plain_node(value_t::string);
         n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
@@ -673,12 +651,12 @@ class editor
                 return string_node(s.data(), s.size());
             }
             case value_t::binary:
-                throw_type_error(319, "cannot store a binary value in a json_document", "");
+                throw_type_error(exception_id::document_binary_value, "cannot store a binary value in a json_document", "");
             case value_t::discarded:
             case value_t::object:
             case value_t::array:
             default:
-                throw_type_error(302, "type must be a value, but is ", "discarded");
+                throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
     }
 

include/nlohmann/detail/view/edit_storage.hpp

@@ -84,7 +84,7 @@ inline std::size_t text_capacity(std::size_t cap, std::size_t used, std::size_t
     constexpr std::size_t limit = 0xFFFFFFFFu;
     if (NLOHMANN_VIEW_UNLIKELY(used > limit || n > limit - used))
     {
-        throw_out_of_range(416, "edits of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "edits of 4 GiB or more are not supported by json_document");
     }
     const std::size_t needed = used + n;
     const std::size_t wanted = needed + (std::min)(limit - needed, std::size_t{256});
@@ -135,7 +135,7 @@ inline void reserve_moved(document_data& d)
     document_data::edit_state& e = edit_state_of(d);
     if (e.moved.size() >= 0xFFFFFFFFu)
     {
-        throw_out_of_range(416, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
+        throw_out_of_range(exception_id::document_too_large, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
     }
     if (e.moved.size() == e.moved.capacity() || e.moved_cap.size() == e.moved_cap.capacity())
     {

include/nlohmann/detail/view/errors.hpp

@@ -25,32 +25,52 @@ namespace view
 // Exceptions are thrown out of line, so that the accessors that may throw stay
 // small enough to be inlined.
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const char* prefix, const char* type)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const char* prefix, const char* type)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, concat(prefix, type), nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(out_of_range::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(int id, const char* msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(exception_id id, const char* msg)
 {
     NLOHMANN_VIEW_THROW(invalid_iterator::create(id, msg, nullptr));
 }
 
 /// a parse error without a position (as those of json_pointer)
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(parse_error::create(id, 0, msg, nullptr));
 }
 
+/// out_of_range.401: the array index @a idx is not below the size
+template<typename Index>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_array_index_out_of_range(const Index idx)
+{
+    throw_out_of_range(exception_id::array_index_out_of_range, concat("array index ", std::to_string(idx), " is out of range"));
+}
+
+/// out_of_range.402: the JSON Pointer token '-' of an array of @a size elements
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_array_index_past_end(std::size_t size)
+{
+    throw_out_of_range(exception_id::pointer_past_the_end_index, concat("array index '-' (", std::to_string(size), ") is out of range"));
+}
+
+/// out_of_range.403: the object has no member @a key
+template<typename Key>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_key_not_found(const Key& key)
+{
+    throw_out_of_range(exception_id::key_not_found, concat("key '", key, "' not found"));
+}
+
 /// SAX handler of the error replay: accepts every event without storing it,
 /// and throws the exception the parser reports
 template<typename BasicJsonType>
@@ -149,7 +169,7 @@ template<typename BasicJsonType>
     if (f.code == error_code::input_too_large)
     {
         // (the limit is detail::view::max_input_size(): 4 GiB minus 16 bytes)
-        NLOHMANN_VIEW_THROW(out_of_range::create(416, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
+        NLOHMANN_VIEW_THROW(out_of_range::create(exception_id::document_too_large, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
     }
     throwing_sax<BasicJsonType> sax;
     const bool accepted = BasicJsonType::sax_parse(src, src + size, &sax, input_format_t::json, true, ignore_comments, ignore_trailing_commas);
@@ -169,7 +189,7 @@ template<typename BasicJsonType>
         }
     }
     pos.chars_read_current_line = off + 1 - line_start;
-    NLOHMANN_VIEW_THROW(parse_error::create(101, pos, "syntax error while parsing value", nullptr));
+    NLOHMANN_VIEW_THROW(parse_error::create(exception_id::syntax_error, pos, "syntax error while parsing value", nullptr));
     // LCOV_EXCL_STOP
 }
 

include/nlohmann/detail/view/image.hpp

@@ -186,7 +186,7 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
 inline std::vector<std::uint8_t> save_image(const document_data& d)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     const std::size_t arena_size = d.arena_size;
     std::vector<node> compacted;
@@ -203,7 +203,7 @@ inline std::vector<std::uint8_t> save_image(const document_data& d)
     if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
     {
         // LCOV_EXCL_START (4 GiB)
-        throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "images of 4 GiB or more are not supported by json_document");
         // LCOV_EXCL_STOP
     }
     image_header h{};
@@ -660,7 +660,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 
 [[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
 {
-    throw_parse_error(116, concat("invalid json_document image: ", what));
+    throw_parse_error(exception_id::invalid_document_image, concat("invalid json_document image: ", what));
 }
 
 /// Read an image into d. The text and the decoded strings stay in the image;
@@ -668,7 +668,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     if (image == nullptr || size < sizeof(image_header))
     {

include/nlohmann/detail/view/iterator.hpp

@@ -110,7 +110,7 @@ class view_iterator
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_value_offset == 0))
         {
-            throw_invalid_iterator(207, "cannot use key() for non-object iterators");
+            throw_invalid_iterator(exception_id::iterator_key_not_object, "cannot use key() for non-object iterators");
         }
         return string_view_t(m_doc->str(*m_pos), m_pos->len);
     }

include/nlohmann/detail/view/pointer.hpp

@@ -32,51 +32,15 @@ enum class pointer_mode
     contains,  ///< as basic_json::contains(): no exceptions at all
 };
 
-/// the outcome of reading an array index from a reference token
-enum class index_status
-{
-    ok,
-    leading_zero, ///< parse_error.106
-    not_number,   ///< parse_error.109
-    unresolved,   ///< out_of_range.404
-    too_large,    ///< out_of_range.410
-};
+/// the outcome of reading an array index: detail::parse_array_index(), shared with json_pointer
+using index_status = detail::array_index_status;
 
 /// reads an array index like json_pointer::array_index (RFC 6901, Sect. 4),
 /// but reports errors instead of throwing them
 template<typename StringType>
 index_status array_index(const StringType& s, std::size_t& idx) noexcept
 {
-    // as basic_json: the empty token and "-" (past the last element) are
-    // unresolved rather than not a number
-    if (s.empty() || (s.size() == 1 && s[0] == '-'))
-    {
-        return index_status::unresolved;
-    }
-    if (s[0] < '0' || s[0] > '9')
-    {
-        return index_status::not_number;
-    }
-    if (s.size() > 1 && s[0] == '0')
-    {
-        return index_status::leading_zero;
-    }
-    std::uint64_t v = 0;
-    for (const auto c : s)
-    {
-        const auto d = static_cast<unsigned>(static_cast<unsigned char>(c)) - '0';
-        if (d > 9 || v > ((std::numeric_limits<std::uint64_t>::max)() - d) / 10)
-        {
-            return index_status::unresolved; // not a number, or beyond unsigned long long
-        }
-        v = (v * 10) + d;
-    }
-    if (v >= (std::numeric_limits<std::size_t>::max)()) // (std::size_t converts to std::uint64_t implicitly)
-    {
-        return index_status::too_large;
-    }
-    idx = static_cast<std::size_t>(v);
-    return index_status::ok;
+    return detail::parse_array_index(s, idx);
 }
 
 /// throws the exception json_pointer::array_index throws for this status
@@ -86,15 +50,15 @@ template<typename StringType>
     switch (status)
     {
         case index_status::leading_zero:
-            throw_parse_error(106, concat("array index '", s, "' must not begin with '0'"));
-        case index_status::not_number:
-            throw_parse_error(109, concat("array index '", s, "' is not a number"));
-        case index_status::too_large:
-            throw_out_of_range(410, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
+            throw_parse_error(exception_id::pointer_index_leading_zero, concat("array index '", s, "' must not begin with '0'"));
+        case index_status::not_a_number:
+            throw_parse_error(exception_id::pointer_index_not_a_number, concat("array index '", s, "' is not a number"));
+        case index_status::exceeds_size_type:
+            throw_out_of_range(exception_id::value_out_of_range, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
         case index_status::unresolved:
         case index_status::ok:
         default:
-            throw_out_of_range(404, concat("unresolved reference token '", s, "'"));
+            throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", s, "'"));
     }
 }
 
@@ -119,7 +83,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(403, concat("key '", token, "' not found"));
+                    throw_key_not_found(token);
                 }
                 return View();
             }
@@ -131,7 +95,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (throwing)
                 {
-                    throw_out_of_range(402, concat("array index '-' (", std::to_string(cur.size()), ") is out of range"));
+                    throw_array_index_past_end(cur.size());
                 }
                 return View();
             }
@@ -139,7 +103,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             const index_status status = array_index(token, idx);
             if (status != index_status::ok)
             {
-                const bool parse_error = status == index_status::leading_zero || status == index_status::not_number;
+                const bool parse_error = status == index_status::leading_zero || status == index_status::not_a_number;
                 if (throwing || (mode == pointer_mode::value && parse_error))
                 {
                     throw_array_index_error(status, token);
@@ -150,7 +114,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+                    throw_array_index_out_of_range(idx);
                 }
                 return View();
             }
@@ -160,7 +124,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
         {
             if (throwing)
             {
-                throw_out_of_range(404, concat("unresolved reference token '", token, "'"));
+                throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", token, "'"));
             }
             return View();
         }

include/nlohmann/detail/view/serializer.hpp

@@ -890,21 +890,17 @@ class view_serializer
             m_out.put("null");
             return;
         }
-        static constexpr bool is_ieee_single_or_double
-            = std::numeric_limits<number_float_t>::is_iec559
-              && ((std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
-                  || (std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024));
-        write_float(x, std::integral_constant<bool, is_ieee_single_or_double>());
+        write_float(x, std::integral_constant<bool, ::nlohmann::detail::has_native_float_format<number_float_t>::value>());
     }
 
-    void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::true_type /*has_native_float_format*/)
     {
         std::array<char, 64> buf{};
         const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
         m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
     }
 
-    void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::false_type /*has_native_float_format*/)
     {
         // other types (e.g. long double) are rare: the library writes them
         const string_t s = BasicJsonType(x).dump();
@@ -1031,8 +1027,8 @@ class view_serializer
 
     void write_u_escape(std::uint32_t u)
     {
-        static constexpr const char* hex = "0123456789abcdef";
-        const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
+        std::array<char, 6> e = {{'\\', 'u', 0, 0, 0, 0}};
+        hex4_lower(static_cast<std::uint16_t>(u), &e[2]);
         m_out.put(e.data(), e.size());
     }
 

include/nlohmann/detail/view/value.hpp

@@ -60,7 +60,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_error(302, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
+            throw_type_error(exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
     }
 }
 
@@ -70,7 +70,7 @@ std::vector<U, A> vector_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_array()))
     {
-        throw_type_error(302, "type must be array, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be array, but is ", v.type_name());
     }
     std::vector<U, A> r;
     r.reserve(v.size());
@@ -88,7 +88,7 @@ Map map_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_object()))
     {
-        throw_type_error(302, "type must be object, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be object, but is ", v.type_name());
     }
     Map r;
     for (auto it = v.begin(); it != v.end(); ++it)

include/nlohmann/json_view.hpp

@@ -267,7 +267,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a string argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", type_name());
         }
         return lookup(key);
     }
@@ -293,7 +293,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", type_name());
         }
         return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
@@ -326,12 +326,12 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         if (NLOHMANN_VIEW_UNLIKELY(r.is_discarded()))
         {
-            detail::view::throw_out_of_range(403, detail::concat("key '", std::string(key.data(), key.size()), "' not found"));
+            detail::view::throw_key_not_found(std::string(key.data(), key.size()));
         }
         return r;
     }
@@ -352,11 +352,11 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_array()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         if (NLOHMANN_VIEW_UNLIKELY(idx >= m_node->len))
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
@@ -384,7 +384,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -403,7 +403,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -421,7 +421,7 @@ class basic_json_view
         const iterator it = begin();
         if (NLOHMANN_VIEW_UNLIKELY(it == end()))
         {
-            detail::view::throw_invalid_iterator(214, "cannot get value");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_value_unavailable, "cannot get value");
         }
         return *it;
     }
@@ -573,7 +573,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_string()))
         {
-            detail::view::throw_type_error(302, "type must be string, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be string, but is ", type_name());
         }
         return {m_doc->str(*m_node), m_node->len};
     }
@@ -585,7 +585,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_number()))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return {m_doc->str(*m_node), detail::view::number_length(*m_node)};
     }
@@ -795,7 +795,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_boolean()))
         {
-            detail::view::throw_type_error(302, "type must be boolean, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be boolean, but is ", type_name());
         }
         return (m_node->flags & detail::view::node_flags::is_true) != 0;
     }
@@ -805,7 +805,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_node == nullptr))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return detail::view::arithmetic_value<T, BasicJsonType>(*m_doc, *m_node);
     }
@@ -814,7 +814,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_null()))
         {
-            detail::view::throw_type_error(302, "type must be null, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be null, but is ", type_name());
         }
         return nullptr;
     }
@@ -1123,7 +1123,7 @@ class basic_json_document
     {
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_type_error(320, "cannot save a discarded json_document");
+            detail::view::throw_type_error(detail::exception_id::document_image_unsupported, "cannot save a discarded json_document");
         }
         return detail::view::save_image(*m_data);
     }
@@ -1224,7 +1224,7 @@ class basic_json_document
                 const std::size_t idx = pointer_index(token);
                 if (idx >= 0xFFFFFFFFu)
                 {
-                    detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+                    detail::view::throw_array_index_out_of_range(idx);
                 }
                 for (std::size_t i = 0; i < idx; ++i)
                 {
@@ -1280,7 +1280,7 @@ class basic_json_document
     {
         if (ptr.empty())
         {
-            detail::view::throw_out_of_range(405, "JSON pointer has no parent");
+            detail::view::throw_out_of_range(detail::exception_id::patch_on_root, "JSON pointer has no parent");
         }
         const view_type parent = root().at(ptr.parent_pointer());
         const auto& token = ptr.back();
@@ -1300,7 +1300,7 @@ class basic_json_document
         static_assert(Editable, "only an editable document can be edited: use basic_json_document<BasicJsonType, true> (json_editable_document)");
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_invalid_iterator(202, "view does not belong to this document");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         return detail::view::editor<BasicJsonType, view_type>(*m_data);
     }
@@ -1317,7 +1317,7 @@ class basic_json_document
     {
         if (idx < 0)
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return static_cast<std::size_t>(idx);
     }

include/nlohmann/ordered_map.hpp

@@ -125,6 +125,19 @@ private:
         Container::pop_back();
     }
 
+    /// @brief remove the entry with the given key; returns the number of removed entries
+    template<class K>
+    size_type erase_impl(const K& key)
+    {
+        const auto it = find_impl(*this, key);
+        if (it != this->end())
+        {
+            erase_at(it);
+            return 1;
+        }
+        return 0;
+    }
+
 public:
     template<class V, detail::enable_if_t<
                  detail::is_constructible<T, V>::value, int> = 0>
@@ -214,26 +227,14 @@ public:
 
     size_type erase(const key_type& key)
     {
-        const auto it = find_impl(*this, key);
-        if (it != this->end())
-        {
-            erase_at(it);
-            return 1;
-        }
-        return 0;
+        return erase_impl(key);
     }
 
     template<class KeyType, detail::enable_if_t<
                  detail::is_usable_as_key_type<key_compare, key_type, KeyType>::value, int> = 0>
     size_type erase(KeyType && key) // NOLINT(cppcoreguidelines-missing-std-forward)
     {
-        const auto it = find_impl(*this, key);
-        if (it != this->end())
-        {
-            erase_at(it);
-            return 1;
-        }
-        return 0;
+        return erase_impl(key);
     }
 
     iterator erase(iterator pos)

single_include/nlohmann/json_view.hpp

@@ -2674,32 +2674,52 @@ namespace view
 // Exceptions are thrown out of line, so that the accessors that may throw stay
 // small enough to be inlined.
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const char* prefix, const char* type)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const char* prefix, const char* type)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, concat(prefix, type), nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(type_error::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(out_of_range::create(id, msg, nullptr));
 }
 
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(int id, const char* msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(exception_id id, const char* msg)
 {
     NLOHMANN_VIEW_THROW(invalid_iterator::create(id, msg, nullptr));
 }
 
 /// a parse error without a position (as those of json_pointer)
-[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(int id, const std::string& msg)
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(exception_id id, const std::string& msg)
 {
     NLOHMANN_VIEW_THROW(parse_error::create(id, 0, msg, nullptr));
 }
 
+/// out_of_range.401: the array index @a idx is not below the size
+template<typename Index>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_array_index_out_of_range(const Index idx)
+{
+    throw_out_of_range(exception_id::array_index_out_of_range, concat("array index ", std::to_string(idx), " is out of range"));
+}
+
+/// out_of_range.402: the JSON Pointer token '-' of an array of @a size elements
+[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_array_index_past_end(std::size_t size)
+{
+    throw_out_of_range(exception_id::pointer_past_the_end_index, concat("array index '-' (", std::to_string(size), ") is out of range"));
+}
+
+/// out_of_range.403: the object has no member @a key
+template<typename Key>
+[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_key_not_found(const Key& key)
+{
+    throw_out_of_range(exception_id::key_not_found, concat("key '", key, "' not found"));
+}
+
 /// SAX handler of the error replay: accepts every event without storing it,
 /// and throws the exception the parser reports
 template<typename BasicJsonType>
@@ -2798,7 +2818,7 @@ template<typename BasicJsonType>
     if (f.code == error_code::input_too_large)
     {
         // (the limit is detail::view::max_input_size(): 4 GiB minus 16 bytes)
-        NLOHMANN_VIEW_THROW(out_of_range::create(416, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
+        NLOHMANN_VIEW_THROW(out_of_range::create(exception_id::document_too_large, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
     }
     throwing_sax<BasicJsonType> sax;
     const bool accepted = BasicJsonType::sax_parse(src, src + size, &sax, input_format_t::json, true, ignore_comments, ignore_trailing_commas);
@@ -2818,7 +2838,7 @@ template<typename BasicJsonType>
         }
     }
     pos.chars_read_current_line = off + 1 - line_start;
-    NLOHMANN_VIEW_THROW(parse_error::create(101, pos, "syntax error while parsing value", nullptr));
+    NLOHMANN_VIEW_THROW(parse_error::create(exception_id::syntax_error, pos, "syntax error while parsing value", nullptr));
     // LCOV_EXCL_STOP
 }
 
@@ -2893,7 +2913,7 @@ inline std::size_t text_capacity(std::size_t cap, std::size_t used, std::size_t
     constexpr std::size_t limit = 0xFFFFFFFFu;
     if (NLOHMANN_VIEW_UNLIKELY(used > limit || n > limit - used))
     {
-        throw_out_of_range(416, "edits of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "edits of 4 GiB or more are not supported by json_document");
     }
     const std::size_t needed = used + n;
     const std::size_t wanted = needed + (std::min)(limit - needed, std::size_t{256});
@@ -2944,7 +2964,7 @@ inline void reserve_moved(document_data& d)
     document_data::edit_state& e = edit_state_of(d);
     if (e.moved.size() >= 0xFFFFFFFFu)
     {
-        throw_out_of_range(416, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
+        throw_out_of_range(exception_id::document_too_large, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
     }
     if (e.moved.size() == e.moved.capacity() || e.moved_cap.size() == e.moved_cap.capacity())
     {
@@ -3476,11 +3496,6 @@ struct first_true<false, Conditions...> : std::integral_constant < int, 1 + firs
 inline void check_utf8(const char* s, std::size_t n)
 {
     const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
-    const auto hex = [](unsigned char c)
-    {
-        constexpr const char* digits = "0123456789ABCDEF";
-        return std::string{digits[c >> 4u], digits[c & 0xFu]};
-    };
     for (std::size_t i = 0; i < n;)
     {
         const unsigned char c = p[i];
@@ -3489,39 +3504,22 @@ inline void check_utf8(const char* s, std::size_t n)
             ++i;
             continue;
         }
-        std::size_t len = 0;
-        unsigned char lo = 0x80;
-        unsigned char hi = 0xBF;
-        if (c >= 0xC2 && c <= 0xDF)
+        const utf8_sequence_shape shape = utf8_shape(c);
+        const std::size_t len = shape.length;
+        if (len == 0)
         {
-            len = 2;
-        }
-        else if (c >= 0xE0 && c <= 0xEF)
-        {
-            len = 3;
-            lo = c == 0xE0 ? 0xA0 : 0x80;
-            hi = c == 0xED ? 0x9F : 0xBF;
-        }
-        else if (c >= 0xF0 && c <= 0xF4)
-        {
-            len = 4;
-            lo = c == 0xF0 ? 0x90 : 0x80;
-            hi = c == 0xF4 ? 0x8F : 0xBF;
-        }
-        else
-        {
-            throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex(c)));
+            throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_byte(c)));
         }
         for (std::size_t k = 1; k < len; ++k)
         {
             if (i + k == n)
             {
-                throw_type_error(316, concat("incomplete UTF-8 string; last byte: 0x", hex(p[n - 1])));
+                throw_type_error(exception_id::invalid_utf8, concat("incomplete UTF-8 string; last byte: 0x", hex_byte(p[n - 1])));
             }
             const unsigned char b = p[i + k];
-            if (b < (k == 1 ? lo : 0x80) || b > (k == 1 ? hi : 0xBF))
+            if (b < (k == 1 ? shape.second_lo : 0x80) || b > (k == 1 ? shape.second_hi : 0xBF))
             {
-                throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex(b)));
+                throw_type_error(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex_byte(b)));
             }
         }
         i += len;
@@ -3569,7 +3567,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object) && o->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(305, "cannot use operator[] with a string argument with ", object.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", object.type_name());
         }
         check_utf8(key.data(), key.size());
         const encoded e = encode(std::forward<V>(value));
@@ -3620,7 +3618,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(305, "cannot use operator[] with a numeric argument with ", array.type_name());
+            throw_type_error(exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", array.type_name());
         }
         check_index(idx, a->len);
         const encoded e = encode(std::forward<V>(value));
@@ -3637,7 +3635,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array) && a->kind != static_cast<std::uint8_t>(value_t::null))
         {
-            throw_type_error(308, "cannot use push_back() with ", array.type_name());
+            throw_type_error(exception_id::push_back_wrong_type, "cannot use push_back() with ", array.type_name());
         }
         const encoded e = encode(std::forward<V>(value));
         if (a->kind == static_cast<std::uint8_t>(value_t::null))
@@ -3661,7 +3659,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(309, "cannot use insert() with ", array.type_name());
+            throw_type_error(exception_id::insert_wrong_type, "cannot use insert() with ", array.type_name());
         }
         check_index(idx, a->len + 1);
         const encoded e = encode(std::forward<V>(value));
@@ -3681,7 +3679,7 @@ class editor
         node* const o = own(object);
         if (o->kind != static_cast<std::uint8_t>(value_t::object))
         {
-            throw_type_error(307, "cannot use erase() with ", object.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", object.type_name());
         }
         for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
         {
@@ -3699,7 +3697,7 @@ class editor
         node* const a = own(array);
         if (a->kind != static_cast<std::uint8_t>(value_t::array))
         {
-            throw_type_error(307, "cannot use erase() with ", array.type_name());
+            throw_type_error(exception_id::erase_wrong_type, "cannot use erase() with ", array.type_name());
         }
         check_index(idx, a->len);
         node* const h = block_of(m_doc, a, 0);
@@ -3722,7 +3720,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_doc != &m_doc || v.m_node == nullptr))
         {
-            throw_invalid_iterator(202, "view does not belong to this document");
+            throw_invalid_iterator(exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         edit_state_of(m_doc);
         return const_cast<node*>(v.m_node); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
@@ -3732,7 +3730,7 @@ class editor
     {
         if (idx >= limit)
         {
-            throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+            throw_array_index_out_of_range(idx);
         }
     }
 
@@ -3873,7 +3871,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(v.m_node == nullptr))
         {
-            throw_type_error(302, "type must be a value, but is ", "discarded");
+            throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
         encoded r;
         if (!is_container(*v.m_node))
@@ -4023,7 +4021,7 @@ class editor
     {
         if (NLOHMANN_VIEW_UNLIKELY(len >= 0xFFFFFFFFu))
         {
-            throw_out_of_range(416, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
+            throw_out_of_range(exception_id::document_too_large, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
         }
         node n = plain_node(value_t::string);
         n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
@@ -4098,12 +4096,12 @@ class editor
                 return string_node(s.data(), s.size());
             }
             case value_t::binary:
-                throw_type_error(319, "cannot store a binary value in a json_document", "");
+                throw_type_error(exception_id::document_binary_value, "cannot store a binary value in a json_document", "");
             case value_t::discarded:
             case value_t::object:
             case value_t::array:
             default:
-                throw_type_error(302, "type must be a value, but is ", "discarded");
+                throw_type_error(exception_id::type_mismatch, "type must be a value, but is ", "discarded");
         }
     }
 
@@ -4731,7 +4729,7 @@ inline void compact_nodes(const document_data& d, std::size_t arena_size, std::v
 inline std::vector<std::uint8_t> save_image(const document_data& d)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     const std::size_t arena_size = d.arena_size;
     std::vector<node> compacted;
@@ -4748,7 +4746,7 @@ inline std::vector<std::uint8_t> save_image(const document_data& d)
     if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
     {
         // LCOV_EXCL_START (4 GiB)
-        throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
+        throw_out_of_range(exception_id::document_too_large, "images of 4 GiB or more are not supported by json_document");
         // LCOV_EXCL_STOP
     }
     image_header h{};
@@ -5205,7 +5203,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 
 [[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
 {
-    throw_parse_error(116, concat("invalid json_document image: ", what));
+    throw_parse_error(exception_id::invalid_document_image, concat("invalid json_document image: ", what));
 }
 
 /// Read an image into d. The text and the decoded strings stay in the image;
@@ -5213,7 +5211,7 @@ inline bool check_image(const node* nodes, std::size_t count, const unsigned cha
 inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
 {
 #if !NLOHMANN_VIEW_LITTLE_ENDIAN
-    throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
+    throw_type_error(exception_id::document_image_unsupported, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
 #endif
     if (image == nullptr || size < sizeof(image_header))
     {
@@ -5567,7 +5565,7 @@ class view_iterator
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_value_offset == 0))
         {
-            throw_invalid_iterator(207, "cannot use key() for non-object iterators");
+            throw_invalid_iterator(exception_id::iterator_key_not_object, "cannot use key() for non-object iterators");
         }
         return string_view_t(m_doc->str(*m_pos), m_pos->len);
     }
@@ -5919,51 +5917,15 @@ enum class pointer_mode
     contains,  ///< as basic_json::contains(): no exceptions at all
 };
 
-/// the outcome of reading an array index from a reference token
-enum class index_status
-{
-    ok,
-    leading_zero, ///< parse_error.106
-    not_number,   ///< parse_error.109
-    unresolved,   ///< out_of_range.404
-    too_large,    ///< out_of_range.410
-};
+/// the outcome of reading an array index: detail::parse_array_index(), shared with json_pointer
+using index_status = detail::array_index_status;
 
 /// reads an array index like json_pointer::array_index (RFC 6901, Sect. 4),
 /// but reports errors instead of throwing them
 template<typename StringType>
 index_status array_index(const StringType& s, std::size_t& idx) noexcept
 {
-    // as basic_json: the empty token and "-" (past the last element) are
-    // unresolved rather than not a number
-    if (s.empty() || (s.size() == 1 && s[0] == '-'))
-    {
-        return index_status::unresolved;
-    }
-    if (s[0] < '0' || s[0] > '9')
-    {
-        return index_status::not_number;
-    }
-    if (s.size() > 1 && s[0] == '0')
-    {
-        return index_status::leading_zero;
-    }
-    std::uint64_t v = 0;
-    for (const auto c : s)
-    {
-        const auto d = static_cast<unsigned>(static_cast<unsigned char>(c)) - '0';
-        if (d > 9 || v > ((std::numeric_limits<std::uint64_t>::max)() - d) / 10)
-        {
-            return index_status::unresolved; // not a number, or beyond unsigned long long
-        }
-        v = (v * 10) + d;
-    }
-    if (v >= (std::numeric_limits<std::size_t>::max)()) // (std::size_t converts to std::uint64_t implicitly)
-    {
-        return index_status::too_large;
-    }
-    idx = static_cast<std::size_t>(v);
-    return index_status::ok;
+    return detail::parse_array_index(s, idx);
 }
 
 /// throws the exception json_pointer::array_index throws for this status
@@ -5973,15 +5935,15 @@ template<typename StringType>
     switch (status)
     {
         case index_status::leading_zero:
-            throw_parse_error(106, concat("array index '", s, "' must not begin with '0'"));
-        case index_status::not_number:
-            throw_parse_error(109, concat("array index '", s, "' is not a number"));
-        case index_status::too_large:
-            throw_out_of_range(410, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
+            throw_parse_error(exception_id::pointer_index_leading_zero, concat("array index '", s, "' must not begin with '0'"));
+        case index_status::not_a_number:
+            throw_parse_error(exception_id::pointer_index_not_a_number, concat("array index '", s, "' is not a number"));
+        case index_status::exceeds_size_type:
+            throw_out_of_range(exception_id::value_out_of_range, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
         case index_status::unresolved:
         case index_status::ok:
         default:
-            throw_out_of_range(404, concat("unresolved reference token '", s, "'"));
+            throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", s, "'"));
     }
 }
 
@@ -6006,7 +5968,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(403, concat("key '", token, "' not found"));
+                    throw_key_not_found(token);
                 }
                 return View();
             }
@@ -6018,7 +5980,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (throwing)
                 {
-                    throw_out_of_range(402, concat("array index '-' (", std::to_string(cur.size()), ") is out of range"));
+                    throw_array_index_past_end(cur.size());
                 }
                 return View();
             }
@@ -6026,7 +5988,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             const index_status status = array_index(token, idx);
             if (status != index_status::ok)
             {
-                const bool parse_error = status == index_status::leading_zero || status == index_status::not_number;
+                const bool parse_error = status == index_status::leading_zero || status == index_status::not_a_number;
                 if (throwing || (mode == pointer_mode::value && parse_error))
                 {
                     throw_array_index_error(status, token);
@@ -6037,7 +5999,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
             {
                 if (mode == pointer_mode::checked)
                 {
-                    throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
+                    throw_array_index_out_of_range(idx);
                 }
                 return View();
             }
@@ -6047,7 +6009,7 @@ View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
         {
             if (throwing)
             {
-                throw_out_of_range(404, concat("unresolved reference token '", token, "'"));
+                throw_out_of_range(exception_id::pointer_unresolved, concat("unresolved reference token '", token, "'"));
             }
             return View();
         }
@@ -6956,21 +6918,17 @@ class view_serializer
             m_out.put("null");
             return;
         }
-        static constexpr bool is_ieee_single_or_double
-            = std::numeric_limits<number_float_t>::is_iec559
-              && ((std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
-                  || (std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024));
-        write_float(x, std::integral_constant<bool, is_ieee_single_or_double>());
+        write_float(x, std::integral_constant<bool, ::nlohmann::detail::has_native_float_format<number_float_t>::value>());
     }
 
-    void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::true_type /*has_native_float_format*/)
     {
         std::array<char, 64> buf{};
         const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
         m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
     }
 
-    void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
+    void write_float(number_float_t x, std::false_type /*has_native_float_format*/)
     {
         // other types (e.g. long double) are rare: the library writes them
         const string_t s = BasicJsonType(x).dump();
@@ -7097,8 +7055,8 @@ class view_serializer
 
     void write_u_escape(std::uint32_t u)
     {
-        static constexpr const char* hex = "0123456789abcdef";
-        const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
+        std::array<char, 6> e = {{'\\', 'u', 0, 0, 0, 0}};
+        hex4_lower(static_cast<std::uint16_t>(u), &e[2]);
         m_out.put(e.data(), e.size());
     }
 
@@ -7295,7 +7253,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::binary:
         case value_t::discarded:
         default:
-            throw_type_error(302, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
+            throw_type_error(exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
     }
 }
 
@@ -7305,7 +7263,7 @@ std::vector<U, A> vector_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_array()))
     {
-        throw_type_error(302, "type must be array, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be array, but is ", v.type_name());
     }
     std::vector<U, A> r;
     r.reserve(v.size());
@@ -7323,7 +7281,7 @@ Map map_value(const View& v)
 {
     if (NLOHMANN_VIEW_UNLIKELY(!v.is_object()))
     {
-        throw_type_error(302, "type must be object, but is ", v.type_name());
+        throw_type_error(exception_id::type_mismatch, "type must be object, but is ", v.type_name());
     }
     Map r;
     for (auto it = v.begin(); it != v.end(); ++it)
@@ -7562,7 +7520,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a string argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a string argument with ", type_name());
         }
         return lookup(key);
     }
@@ -7588,7 +7546,7 @@ class basic_json_view
             {
                 return {};
             }
-            detail::view::throw_type_error(305, "cannot use operator[] with a numeric argument with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::subscript_wrong_type, "cannot use operator[] with a numeric argument with ", type_name());
         }
         return idx < m_node->len ? basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx))) : basic_json_view();
     }
@@ -7621,12 +7579,12 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         if (NLOHMANN_VIEW_UNLIKELY(r.is_discarded()))
         {
-            detail::view::throw_out_of_range(403, detail::concat("key '", std::string(key.data(), key.size()), "' not found"));
+            detail::view::throw_key_not_found(std::string(key.data(), key.size()));
         }
         return r;
     }
@@ -7647,11 +7605,11 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_array()))
         {
-            detail::view::throw_type_error(304, "cannot use at() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::at_wrong_type, "cannot use at() with ", type_name());
         }
         if (NLOHMANN_VIEW_UNLIKELY(idx >= m_node->len))
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return basic_json_view(m_doc, navigation::value(detail::view::element_at<Editable>(*m_doc, m_node, idx)));
     }
@@ -7679,7 +7637,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_object()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = lookup(key);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -7698,7 +7656,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_structured()))
         {
-            detail::view::throw_type_error(306, "cannot use value() with ", type_name());
+            detail::view::throw_type_error(detail::exception_id::value_wrong_type, "cannot use value() with ", type_name());
         }
         const basic_json_view r = detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::value);
         return r.is_discarded() ? default_value : r.template get<T>();
@@ -7716,7 +7674,7 @@ class basic_json_view
         const iterator it = begin();
         if (NLOHMANN_VIEW_UNLIKELY(it == end()))
         {
-            detail::view::throw_invalid_iterator(214, "cannot get value");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_value_unavailable, "cannot get value");
         }
         return *it;
     }
@@ -7868,7 +7826,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_string()))
         {
-            detail::view::throw_type_error(302, "type must be string, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be string, but is ", type_name());
         }
         return {m_doc->str(*m_node), m_node->len};
     }
@@ -7880,7 +7838,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_number()))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return {m_doc->str(*m_node), detail::view::number_length(*m_node)};
     }
@@ -8090,7 +8048,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_boolean()))
         {
-            detail::view::throw_type_error(302, "type must be boolean, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be boolean, but is ", type_name());
         }
         return (m_node->flags & detail::view::node_flags::is_true) != 0;
     }
@@ -8100,7 +8058,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(m_node == nullptr))
         {
-            detail::view::throw_type_error(302, "type must be number, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be number, but is ", type_name());
         }
         return detail::view::arithmetic_value<T, BasicJsonType>(*m_doc, *m_node);
     }
@@ -8109,7 +8067,7 @@ class basic_json_view
     {
         if (NLOHMANN_VIEW_UNLIKELY(!is_null()))
         {
-            detail::view::throw_type_error(302, "type must be null, but is ", type_name());
+            detail::view::throw_type_error(detail::exception_id::type_mismatch, "type must be null, but is ", type_name());
         }
         return nullptr;
     }
@@ -8418,7 +8376,7 @@ class basic_json_document
     {
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_type_error(320, "cannot save a discarded json_document");
+            detail::view::throw_type_error(detail::exception_id::document_image_unsupported, "cannot save a discarded json_document");
         }
         return detail::view::save_image(*m_data);
     }
@@ -8519,7 +8477,7 @@ class basic_json_document
                 const std::size_t idx = pointer_index(token);
                 if (idx >= 0xFFFFFFFFu)
                 {
-                    detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+                    detail::view::throw_array_index_out_of_range(idx);
                 }
                 for (std::size_t i = 0; i < idx; ++i)
                 {
@@ -8575,7 +8533,7 @@ class basic_json_document
     {
         if (ptr.empty())
         {
-            detail::view::throw_out_of_range(405, "JSON pointer has no parent");
+            detail::view::throw_out_of_range(detail::exception_id::patch_on_root, "JSON pointer has no parent");
         }
         const view_type parent = root().at(ptr.parent_pointer());
         const auto& token = ptr.back();
@@ -8595,7 +8553,7 @@ class basic_json_document
         static_assert(Editable, "only an editable document can be edited: use basic_json_document<BasicJsonType, true> (json_editable_document)");
         if (NLOHMANN_VIEW_UNLIKELY(!m_data || m_data->discarded))
         {
-            detail::view::throw_invalid_iterator(202, "view does not belong to this document");
+            detail::view::throw_invalid_iterator(detail::exception_id::iterator_from_other_value, "view does not belong to this document");
         }
         return detail::view::editor<BasicJsonType, view_type>(*m_data);
     }
@@ -8612,7 +8570,7 @@ class basic_json_document
     {
         if (idx < 0)
         {
-            detail::view::throw_out_of_range(401, detail::concat("array index ", std::to_string(idx), " is out of range"));
+            detail::view::throw_array_index_out_of_range(idx);
         }
         return static_cast<std::size_t>(idx);
     }

tests/src/unit-binary_writer_sinks.cpp

@@ -492,3 +492,278 @@ TEST_CASE("binary_reserve_hint never over-reserves")
         CHECK(nlohmann::detail::binary_reserve_hint(json({{"a", 1}, {"b", 2}})) == 5);
     }
 }
+
+namespace
+{
+
+// numbers around every boundary of the integer encodings, and floats of each
+// kind (exact in float, needing double, special values)
+std::vector<json> boundary_numbers()
+{
+    std::vector<json> numbers;
+    for (int k = 0; k < 64; ++k)
+    {
+        const std::uint64_t p = std::uint64_t{1} << k;
+        for (const std::uint64_t d :
+                {
+                    p - 1, p, p + 1
+                })
+        {
+            numbers.emplace_back(d);
+            if (d <= static_cast<std::uint64_t>((std::numeric_limits<std::int64_t>::max)()))
+            {
+                numbers.emplace_back(static_cast<std::int64_t>(d));
+                numbers.emplace_back(-static_cast<std::int64_t>(d));
+                numbers.emplace_back(-static_cast<std::int64_t>(d) - 1);
+            }
+        }
+    }
+    numbers.emplace_back((std::numeric_limits<std::int64_t>::min)());
+    numbers.emplace_back((std::numeric_limits<std::uint64_t>::max)());
+    for (const double f :
+            {
+                0.0, -0.0, 1.0, -1.0, 0.5, 0.1, 3.25, 1e300, -1e-300, 3.4028234663852886e38, 1e39,
+                std::numeric_limits<double>::infinity(), -std::numeric_limits<double>::infinity(),
+                std::numeric_limits<double>::quiet_NaN()
+            })
+    {
+        numbers.emplace_back(f);
+    }
+    return numbers;
+}
+
+// the concatenation of the encodings of the elements of @a numbers[first, first + count)
+template<typename Single>
+std::vector<std::uint8_t> concat_singles(const std::vector<json>& numbers, const std::size_t first, const std::size_t count, Single single)
+{
+    std::vector<std::uint8_t> bytes;
+    for (std::size_t i = first; i < first + count; ++i)
+    {
+        const auto one = single(numbers[i]);
+        bytes.insert(bytes.end(), one.begin(), one.end());
+    }
+    return bytes;
+}
+
+} // namespace
+
+// Runs of numbers in arrays are encoded straight into space reserved from the
+// sink, by code that is separate from the encoding of a single value. Both have
+// to agree on every number: an array is its head and the encodings of its
+// elements, one after the other.
+TEST_CASE("runs of numbers in arrays are encoded as the numbers one by one")
+{
+    const std::vector<json> numbers = boundary_numbers();
+
+    // arrays of every length that a one-byte head covers, so that runs are as
+    // long as, and longer and shorter than, what fits one reservation
+    for (const std::size_t count :
+            {
+                1u, 2u, 3u, 5u, 14u, 15u, 23u
+            })
+    {
+        for (std::size_t first = 0; first + count <= numbers.size(); first += 7)
+        {
+            const json array(std::vector<json>(numbers.begin() + static_cast<std::ptrdiff_t>(first),
+                                               numbers.begin() + static_cast<std::ptrdiff_t>(first + count)));
+            CAPTURE(array.dump(-1, ' ', false, json::error_handler_t::replace))
+
+            std::vector<std::uint8_t> expected{static_cast<std::uint8_t>(0x80 + count)};
+            auto elements = concat_singles(numbers, first, count, [](const json & j)
+            {
+                return json::to_cbor(j);
+            });
+            expected.insert(expected.end(), elements.begin(), elements.end());
+            CHECK(json::to_cbor(array) == expected);
+
+            expected.assign(1, static_cast<std::uint8_t>(count <= 15 ? 0x90 + count : 0xDC));
+            if (count > 15)
+            {
+                expected.push_back(0);
+                expected.push_back(static_cast<std::uint8_t>(count));
+            }
+            elements = concat_singles(numbers, first, count, [](const json & j)
+            {
+                return json::to_msgpack(j);
+            });
+            expected.insert(expected.end(), elements.begin(), elements.end());
+            CHECK(json::to_msgpack(array) == expected);
+
+            for (const bool bjdata :
+                    {
+                        false, true
+                    })
+            {
+                expected.assign(1, static_cast<std::uint8_t>('['));
+                elements = concat_singles(numbers, first, count, [bjdata](const json & j)
+                {
+                    return bjdata ? json::to_bjdata(j) : json::to_ubjson(j);
+                });
+                expected.insert(expected.end(), elements.begin(), elements.end());
+                expected.push_back(static_cast<std::uint8_t>(']'));
+                CHECK((bjdata ? json::to_bjdata(array) : json::to_ubjson(array)) == expected);
+            }
+
+            // BON8 has no integers above the int64 range
+            bool representable = true;
+            for (std::size_t i = first; i < first + count; ++i)
+            {
+                representable = representable && bon8_representable(numbers[i]);
+            }
+            if (representable)
+            {
+                expected.assign(1, static_cast<std::uint8_t>(count <= 4 ? 0x80 + count : 0x85));
+                elements = concat_singles(numbers, first, count, [](const json & j)
+                {
+                    return json::to_bon8(j);
+                });
+                expected.insert(expected.end(), elements.begin(), elements.end());
+                if (count > 4)
+                {
+                    expected.push_back(0xFE);
+                }
+                CHECK(json::to_bon8(array) == expected);
+            }
+            else
+            {
+                CHECK_THROWS_AS(json::to_bon8(array), json::out_of_range&);
+            }
+        }
+    }
+}
+
+// An array that is written in more than one reservation (more numbers than fit
+// one), and arrays of an index with more digits, round trip for every format.
+TEST_CASE("large arrays and many digits of indices round trip")
+{
+    json array = json::array();
+    for (int i = 0; i < 12000; ++i)
+    {
+        switch (i % 4)
+        {
+            case 0:
+                array.push_back(i);
+                break;
+            case 1:
+                array.push_back(-i);
+                break;
+            case 2:
+                array.push_back(i * 0.25);
+                break;
+            default:
+                array.push_back(i % 8 == 3);
+                break;
+        }
+    }
+    json document = json::object();
+    document["numbers"] = array;
+    document["nested"] = json::array({array, "text", array});
+
+    CHECK(json::from_cbor(json::to_cbor(document)) == document);
+    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
+    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
+    CHECK(json::from_bson(json::to_bson(document)) == document);
+    CHECK(json::from_bon8(json::to_bon8(document)) == document);
+}
+
+// Strings and keys are written with their head in one reservation up to a
+// length; around that length, and with every kind of head, they must read back.
+TEST_CASE("strings of every head length round trip")
+{
+    json document = json::object();
+    json array = json::array();
+    for (const std::size_t length :
+            {
+                0u, 1u, 2u, 3u, 4u, 7u, 8u, 15u, 16u, 17u, 23u, 24u, 25u, 31u, 32u, 33u, 63u, 127u, 128u, 129u, 200u, 245u, 246u, 247u, 248u, 249u, 250u, 251u, 252u, 253u, 254u, 255u, 256u, 257u, 300u, 1000u, 65535u, 65536u, 70000u
+            })
+    {
+        const std::string text(length, 'x');
+        array.push_back(text);
+        document[std::string(length, 'k')] = text;
+    }
+    document["array"] = array;
+
+    CHECK(json::from_cbor(json::to_cbor(document)) == document);
+    CHECK(json::from_msgpack(json::to_msgpack(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document)) == document);
+    CHECK(json::from_ubjson(json::to_ubjson(document, true, true)) == document);
+    CHECK(json::from_bjdata(json::to_bjdata(document)) == document);
+    CHECK(json::from_bson(json::to_bson(document)) == document);
+    CHECK(json::from_bon8(json::to_bon8(document)) == document);
+}
+
+#if !defined(JSON_NOEXCEPTION)
+// What a write that throws leaves behind in an output adapter is what was written
+// before it, whatever the adapter and however the adapter sink buffers. (Without
+// exceptions, the writes in CHECK_THROWS_AS do not run.)
+TEST_CASE("a write that throws leaves the same bytes in every kind of output")
+{
+    json array = json::array();
+    for (int i = 0; i < 700; ++i)
+    {
+        array.push_back(i * 1000);
+        array.push_back("text " + std::to_string(i));
+    }
+    array.push_back("bad \xFF byte");
+    json document = json::object();
+    document["first"] = array;
+    document["second"] = 1;
+
+    const auto strict = json::error_handler_t::strict;
+
+    SECTION("cbor")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_cbor(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_cbor(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_cbor(document, as_stream, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("msgpack")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_msgpack(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_msgpack(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_msgpack(document, as_stream, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("ubjson")
+    {
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_ubjson(document, as_vector, false, false, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_ubjson(document, as_string, false, false, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_ubjson(document, as_stream, false, false, strict), json::type_error&);
+        CHECK(!as_vector.empty());
+        CHECK(std::string(reinterpret_cast<const char*>(as_vector.data()), as_vector.size()) == as_string); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        CHECK(as_stream.str() == as_string);
+    }
+
+    SECTION("bson")
+    {
+        // the size pass finds the string before anything is written
+        std::vector<std::uint8_t> as_vector;
+        std::string as_string;
+        std::ostringstream as_stream;
+        CHECK_THROWS_AS(json::to_bson(document, as_vector, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_bson(document, as_string, strict), json::type_error&);
+        CHECK_THROWS_AS(json::to_bson(document, as_stream, strict), json::type_error&);
+        CHECK(as_vector.empty());
+        CHECK(as_string.empty());
+        CHECK(as_stream.str().empty());
+    }
+}
+#endif

tests/src/unit-class_lexer.cpp

@@ -2042,3 +2042,118 @@ TEST_CASE("string scanning kernels")
     CHECK(nlohmann::detail::read_eight_bytes(bytes.data() + 8) == 0xFF0F0E0D0C0B0A09u);
     CHECK(nlohmann::detail::read_eight_bytes(reinterpret_cast<const char*>(bytes.data()) + 3) == 0x0B0A090807060504u);
 }
+
+TEST_CASE("find_ascii_copyable_run agrees with is_ascii_copyable for every byte")
+{
+    // the SWAR mask in find_ascii_copyable_run() encodes the predicate a
+    // second time; check every byte value at every position of a 24-byte buffer
+    // (three words) and for several lengths, with the byte at the end or inside
+    for (unsigned int value = 0; value < 256; ++value)
+    {
+        for (std::size_t position = 0; position < 24; ++position)
+        {
+            std::array<unsigned char, 24> buffer{};
+            buffer.fill(static_cast<unsigned char>('a'));
+            buffer[position] = static_cast<unsigned char>(value);
+            const bool copyable = nlohmann::detail::is_ascii_copyable(static_cast<unsigned char>(value));
+            for (const std::size_t n :
+                    {
+                        position, position + 1, std::size_t{24}
+                    })
+            {
+                if (n > 24)
+                {
+                    continue;
+                }
+                const std::size_t expected = (copyable || n <= position) ? n : position;
+                CAPTURE(value)
+                CAPTURE(position)
+                CAPTURE(n)
+                CHECK(nlohmann::detail::find_ascii_copyable_run(buffer.data(), n) == expected);
+            }
+        }
+    }
+}
+
+TEST_CASE("UTF-8 validators accept the same sequences")
+{
+    // The library checks UTF-8 in several places: detail::decode (serializer),
+    // the per-lead-byte switch of the lexer (json::accept), validate_one_utf8
+    // (bulk string scan), utf8_shape, and the byte path of the BON8 reader.
+    // They must accept exactly the same sequences (RFC 3629, section 4).
+    using nlohmann::json;
+
+    // bytes for the third and fourth position: the first two pairs are checked
+    // against all validators, the others only against the cheap ones
+    const std::array<std::array<unsigned char, 2>, 6> tails =
+    {
+        {
+            {{0x80, 0x80}}, {{0xBF, 0xBF}}, {{0x7F, 0x80}}, {{0xC0, 0x80}}, {{0x80, 0x7F}}, {{0x80, 0xC0}}
+        }
+    };
+
+    for (unsigned lead = 0x80; lead <= 0xFF; ++lead)
+    {
+        const auto shape = nlohmann::detail::utf8_shape(static_cast<std::uint8_t>(lead));
+        for (unsigned second = 0; second <= 0xFF; ++second)
+        {
+            for (std::size_t t = 0; t < tails.size(); ++t)
+            {
+                const std::array<unsigned char, 4> bytes = {{static_cast<unsigned char>(lead), static_cast<unsigned char>(second), tails[t][0], tails[t][1]}};
+
+                // expectation from the shape: the sequence is bytes[0..length)
+                const std::size_t length = shape.length;
+                bool expected = length >= 2 && second >= shape.second_lo && second <= shape.second_hi;
+                for (std::size_t i = 2; expected && i < length; ++i)
+                {
+                    expected = bytes[i] >= 0x80 && bytes[i] <= 0xBF;
+                }
+
+                // the DFA of the serializer
+                bool dfa = length >= 2;
+                if (dfa)
+                {
+                    std::uint8_t state = nlohmann::detail::UTF8_ACCEPT;
+                    std::uint32_t codep = 0;
+                    for (std::size_t i = 0; i < length; ++i)
+                    {
+                        nlohmann::detail::decode(state, codep, bytes[i]);
+                    }
+                    dfa = state == nlohmann::detail::UTF8_ACCEPT;
+                }
+
+                // the bulk path: exactly the sequence, and one byte short
+                const std::size_t bulk = nlohmann::detail::validate_one_utf8(bytes.data(), length);
+                const std::size_t bulk_short = length > 0 ? nlohmann::detail::validate_one_utf8(bytes.data(), length - 1) : 0;
+
+                CAPTURE(lead)
+                CAPTURE(second)
+                CAPTURE(t)
+                CHECK((dfa == expected && bulk == (expected ? length : 0) && bulk_short == 0));
+
+                if (t < 2 && length >= 2)
+                {
+                    // the lexer's byte path
+                    const std::string sequence(reinterpret_cast<const char*>(bytes.data()), length); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+                    CHECK(json::accept("\"" + sequence + "\"") == expected);
+
+                    // the byte path of the BON8 reader (a string ends at 0xFF)
+                    if (lead >= 0xC2 && lead <= 0xF7)
+                    {
+                        std::vector<std::uint8_t> packed(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length));
+                        packed.push_back(0xFF);
+                        const json j = json::from_bon8(packed, true, false);
+                        if (expected)
+                        {
+                            CHECK(j == json(sequence));
+                        }
+                        else
+                        {
+                            CHECK_FALSE((j.is_string() && j.get<std::string>() == sequence));
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

tests/src/unit-custom-number-types.cpp

@@ -285,6 +285,58 @@ TEST_CASE("custom number types: integers beyond 64 bits")
         CHECK(wide_json::to_bjdata(wide_json::array({uint_big, uint_big}), true, true) == expected_bjdata_array);
     }
 
+    SECTION("integers in arrays and objects")
+    {
+        // runs of numbers and scalar object members are encoded by loops of
+        // their own for the number types up to 64 bits; a wider number type
+        // takes the generic path, which checks the range of every integer
+        const wide_json run = wide_json::array({make_int(1), make_int(-3), make_uint(7), wide_json(1.5), int_big, make_int(5)});
+        const wide_json run_negative = wide_json::array({make_int(1), make_int(-3), int_big_negative});
+        const wide_json run_unsigned = wide_json::array({make_uint(1), make_uint(7), uint_big});
+        const wide_json members = wide_json::object({{"a", make_int(1)}, {"b", wide_json(1.5)}, {"c", int_big}});
+
+        const std::vector<wide_json> failing = {run, run_negative, run_unsigned, members, wrap(run), wrap(members)};
+        for (const auto& value : failing)
+        {
+            CHECK_THROWS_AS(_ = wide_json::to_cbor(value), out_of_range&);
+            CHECK_THROWS_AS(_ = wide_json::to_msgpack(value), out_of_range&);
+            CHECK_THROWS_AS(_ = wide_json::to_bson(wrap(value)), out_of_range&);
+            CHECK_THROWS_AS(_ = wide_json::to_bon8(value), out_of_range&);
+        }
+
+#if !defined(JSON_NOEXCEPTION)
+        // a failing write leaves no more than the elements before the failing one
+        // (without exceptions, the writes in CHECK_THROWS_AS do not run)
+        std::vector<std::uint8_t> out;
+        CHECK_THROWS_AS(wide_json::to_cbor(run, out), out_of_range&);
+        // (the head of the array, 1, -3, 7, and 1.5 as a single-precision float)
+        CHECK(out == std::vector<std::uint8_t>({0x86, 0x01, 0x22, 0x07, 0xFA, 0x3F, 0xC0, 0x00, 0x00}));
+        out.clear();
+        CHECK_THROWS_AS(wide_json::to_bon8(run, out), out_of_range&);
+        CHECK(!out.empty());
+#endif
+
+        // the same values that fit are written exactly as with 64-bit number types
+        const wide_json fits = wide_json::array({make_int(1), make_int(-3), make_uint(7), wide_json(1.5), make_int(min_int64), make_int(max_int64), make_int(200), make_int(-70000)});
+        const nlohmann::json fits64 = nlohmann::json::array({1, -3, 7, 1.5, (std::numeric_limits<std::int64_t>::min)(), (std::numeric_limits<std::int64_t>::max)(), 200, -70000});
+        CHECK(wide_json::to_cbor(fits) == nlohmann::json::to_cbor(fits64));
+        CHECK(wide_json::to_msgpack(fits) == nlohmann::json::to_msgpack(fits64));
+        CHECK(wide_json::to_ubjson(fits) == nlohmann::json::to_ubjson(fits64));
+        CHECK(wide_json::to_ubjson(fits, true, true) == nlohmann::json::to_ubjson(fits64, true, true));
+        CHECK(wide_json::to_bjdata(fits) == nlohmann::json::to_bjdata(fits64));
+        CHECK(wide_json::to_bjdata(fits, true, true) == nlohmann::json::to_bjdata(fits64, true, true));
+        CHECK(wide_json::to_bon8(fits) == nlohmann::json::to_bon8(fits64));
+        CHECK(wide_json::to_bson(wrap(fits)) == nlohmann::json::to_bson(nlohmann::json::object({{"v", fits64}})));
+
+        const wide_json fit_members = wide_json::object({{"a", make_int(1)}, {"b", make_int(-300)}, {"c", make_uint(max_uint64)}, {"d", wide_json(2.5)}});
+        const nlohmann::json fit_members64 = nlohmann::json::object({{"a", 1}, {"b", -300}, {"c", (std::numeric_limits<std::uint64_t>::max)()}, {"d", 2.5}});
+        CHECK(wide_json::to_cbor(fit_members) == nlohmann::json::to_cbor(fit_members64));
+        CHECK(wide_json::to_msgpack(fit_members) == nlohmann::json::to_msgpack(fit_members64));
+        CHECK(wide_json::to_ubjson(fit_members) == nlohmann::json::to_ubjson(fit_members64));
+        CHECK(wide_json::to_bjdata(fit_members) == nlohmann::json::to_bjdata(fit_members64));
+        CHECK(wide_json::to_bson(fit_members) == nlohmann::json::to_bson(fit_members64));
+    }
+
     SECTION("BJData ND-array")
     {
         // an ND-array element beyond 64 bits does not fit any dtype, so the

tests/src/unit-serialization.cpp

@@ -1580,3 +1580,94 @@ TEST_CASE("invalid UTF-8 at every position is handled like the reference")
         }
     }
 }
+
+TEST_CASE("short strings are written like the reference, as values and as keys")
+{
+    // strings of up to 16 characters (32 with vector instructions) that need no
+    // escaping are written as a whole (together with the quotes and, for a key,
+    // the colon); everything else, including a string that is merely short,
+    // takes the general path.
+    // Every length around the edges of the size classes of the fast path is
+    // combined with each kind of byte that must send a string to the general
+    // path, at each position, and compared with the reference for values and,
+    // via the value, for keys.
+    const std::vector<std::string> specials =
+    {
+        "\"", "\\", "\n", "\x1f", "\x7f", "\xc3\xa9", "\xe2\x82\xac", "\xf0\x9f\x98\x80", "\xff", "\x80", "\xc3"
+    };
+
+    for (std::size_t length = 0; length <= 36; ++length)
+    {
+        const std::string plain(length, 'k');
+        check_dump_against_reference(plain, false);
+
+        for (const auto& special : specials)
+        {
+            for (std::size_t pos = 0; pos <= length; ++pos)
+            {
+                std::string s = plain;
+                s.insert(pos, special);
+                check_dump_against_reference(s, false);
+
+                for (const bool ensure_ascii :
+                        {
+                            false, true
+                        })
+                {
+                    // a key and a value are written alike, in compact and
+                    // in pretty-printed form
+                    const json value = s;
+                    const json object = json::object({{s, 1}});
+                    for (const auto error_handler :
+                            {
+                                json::error_handler_t::replace, json::error_handler_t::keep
+                            })
+                    {
+                        const std::string quoted = value.dump(-1, ' ', ensure_ascii, error_handler);
+                        CHECK(object.dump(-1, ' ', ensure_ascii, error_handler) == "{" + quoted + ":1}");
+                        CHECK(object.dump(2, ' ', ensure_ascii, error_handler) == "{\n  " + quoted + ": 1\n}");
+                    }
+                }
+            }
+        }
+    }
+}
+
+TEST_CASE("runs of multi-byte characters are escaped like the reference under ensure_ascii")
+{
+    // a run of well-formed multi-byte characters is escaped straight into the
+    // write buffer; it has to flush that mid-run, stop at an ASCII character or
+    // an ill-formed sequence and leave those to the general path, and pick up
+    // behind what the general path has pending
+    const std::vector<std::string> characters =
+    {
+        "\xc2\x80", "\xdf\xbf", "\xe0\xa0\x80", "\xe2\x82\xac", "\xed\x9f\xbf", "\xef\xbf\xbf",
+        "\xf0\x90\x80\x80", "\xf0\x9f\x98\x80", "\xf4\x8f\xbf\xbf"
+    };
+    const std::vector<std::string> interruptions =
+    {
+        "", "a", "\n", "\"", "\x7f", "\xff", "\x80", "\xc3", "\xe2\x82", "\xf0\x9f\x98", "\xed\xa0\x80"
+    };
+
+    for (std::size_t shift = 0; shift <= 13; ++shift)
+    {
+        for (const auto& interruption : interruptions)
+        {
+            for (const std::size_t count :
+                    {
+                        std::size_t{1}, std::size_t{2}, std::size_t{85}, std::size_t{200}
+                    })
+            {
+                std::string s(shift, 'x');
+                for (std::size_t i = 0; i < count; ++i)
+                {
+                    s += characters[(i + shift) % characters.size()];
+                }
+                s += interruption;
+                s += characters[shift % characters.size()];
+                s += characters[(shift + 3) % characters.size()];
+                check_dump_against_reference(s, shift < 2);
+            }
+        }
+    }
+}

tests/src/unit-stream-bulk-scan.cpp

@@ -48,14 +48,16 @@ namespace
 class chunked_streambuf : public std::streambuf
 {
   public:
-    chunked_streambuf(std::string s, std::size_t chunk_size)
-        : m_data(std::move(s)), m_chunk_size(chunk_size)
+    // The first @a unbuffered characters are served without a get area, the
+    // rest in get areas of @a chunk_size.
+    chunked_streambuf(std::string s, std::size_t chunk_size, std::size_t unbuffered = 0)
+        : m_data(std::move(s)), m_chunk_size(chunk_size), m_unbuffered(unbuffered)
     {}
 
   protected:
     int_type underflow() override
     {
-        if (m_chunk_size == 0)
+        if (m_chunk_size == 0 || m_pos < m_unbuffered)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos]) : traits_type::eof();
         }
@@ -77,7 +79,7 @@ class chunked_streambuf : public std::streambuf
 
     int_type uflow() override
     {
-        if (m_chunk_size == 0)
+        if (m_chunk_size == 0 || m_pos < m_unbuffered)
         {
             return m_pos < m_data.size() ? traits_type::to_int_type(m_data[m_pos++]) : traits_type::eof();
         }
@@ -88,6 +90,7 @@ class chunked_streambuf : public std::streambuf
     std::string m_data;
     std::size_t m_pos = 0;
     std::size_t m_chunk_size;
+    std::size_t m_unbuffered;
 };
 
 // how a test reads from the stream
@@ -101,9 +104,9 @@ enum class read_mode
 // Read @a input from a chunked_streambuf and describe everything observable:
 // the values or the exception, the stream state after each value, and the
 // characters left in the stream.
-std::string observe(const std::string& input, std::size_t chunk_size, read_mode mode)
+std::string observe(const std::string& input, std::size_t chunk_size, read_mode mode, std::size_t unbuffered = 0)
 {
-    chunked_streambuf buf(input, chunk_size);
+    chunked_streambuf buf(input, chunk_size, unbuffered);
     std::istream is(&buf);
     std::string result;
     for (int i = 0; i < 4; ++i)
@@ -212,6 +215,31 @@ TEST_CASE("parsing from a std::istream scans the get area in bulk")
         }
     }
 
+    SECTION("results do not depend on a get area that appears late")
+    {
+        // the first characters come without a get area, then the streambuf
+        // starts to use one: the token that is read at that point is complete
+        for (const auto& input : corpus())
+        {
+            const std::string expected = observe(input, 0, read_mode::extract);
+            for (const std::size_t unbuffered :
+                    {
+                        1u, 2u, 3u, 5u, 8u, 13u, 21u
+                    })
+            {
+                for (const std::size_t chunk_size :
+                        {
+                            1u, 2u, 3u, 7u, 64u
+                        })
+                {
+                    CAPTURE(input)
+                    CAPTURE(unbuffered)
+                    CAPTURE(chunk_size)
+                    CHECK(observe(input, chunk_size, read_mode::extract, unbuffered) == expected);
+                }
+            }
+        }
+    }
 #endif // !defined(JSON_NOEXCEPTION)
 
     SECTION("values are the same as when parsing from a string")

tools/generate_natvis/generate_natvis.py

@@ -139,9 +139,12 @@ if __name__ == '__main__':
 
     namespaces += [f'{namespaces[0]}::{ns}' for ns in inline_namespaces]
 
+    # The template renders a local XML file, not a web response, and autoescape is enabled.
+    # nosemgrep: python.flask.security.xss.audit.direct-use-of-jinja2.direct-use-of-jinja2
     env = jinja2.Environment(loader=jinja2.FileSystemLoader(searchpath=sys.path[0]), autoescape=True, trim_blocks=True,
                                                             lstrip_blocks=True, keep_trailing_newline=True)
     template = env.get_template('nlohmann_json.natvis.j2')
+    # nosemgrep: python.flask.security.xss.audit.direct-use-of-jinja2.direct-use-of-jinja2
     natvis = template.render(namespaces=namespaces)
 
     output = args.output or os.path.join(args.repo_root, 'nlohmann_json.natvis')