Merge branch 'develop' into claude/issue-3885-3dcafd

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

.github/workflows/ubuntu.yml

@@ -31,6 +31,45 @@ jobs:
       - name: Build
         run: cmake --build build --target ci_test_gcc
 
+  ci_meson_install:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+      - name: Get latest CMake and ninja
+        uses: lukka/get-cmake@fffaaafeea488556c2c12dad60690008bc1caacb # v4.4.2
+      - name: Install Meson
+        run: pip install meson
+      - name: Install with Meson
+        run: |
+          meson setup build-meson --prefix=${{ github.workspace }}/install
+          meson install -C build-meson
+      - name: Use the installed package with find_package
+        run: |
+          cmake -S tests/cmake_import/project -B build-import -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install
+          cmake --build build-import
+      - name: Install with Meson and non-default options
+        run: |
+          meson setup build-meson-options --prefix=${{ github.workspace }}/install-options -DMultipleHeaders=true -DDiagnostics=true -DGlobalUDLs=false
+          meson install -C build-meson-options
+      - name: Check that the options reach the installed files
+        run: |
+          test -d install-options/include/nlohmann/detail
+          cflags=$(PKG_CONFIG_PATH=${{ github.workspace }}/install-options/share/pkgconfig pkg-config --cflags nlohmann_json)
+          echo "$cflags"
+          echo "$cflags" | grep -q -- '-DJSON_DIAGNOSTICS=1'
+          echo "$cflags" | grep -q -- '-DJSON_USE_GLOBAL_UDLS=0'
+          grep -q 'JSON_USE_GLOBAL_UDLS=0;JSON_DIAGNOSTICS=1' install-options/share/cmake/nlohmann_json/nlohmann_jsonTargets.cmake
+          cmake -S tests/cmake_import/project -B build-import-options -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install-options
+          cmake --build build-import-options
+      - name: Install with Meson and the include directory outside the prefix
+        run: |
+          meson setup build-meson-split --prefix=${{ github.workspace }}/install-split --includedir=${{ github.workspace }}/install-split-dev/include
+          meson install -C build-meson-split
+          cmake -S tests/cmake_import/project -B build-import-split -DCMAKE_PREFIX_PATH=${{ github.workspace }}/install-split
+          cmake --build build-import-split
+
   ci_infer:
     runs-on: ubuntu-latest
     steps:

CMakeLists.txt

@@ -168,7 +168,30 @@ if (MSVC)
     )
 endif()
 
-# Install a pkg-config file, so other tools can find this.
+# Install a pkg-config file, so other tools can find this. It carries the same
+# compile definitions as the target above.
+set(NLOHMANN_JSON_PKGCONFIG_CFLAGS "")
+if (NOT JSON_GlobalUDLs)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_GLOBAL_UDLS=0")
+endif()
+if (NOT JSON_ImplicitConversions)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_IMPLICIT_CONVERSIONS=0")
+endif()
+if (JSON_DisableEnumSerialization)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DISABLE_ENUM_SERIALIZATION=1")
+endif()
+if (JSON_Diagnostics)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DIAGNOSTICS=1")
+endif()
+if (JSON_Diagnostic_Positions)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_DIAGNOSTIC_POSITIONS=1")
+endif()
+if (JSON_LegacyDiscardedValueComparison)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1")
+endif()
+if (JSON_StrictNulHandling)
+    string(APPEND NLOHMANN_JSON_PKGCONFIG_CFLAGS " -DJSON_STRICT_NUL_HANDLING=1")
+endif()
 configure_file(
     "${CMAKE_CURRENT_SOURCE_DIR}/cmake/pkg-config.pc.in"
     "${CMAKE_CURRENT_BINARY_DIR}/${PROJECT_NAME}.pc"

FILES.md

@@ -260,9 +260,29 @@ make BUILD.bazel
 
 The "Check amalgamation" workflow fails if the file is out of date.
 
-### `meson.build`
+### `meson.build` and `meson_options.txt`
 
-The build definition for the [Meson](https://mesonbuild.com) build system.
+Meson build definitions suitable for use as a subproject ("wrap" in Meson terminology).
+
+Projects wishing to use the wrap can execute:
+```sh
+meson wrap install nlohmann_json
+```
+
+Which allows Meson to build from source when a system provided dependency isn't available.
+
+To build directly:
+```sh
+meson setup builddir
+ninja -C builddir
+```
+
+`meson_options.txt` defines the options, which mirror the CMake options that change the library's target (for example,
+`-DDiagnostics=true`). Meson requires this file next to `meson.build`, so it is also part of `include.zip`.
+
+When installing, `meson.build` installs the headers, a pkg-config file, and the CMake package config files, so that
+`find_package(nlohmann_json)` works. As Meson cannot generate `nlohmann_jsonTargets.cmake` itself, it is created from
+the template `cmake/nlohmann_jsonTargets.cmake.in`, which is only used by Meson.
 
 ### `Package.swift`
 

Makefile

@@ -222,7 +222,7 @@ json.tar.xz:
 # We use `-X` to make the resulting ZIP file reproducible, see
 # <https://content.pivotal.io/blog/barriers-to-deterministic-reproducible-zip-files>.
 include.zip: BUILD.bazel
-	zip -9 --recurse-paths -X include.zip $(SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) BUILD.bazel MODULE.bazel meson.build LICENSE.MIT
+	zip -9 --recurse-paths -X include.zip $(SRCS) $(AMALGAMATED_FILE) $(AMALGAMATED_FWD_FILE) BUILD.bazel MODULE.bazel meson.build meson_options.txt LICENSE.MIT
 
 # Create the files for a release and add signatures and hashes.
 release: include.zip json.tar.xz

cmake/nlohmann_jsonTargets.cmake.in

@@ -0,0 +1,38 @@
+# Imported target for installations made with Meson (see meson.build).
+#
+# CMake installations generate this file with install(EXPORT ...). Meson cannot
+# do that, but as the library is header-only, the target only needs an include
+# directory, the C++ standard, and the compile definitions of the options that
+# differ from their defaults. Paths are computed relative to this file so that
+# the installation can be relocated (e.g., into a sysroot), unless includedir or
+# datadir is outside the prefix.
+
+if(TARGET @PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@)
+    return()
+endif()
+
+get_filename_component(_IMPORT_PREFIX "${CMAKE_CURRENT_LIST_DIR}/@NLOHMANN_JSON_CONFIG_TO_PREFIX@" ABSOLUTE)
+
+add_library(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ INTERFACE IMPORTED)
+set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+    INTERFACE_INCLUDE_DIRECTORIES "@NLOHMANN_JSON_INCLUDE_DIR@"
+)
+if(CMAKE_VERSION VERSION_LESS 3.8)
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_FEATURES cxx_range_for
+    )
+else()
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_FEATURES cxx_std_11
+    )
+endif()
+
+set(_NLOHMANN_JSON_COMPILE_DEFINITIONS "@NLOHMANN_JSON_COMPILE_DEFINITIONS@")
+if(_NLOHMANN_JSON_COMPILE_DEFINITIONS)
+    set_target_properties(@PROJECT_NAME@::@NLOHMANN_JSON_TARGET_NAME@ PROPERTIES
+        INTERFACE_COMPILE_DEFINITIONS "${_NLOHMANN_JSON_COMPILE_DEFINITIONS}"
+    )
+endif()
+
+unset(_NLOHMANN_JSON_COMPILE_DEFINITIONS)
+unset(_IMPORT_PREFIX)

cmake/pkg-config.pc.in

@@ -4,4 +4,4 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 Name: @PROJECT_NAME@
 Description: JSON for Modern C++
 Version: @PROJECT_VERSION@
-Cflags: -I${includedir}
+Cflags: -I${includedir}@NLOHMANN_JSON_PKGCONFIG_CFLAGS@

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

@@ -80,8 +80,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
   the end of the file was not reached when `strict` was set to true
 - Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if unsupported features from CBOR were
   used in the given input or if the input is not valid CBOR
-- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of other
-  types are not supported, as JSON object keys are always strings) or a string is malformed
+- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a string was expected as a map key,
+  but not found
 
 ## Complexity
 

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

@@ -73,8 +73,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
   the end of the file was not reached when `strict` was set to true
 - Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if unsupported features from
   MessagePack were used in the given input or if the input is not valid MessagePack
-- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a map key is not a string (keys of other
-  types are not supported, as JSON object keys are always strings) or a string is malformed
+- Throws [parse_error.113](../../home/exceptions.md#jsonexceptionparse_error113) if a string was expected as a map key,
+  but not found
 
 ## Complexity
 

docs/mkdocs/docs/features/binary_formats/cbor.md

@@ -174,20 +174,7 @@ The library maps CBOR types to JSON value types as follows:
 
 !!! warning "Object keys"
 
-    CBOR allows map keys of any type, whereas JSON only allows strings as keys in object values. Therefore, CBOR maps
-    with keys other than text strings (major type 3) are rejected with a
-    [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with `allow_exceptions` set
-    to `false`, a discarded value) naming the type of the key that was found, for instance:
-
-    ```
-    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found an unsigned integer; last byte: 0x01
-    ```
-
-    This applies to the [SAX interface](../parsing/sax_interface.md) as well, as the key is read before it is passed
-    on. This is a deliberate restriction of the library's JSON value model, not an oversight: formats built on CBOR
-    maps with integer keys, such as COSE ([RFC 9052](https://www.rfc-editor.org/rfc/rfc9052.html)) or CWT
-    ([RFC 8392](https://www.rfc-editor.org/rfc/rfc8392.html)), cannot be read with this library and need a
-    general-purpose CBOR library instead.
+    CBOR allows map keys of any type, whereas JSON only allows strings as keys in object values. Therefore, CBOR maps with keys other than UTF-8 strings are rejected.
 
 !!! warning "UTF-8 validation of text strings"
 

docs/mkdocs/docs/features/binary_formats/messagepack.md

@@ -138,21 +138,6 @@ The library maps MessagePack types to JSON value types as follows:
 
     Any MessagePack output created by `to_msgpack` can be successfully parsed by `from_msgpack`.
 
-!!! warning "Object keys"
-
-    MessagePack allows map keys of any type, whereas JSON only allows strings as keys in object values. Like the
-    JSON-compatible [profile](https://github.com/msgpack/msgpack/blob/master/spec.md#profile) sketched in the
-    MessagePack specification, this library restricts map keys to `str` values. Maps with keys of any other type are
-    rejected with a [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with
-    `allow_exceptions` set to `false`, a discarded value) naming the type of the key that was found, for instance:
-
-    ```
-    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found nil; last byte: 0xC0
-    ```
-
-    This applies to the [SAX interface](../parsing/sax_interface.md) as well, as the key is read before it is passed
-    on. Such input needs a general-purpose MessagePack library instead.
-
 !!! warning "UTF-8 validation of string values"
 
     The MessagePack specification requires `str` values (`fixstr`, `str 8`, `str 16`, `str 32`) to be valid UTF-8.

docs/mkdocs/docs/home/exceptions.md

@@ -343,20 +343,13 @@ A string could not be read from a [binary format](../features/binary_formats/ind
 string was read where one was required (for instance as a map key), the string's length specification is invalid, or
 the string's bytes are not valid UTF-8.
 
-CBOR and MessagePack allow map keys of any type, but JSON object keys are always strings. Maps with keys of any other
-type (for instance integers or `null`) are therefore not supported; see the notes on
-[CBOR](../features/binary_formats/cbor.md) and [MessagePack](../features/binary_formats/messagepack.md).
-
 !!! failure "Example messages"
 
     ```
-    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found an unsigned integer; last byte: 0x01
+    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF
     ```
     ```
-    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found nil; last byte: 0xC0
-    ```
-    ```
-    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C
+    [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack string: expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0xFF
     ```
     ```
     [json.exception.parse_error.113] parse error at byte 2: syntax error while parsing UBJSON char: byte after 'C' must be in range 0x00..0x7F; last byte: 0x82

docs/mkdocs/docs/integration/package_managers.md

@@ -121,10 +121,23 @@ meson wrap install nlohmann_json
 Please see the Meson project for any issues regarding the packaging.
 
 The provided `meson.build` can also be used as an alternative to CMake for installing `nlohmann_json` system-wide in
-which case a pkg-config file is installed. To use it, have your build system require the `nlohmann_json`
-pkg-config dependency. In Meson, it is preferred to use the
-[`dependency()`](https://mesonbuild.com/Reference-manual.html#dependency) object with a subproject fallback, rather than
-using the subproject directly.
+which case a pkg-config file and the CMake package config files are installed. To use it, have your build system require
+the `nlohmann_json` pkg-config dependency, or use [`find_package(nlohmann_json)`](cmake.md#external) in CMake. In Meson,
+it is preferred to use the [`dependency()`](https://mesonbuild.com/Reference-manual.html#dependency) object with a
+subproject fallback, rather than using the subproject directly.
+
+The options that change the library's configuration are available in Meson as well, named like the
+[CMake options](cmake.md#cmake-options) without the `JSON_` prefix: `MultipleHeaders`, `GlobalUDLs`,
+`ImplicitConversions`, `DisableEnumSerialization`, `Diagnostics`, `Diagnostic_Positions`,
+`LegacyDiscardedValueComparison`, and `StrictNulHandling`. They have the same defaults as in CMake, except that
+`MultipleHeaders` is `false`. Set them with `-D` when setting up the build, or with the subproject name as prefix when
+the library is used as a subproject:
+
+```shell
+meson setup build -Dnlohmann_json:Diagnostics=true
+```
+
+The resulting compile definitions are part of the Meson dependency, the pkg-config file, and the CMake target.
 
 ??? example "Example: Wrap"
 

include/nlohmann/detail/input/binary_reader.hpp

@@ -1324,80 +1324,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR object key
-
-    RFC 8949 allows any data item as a map key, but only strings have a
-    counterpart in JSON. A key of any other type is rejected with a message
-    naming that type, rather than the one @ref get_cbor_string gives for a
-    malformed string.
-
-    @param[out] result  created key
-
-    @return whether key creation completed
-    */
-    bool get_cbor_object_key(string_t& result)
-    {
-        // EOF and major type 3 (text string) are left to get_cbor_string
-        if (current == char_traits<char_type>::eof() || (static_cast<unsigned int>(current) & 0xE0u) == 0x60u)
-        {
-            return get_cbor_string(result);
-        }
-
-        const char* found = nullptr;
-        switch (static_cast<unsigned int>(current) >> 5u)
-        {
-            case 0:
-                found = "an unsigned integer";
-                break;
-            case 1:
-                found = "a negative integer";
-                break;
-            case 2:
-                found = "a byte string";
-                break;
-            case 4:
-                found = "an array";
-                break;
-            case 5:
-                found = "a map";
-                break;
-            case 6:
-                found = "a tag";
-                break;
-            default: // major type 7
-                switch (current)
-                {
-                    case 0xF4:
-                    case 0xF5:
-                        found = "a boolean";
-                        break;
-                    case 0xF6:
-                        found = "null";
-                        break;
-                    case 0xF7:
-                        found = "undefined";
-                        break;
-                    case 0xF9:
-                    case 0xFA:
-                    case 0xFB:
-                        found = "a floating-point number";
-                        break;
-                    case 0xFF:
-                        found = "a break stop code";
-                        break;
-                    default:
-                        found = "a simple value";
-                        break;
-                }
-                break;
-        }
-
-        auto last_token = get_token_string();
-        return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
-                                exception_message(input_format_t::cbor, concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
-    }
-
     /*!
     @brief reads a definite-length CBOR byte array
 
@@ -1642,7 +1568,7 @@ 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(!get_cbor_string(key) || !sax->key(key)))
                     {
                         return false;
                     }
@@ -2143,98 +2069,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a MessagePack object key
-
-    The MessagePack specification allows any type as a map key, but only
-    strings have a counterpart in JSON. A key of any other type is rejected
-    with a message naming that type, rather than the one @ref
-    get_msgpack_string gives for a malformed string.
-
-    @param[out] result  created key
-
-    @return whether key creation completed
-    */
-    bool get_msgpack_object_key(string_t& result)
-    {
-        const char* found = nullptr;
-        switch (current)
-        {
-            case 0xC0:
-                found = "nil";
-                break;
-            case 0xC2:
-            case 0xC3:
-                found = "a boolean";
-                break;
-            case 0xCA:
-            case 0xCB:
-                found = "a float";
-                break;
-            case 0xC4:
-            case 0xC5:
-            case 0xC6:
-                found = "a bin";
-                break;
-            case 0xC7:
-            case 0xC8:
-            case 0xC9:
-            case 0xD4:
-            case 0xD5:
-            case 0xD6:
-            case 0xD7:
-            case 0xD8:
-                found = "an ext";
-                break;
-            case 0xCC:
-            case 0xCD:
-            case 0xCE:
-            case 0xCF:
-            case 0xD0:
-            case 0xD1:
-            case 0xD2:
-            case 0xD3:
-                found = "an integer";
-                break;
-            case 0xDC:
-            case 0xDD:
-                found = "an array";
-                break;
-            case 0xDE:
-            case 0xDF:
-                found = "a map";
-                break;
-            default:
-                // fixint, fixmap, and fixarray; strings, EOF, and the unused
-                // byte 0xC1 are left to get_msgpack_string
-                if (current == char_traits<char_type>::eof())
-                {
-                    return get_msgpack_string(result);
-                }
-                if (current <= 0x7F || current >= 0xE0)
-                {
-                    found = "an integer";
-                }
-                else if (current <= 0x8F)
-                {
-                    found = "a map";
-                }
-                else if (current <= 0x9F)
-                {
-                    found = "an array";
-                }
-                else
-                {
-                    return get_msgpack_string(result);
-                }
-                break;
-        }
-
-        auto last_token = get_token_string();
-        return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
-                                exception_message(input_format_t::msgpack, concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
-    }
-
     /*!
     @brief reads a MessagePack byte array
 
@@ -2397,7 +2231,7 @@ class binary_reader
                 {
                     get();
                     key.clear();
-                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_object_key(key) || !sax->key(key)))
+                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
                     {
                         return false;
                     }

include/nlohmann/detail/input/lexer.hpp

@@ -206,6 +206,7 @@ class lexer : public lexer_base<BasicJsonType>
     explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
+        , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
         , discard_number_values(discard_number_values_)
     {}
 
@@ -221,7 +222,8 @@ class lexer : public lexer_base<BasicJsonType>
     // locales
     /////////////////////
 
-    /// return the decimal point of the current locale
+    /// return the locale-dependent decimal point
+    JSON_HEDLEY_PURE
     static char get_decimal_point() noexcept
     {
         const auto* loc = localeconv();
@@ -1090,10 +1092,9 @@ class lexer : public lexer_base<BasicJsonType>
             token_type::value_float if number could be successfully scanned,
             token_type::parse_error otherwise
 
-    @note The scanner is independent of the current locale: token_buffer
-          always holds `.`. Only the std::strtod fallback of convert_number()
-          depends on the locale, and it looks up the decimal point right
-          before converting (see convert_float_locale_aware()).
+    @note The scanner is independent of the current locale. Internally, the
+          locale's decimal point is used instead of `.` to work with the
+          locale-dependent converters.
     */
     token_type scan_number()  // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
     {
@@ -1182,7 +1183,7 @@ scan_number_zero:
         {
             case '.':
             {
-                add(current);
+                add(decimal_point_char);
                 decimal_point_position = token_buffer.size() - 1;
                 goto scan_number_decimal1;
             }
@@ -1219,7 +1220,7 @@ scan_number_any1:
 
             case '.':
             {
-                add(current);
+                add(decimal_point_char);
                 decimal_point_position = token_buffer.size() - 1;
                 goto scan_number_decimal1;
             }
@@ -1461,9 +1462,9 @@ scan_number_done:
 
         // Only a number below 1 can carry further insignificant zeros, and only
         // while the count stays at the limit does removing them change the
-        // answer - so this loop is skipped for all but a few tokens. The
-        // fraction is located through decimal_point_position rather than by
-        // searching '.'.
+        // answer - so this loop is skipped for all but a few tokens. Note
+        // token_buffer holds the locale's decimal point, so the fraction is
+        // located through decimal_point_position rather than by searching '.'.
         if (lead_zero != 0)
         {
             JSON_ASSERT(has_dot != 0); // an integer "0" cannot reach the limit
@@ -1481,8 +1482,8 @@ scan_number_done:
     @brief convert the number text in token_buffer to its value and token type
 
     The digit sequence in token_buffer has already been validated (by the
-    scan_number() state machine or by the contiguous fast path) and holds '.'
-    as decimal point, independent of the locale. Integers are parsed first and fall
+    scan_number() state machine or by the contiguous fast path) and holds the
+    locale decimal point in place of '.'. Integers are parsed first and fall
     back to floating point on overflow. This is shared so both scanners produce
     identical results.
 
@@ -1562,7 +1563,7 @@ scan_number_done:
         // integer conversion above overflowed. Prefer std::from_chars
         // (Eisel-Lemire, locale-independent, correctly rounded) when available;
         // otherwise the exact Clinger fast path (double only); otherwise the
-        // locale-aware strtof/strtod/strtold.
+        // locale-aware strtof/strtod.
         if (parse_float_from_chars(num_begin, num_end, value_float))
         {
             return token_type::value_float;
@@ -1571,75 +1572,26 @@ scan_number_done:
         // extra pass over the token's bytes, which otherwise shows up on
         // high-precision inputs such as canada.json
         if (mantissa_fits_clinger(mantissa_end)
-                && parse_float_fast(num_begin, num_end, value_float))
+                && parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
         {
             return token_type::value_float;
         }
 
-        convert_float_locale_aware();
+        char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+        strtof(value_float, token_buffer.data(), &endptr);
+
+        // we checked the number format before
+        JSON_ASSERT(endptr == token_buffer.data() + token_buffer.size());
+
         return token_type::value_float;
     }
 
-    /*!
-    @brief convert the float in token_buffer with strtof/strtod/strtold
-
-    These functions expect the decimal point of the *current* locale, so it is
-    looked up right before the conversion instead of once when the lexer is
-    constructed: a locale change in between (by a parser callback, a SAX
-    handler, or another thread) must not truncate the value (#5198). The
-    token has been validated before, so if the conversion stops early and the
-    decimal point changed in the meantime, the locale changed between the
-    lookup and the call, and the conversion is repeated with the new decimal
-    point. If the decimal point did not change, a retry cannot succeed: the
-    locale's decimal point is not a single character (e.g., the two-byte
-    U+066B of ar_EG.UTF-8 or fa_IR.UTF-8) and cannot be substituted in place.
-    The value strtod parsed up to that point is kept, as before this change.
-
-    Note that changing the locale in another thread *while* strtod runs is
-    undefined behavior of the C library, which this function cannot prevent.
-    */
-    void convert_float_locale_aware()
-    {
-        const bool has_dot = decimal_point_position != std::string::npos;
-        char decimal_point = get_decimal_point();
-        for (;;)
-        {
-            const bool substitute = has_dot && decimal_point != '.';
-            if (substitute)
-            {
-                token_buffer[decimal_point_position] = static_cast<typename string_t::value_type>(decimal_point);
-            }
-
-            char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
-            strtof(value_float, token_buffer.data(), &endptr);
-
-            if (substitute)
-            {
-                // get_string() hands the token to the SAX interface with '.'
-                token_buffer[decimal_point_position] = '.';
-            }
-
-            if (JSON_HEDLEY_LIKELY(endptr == token_buffer.data() + token_buffer.size()))
-            {
-                return;
-            }
-
-            // retry only if the locale changed; otherwise, this would loop forever
-            const char current_decimal_point = get_decimal_point();
-            if (current_decimal_point == decimal_point)
-            {
-                return;
-            }
-            decimal_point = current_decimal_point;
-        }
-    }
-
     /*!
     @brief contiguous fast path for scanning a number
 
     Parses the whole number token straight from the input buffer, avoiding the
     per-character get()/add() of scan_number(). On success it fills token_buffer
-    (as scan_number() does) and
+    (with the locale decimal point substituted, as scan_number() does) and
     returns the token type. On anything it does not fully recognize as a
     well-formed number it makes no state change and returns
     token_type::uninitialized, so the caller falls back to scan_number(), which
@@ -1755,11 +1707,16 @@ scan_number_done:
         }
 #endif
 
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
+        // materialize the token exactly as scan_number() would, substituting the
+        // locale decimal point so convert_number()'s strtof fallback stays valid.
+        // reset() already cleared token_buffer, so append() fills it (assign() is
+        // avoided because custom string_t types need not provide it)
         token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
-        decimal_point_position = dot_index;
+        if (dot_index != std::string::npos)
+        {
+            token_buffer[dot_index] = static_cast<typename string_t::value_type>(decimal_point_char);
+            decimal_point_position = dot_index;
+        }
 
         ia.bulk_skip(len - 1);
         position.chars_read_total += (len - 1);
@@ -2026,7 +1983,11 @@ scan_number_done:
     /// return current string value (implicitly resets the token; useful only once)
     string_t& get_string()
     {
-        // a number token holds '.' regardless of the locale (#4084)
+        // translate decimal points from locale back to '.' (#4084)
+        if (decimal_point_char != '.' && decimal_point_position != std::string::npos)
+        {
+            token_buffer[decimal_point_position] = '.';
+        }
         return token_buffer;
     }
 
@@ -2322,7 +2283,9 @@ scan_number_done:
     number_unsigned_t value_unsigned = 0;
     number_float_t value_float = 0;
 
-    /// the position of the decimal point in token_buffer
+    /// the decimal point
+    const char_int_type decimal_point_char = '.';
+    /// the position of the decimal point in the input
     std::size_t decimal_point_position = std::string::npos;
 
     /// whether the caller (e.g. accept()/json_sax_acceptor) only needs the

include/nlohmann/detail/input/number_parse.hpp

@@ -118,12 +118,14 @@ std::strtod. The parser only activates for number_float_t == double; float and
 long double keep the std::strtof/std::strtold paths (see the templated overload
 below).
 
-@param[in]  first  pointer to the first character of the number
-@param[in]  last   pointer past the last character
-@param[out] out    the parsed value on success
+@param[in]  first          pointer to the first character of the number
+@param[in]  last           pointer past the last character
+@param[in]  decimal_point  the (locale-dependent) decimal point character
+@param[out] out            the parsed value on success
 @return true if the value was parsed exactly; false to fall back to strtod
 */
-inline bool parse_float_fast(const char* first, const char* last, double& out) noexcept
+template<typename DecimalPointType>
+bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
 {
 #if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
     // Clinger's fast path is only exact when double operations are evaluated in
@@ -134,6 +136,7 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
     // std::from_chars / std::strtod path.
     static_cast<void>(first);
     static_cast<void>(last);
+    static_cast<void>(decimal_point);
     static_cast<void>(out);
     return false;
 #else
@@ -172,7 +175,7 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
             ++num_digits;
             fractional_digits += static_cast<int>(seen_dot);
         }
-        else if (c == '.')
+        else if (static_cast<DecimalPointType>(c) == decimal_point)
         {
             if (JSON_HEDLEY_UNLIKELY(seen_dot))
             {
@@ -257,8 +260,8 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
 }
 
 /// fast float path is only exact for `double`; decline for float/long double
-template<typename FloatType>
-bool parse_float_fast(const char* /*first*/, const char* /*last*/, FloatType& /*out*/) noexcept
+template<typename DecimalPointType, typename FloatType>
+bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointType /*decimal_point*/, FloatType& /*out*/) noexcept
 {
     return false;
 }
@@ -270,7 +273,9 @@ std::from_chars is locale-independent, correctly rounded, and - via the
 Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
 over the whole value range (not just the Clinger subset). It is used only when
 __cpp_lib_to_chars indicates full floating-point support and only when it
-consumes the entire token ([first, last)). An under-/overflow (result_out_of_range) also declines, so
+consumes the entire token ([first, last)); a partial parse means the buffer
+uses a non-'.' locale decimal point, in which case the caller falls back to the
+locale-aware path. An under-/overflow (result_out_of_range) also declines, so
 the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
 expects (side-stepping the P4168 divergence between implementations).
 

meson.build

@@ -2,23 +2,111 @@ project('nlohmann_json',
     'cpp',
     version : '3.12.0',
     license : 'MIT',
+    meson_version : '>= 0.64',
+    default_options: ['cpp_std=c++11'],
 )
 
+if get_option('MultipleHeaders')
+    incdir = 'include'
+else
+    incdir = 'single_include'
+endif
+
+# The same compile definitions as the CMake target (see target_compile_definitions
+# in CMakeLists.txt): only an option that differs from its default adds one.
+json_defines = []
+if not get_option('GlobalUDLs')
+    json_defines += 'JSON_USE_GLOBAL_UDLS=0'
+endif
+if not get_option('ImplicitConversions')
+    json_defines += 'JSON_USE_IMPLICIT_CONVERSIONS=0'
+endif
+if get_option('DisableEnumSerialization')
+    json_defines += 'JSON_DISABLE_ENUM_SERIALIZATION=1'
+endif
+if get_option('Diagnostics')
+    json_defines += 'JSON_DIAGNOSTICS=1'
+endif
+if get_option('Diagnostic_Positions')
+    json_defines += 'JSON_DIAGNOSTIC_POSITIONS=1'
+endif
+if get_option('LegacyDiscardedValueComparison')
+    json_defines += 'JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON=1'
+endif
+if get_option('StrictNulHandling')
+    json_defines += 'JSON_STRICT_NUL_HANDLING=1'
+endif
+
+cpp_args = []
+foreach define : json_defines
+    cpp_args += '-D' + define
+endforeach
+
 nlohmann_json_dep = declare_dependency(
-    include_directories: include_directories('single_include')
+    compile_args: cpp_args,
+    include_directories: include_directories(incdir)
 )
+meson.override_dependency('nlohmann_json', nlohmann_json_dep)
 
+# The multi-header version under the name earlier versions of this file used
 nlohmann_json_multiple_headers = declare_dependency(
+    compile_args: cpp_args,
     include_directories: include_directories('include')
 )
 
 if not meson.is_subproject()
-install_headers('single_include/nlohmann/json.hpp', subdir: 'nlohmann')
-install_headers('single_include/nlohmann/json_fwd.hpp', subdir: 'nlohmann')
+    install_subdir(
+        incdir / 'nlohmann',
+        install_dir: get_option('includedir'),
+        install_tag: 'devel',
+    )
 
-pkgc = import('pkgconfig')
-pkgc.generate(name: 'nlohmann_json',
-    version: meson.project_version(),
-    description: 'JSON for Modern C++'
-)
+    pkgc = import('pkgconfig')
+    pkgc.generate(name: 'nlohmann_json',
+        version: meson.project_version(),
+        description: 'JSON for Modern C++',
+        extra_cflags: cpp_args,
+        install_dir: get_option('datadir') / 'pkgconfig',
+    )
+
+    # CMake package config files, so that find_package(nlohmann_json) works. The
+    # include directory is given relative to the config files, so that the
+    # installation can be relocated. This is not possible if includedir or datadir
+    # is an absolute path outside the prefix (e.g., with the separate outputs of
+    # Nix); then the absolute include directory is used, as CMake does.
+    fs = import('fs')
+    cmake_install_dir = get_option('datadir') / 'cmake' / meson.project_name()
+    cmake_to_prefix = []
+    if fs.is_absolute(get_option('includedir')) or fs.is_absolute(cmake_install_dir)
+        cmake_include_dir = (get_option('prefix') / get_option('includedir')).replace('\\', '/')
+    else
+        foreach component : cmake_install_dir.split('/')
+            cmake_to_prefix += '..'
+        endforeach
+        cmake_include_dir = '${_IMPORT_PREFIX}/' + get_option('includedir')
+    endif
+
+    cmake_conf = configuration_data()
+    cmake_conf.set('PROJECT_NAME', meson.project_name())
+    cmake_conf.set('PROJECT_VERSION', meson.project_version())
+    cmake_conf.set('PROJECT_VERSION_MAJOR', meson.project_version().split('.')[0])
+    cmake_conf.set('NLOHMANN_JSON_TARGET_NAME', meson.project_name())
+    cmake_conf.set('NLOHMANN_JSON_TARGETS_EXPORT_NAME', meson.project_name() + 'Targets')
+    cmake_conf.set('NLOHMANN_JSON_INCLUDE_DIR', cmake_include_dir)
+    cmake_conf.set('NLOHMANN_JSON_CONFIG_TO_PREFIX', '/'.join(cmake_to_prefix))
+    cmake_conf.set('NLOHMANN_JSON_COMPILE_DEFINITIONS', ';'.join(json_defines))
+
+    foreach cmake_file : [
+        ['cmake/config.cmake.in', 'nlohmann_jsonConfig.cmake'],
+        ['cmake/nlohmann_jsonConfigVersion.cmake.in', 'nlohmann_jsonConfigVersion.cmake'],
+        ['cmake/nlohmann_jsonTargets.cmake.in', 'nlohmann_jsonTargets.cmake'],
+    ]
+        configure_file(
+            input: cmake_file[0],
+            output: cmake_file[1],
+            configuration: cmake_conf,
+            format: 'cmake@',
+            install_dir: cmake_install_dir,
+        )
+    endforeach
 endif

meson_options.txt

@@ -0,0 +1,48 @@
+option(
+    'MultipleHeaders',
+    type: 'boolean',
+    value: false,
+    description: 'Use non-amalgamated version of the library',
+)
+option(
+    'GlobalUDLs',
+    type: 'boolean',
+    value: true,
+    description: 'Place user-defined string literals in the global namespace',
+)
+option(
+    'ImplicitConversions',
+    type: 'boolean',
+    value: true,
+    description: 'Enable implicit conversions',
+)
+option(
+    'DisableEnumSerialization',
+    type: 'boolean',
+    value: false,
+    description: 'Disable default integer enum serialization',
+)
+option(
+    'Diagnostics',
+    type: 'boolean',
+    value: false,
+    description: 'Use extended diagnostic messages',
+)
+option(
+    'Diagnostic_Positions',
+    type: 'boolean',
+    value: false,
+    description: 'Enable diagnostic positions',
+)
+option(
+    'LegacyDiscardedValueComparison',
+    type: 'boolean',
+    value: false,
+    description: 'Enable legacy discarded value comparison',
+)
+option(
+    'StrictNulHandling',
+    type: 'boolean',
+    value: false,
+    description: 'Enable strict NUL-byte handling',
+)

single_include/nlohmann/json.hpp

@@ -8605,12 +8605,14 @@ std::strtod. The parser only activates for number_float_t == double; float and
 long double keep the std::strtof/std::strtold paths (see the templated overload
 below).
 
-@param[in]  first  pointer to the first character of the number
-@param[in]  last   pointer past the last character
-@param[out] out    the parsed value on success
+@param[in]  first          pointer to the first character of the number
+@param[in]  last           pointer past the last character
+@param[in]  decimal_point  the (locale-dependent) decimal point character
+@param[out] out            the parsed value on success
 @return true if the value was parsed exactly; false to fall back to strtod
 */
-inline bool parse_float_fast(const char* first, const char* last, double& out) noexcept
+template<typename DecimalPointType>
+bool parse_float_fast(const char* first, const char* last, DecimalPointType decimal_point, double& out) noexcept
 {
 #if defined(FLT_EVAL_METHOD) && FLT_EVAL_METHOD != 0
     // Clinger's fast path is only exact when double operations are evaluated in
@@ -8621,6 +8623,7 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
     // std::from_chars / std::strtod path.
     static_cast<void>(first);
     static_cast<void>(last);
+    static_cast<void>(decimal_point);
     static_cast<void>(out);
     return false;
 #else
@@ -8659,7 +8662,7 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
             ++num_digits;
             fractional_digits += static_cast<int>(seen_dot);
         }
-        else if (c == '.')
+        else if (static_cast<DecimalPointType>(c) == decimal_point)
         {
             if (JSON_HEDLEY_UNLIKELY(seen_dot))
             {
@@ -8744,8 +8747,8 @@ inline bool parse_float_fast(const char* first, const char* last, double& out) n
 }
 
 /// fast float path is only exact for `double`; decline for float/long double
-template<typename FloatType>
-bool parse_float_fast(const char* /*first*/, const char* /*last*/, FloatType& /*out*/) noexcept
+template<typename DecimalPointType, typename FloatType>
+bool parse_float_fast(const char* /*first*/, const char* /*last*/, DecimalPointType /*decimal_point*/, FloatType& /*out*/) noexcept
 {
     return false;
 }
@@ -8757,7 +8760,9 @@ std::from_chars is locale-independent, correctly rounded, and - via the
 Eisel-Lemire algorithm in modern standard libraries - much faster than strtod
 over the whole value range (not just the Clinger subset). It is used only when
 __cpp_lib_to_chars indicates full floating-point support and only when it
-consumes the entire token ([first, last)). An under-/overflow (result_out_of_range) also declines, so
+consumes the entire token ([first, last)); a partial parse means the buffer
+uses a non-'.' locale decimal point, in which case the caller falls back to the
+locale-aware path. An under-/overflow (result_out_of_range) also declines, so
 the caller's strtod fallback supplies the well-defined ±inf/0 result the parser
 expects (side-stepping the P4168 divergence between implementations).
 
@@ -9298,6 +9303,7 @@ class lexer : public lexer_base<BasicJsonType>
     explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
         : ia(std::move(adapter))
         , ignore_comments(ignore_comments_)
+        , decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
         , discard_number_values(discard_number_values_)
     {}
 
@@ -9313,7 +9319,8 @@ class lexer : public lexer_base<BasicJsonType>
     // locales
     /////////////////////
 
-    /// return the decimal point of the current locale
+    /// return the locale-dependent decimal point
+    JSON_HEDLEY_PURE
     static char get_decimal_point() noexcept
     {
         const auto* loc = localeconv();
@@ -10182,10 +10189,9 @@ class lexer : public lexer_base<BasicJsonType>
             token_type::value_float if number could be successfully scanned,
             token_type::parse_error otherwise
 
-    @note The scanner is independent of the current locale: token_buffer
-          always holds `.`. Only the std::strtod fallback of convert_number()
-          depends on the locale, and it looks up the decimal point right
-          before converting (see convert_float_locale_aware()).
+    @note The scanner is independent of the current locale. Internally, the
+          locale's decimal point is used instead of `.` to work with the
+          locale-dependent converters.
     */
     token_type scan_number()  // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
     {
@@ -10274,7 +10280,7 @@ scan_number_zero:
         {
             case '.':
             {
-                add(current);
+                add(decimal_point_char);
                 decimal_point_position = token_buffer.size() - 1;
                 goto scan_number_decimal1;
             }
@@ -10311,7 +10317,7 @@ scan_number_any1:
 
             case '.':
             {
-                add(current);
+                add(decimal_point_char);
                 decimal_point_position = token_buffer.size() - 1;
                 goto scan_number_decimal1;
             }
@@ -10553,9 +10559,9 @@ scan_number_done:
 
         // Only a number below 1 can carry further insignificant zeros, and only
         // while the count stays at the limit does removing them change the
-        // answer - so this loop is skipped for all but a few tokens. The
-        // fraction is located through decimal_point_position rather than by
-        // searching '.'.
+        // answer - so this loop is skipped for all but a few tokens. Note
+        // token_buffer holds the locale's decimal point, so the fraction is
+        // located through decimal_point_position rather than by searching '.'.
         if (lead_zero != 0)
         {
             JSON_ASSERT(has_dot != 0); // an integer "0" cannot reach the limit
@@ -10573,8 +10579,8 @@ scan_number_done:
     @brief convert the number text in token_buffer to its value and token type
 
     The digit sequence in token_buffer has already been validated (by the
-    scan_number() state machine or by the contiguous fast path) and holds '.'
-    as decimal point, independent of the locale. Integers are parsed first and fall
+    scan_number() state machine or by the contiguous fast path) and holds the
+    locale decimal point in place of '.'. Integers are parsed first and fall
     back to floating point on overflow. This is shared so both scanners produce
     identical results.
 
@@ -10654,7 +10660,7 @@ scan_number_done:
         // integer conversion above overflowed. Prefer std::from_chars
         // (Eisel-Lemire, locale-independent, correctly rounded) when available;
         // otherwise the exact Clinger fast path (double only); otherwise the
-        // locale-aware strtof/strtod/strtold.
+        // locale-aware strtof/strtod.
         if (parse_float_from_chars(num_begin, num_end, value_float))
         {
             return token_type::value_float;
@@ -10663,75 +10669,26 @@ scan_number_done:
         // extra pass over the token's bytes, which otherwise shows up on
         // high-precision inputs such as canada.json
         if (mantissa_fits_clinger(mantissa_end)
-                && parse_float_fast(num_begin, num_end, value_float))
+                && parse_float_fast(num_begin, num_end, decimal_point_char, value_float))
         {
             return token_type::value_float;
         }
 
-        convert_float_locale_aware();
+        char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+        strtof(value_float, token_buffer.data(), &endptr);
+
+        // we checked the number format before
+        JSON_ASSERT(endptr == token_buffer.data() + token_buffer.size());
+
         return token_type::value_float;
     }
 
-    /*!
-    @brief convert the float in token_buffer with strtof/strtod/strtold
-
-    These functions expect the decimal point of the *current* locale, so it is
-    looked up right before the conversion instead of once when the lexer is
-    constructed: a locale change in between (by a parser callback, a SAX
-    handler, or another thread) must not truncate the value (#5198). The
-    token has been validated before, so if the conversion stops early and the
-    decimal point changed in the meantime, the locale changed between the
-    lookup and the call, and the conversion is repeated with the new decimal
-    point. If the decimal point did not change, a retry cannot succeed: the
-    locale's decimal point is not a single character (e.g., the two-byte
-    U+066B of ar_EG.UTF-8 or fa_IR.UTF-8) and cannot be substituted in place.
-    The value strtod parsed up to that point is kept, as before this change.
-
-    Note that changing the locale in another thread *while* strtod runs is
-    undefined behavior of the C library, which this function cannot prevent.
-    */
-    void convert_float_locale_aware()
-    {
-        const bool has_dot = decimal_point_position != std::string::npos;
-        char decimal_point = get_decimal_point();
-        for (;;)
-        {
-            const bool substitute = has_dot && decimal_point != '.';
-            if (substitute)
-            {
-                token_buffer[decimal_point_position] = static_cast<typename string_t::value_type>(decimal_point);
-            }
-
-            char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
-            strtof(value_float, token_buffer.data(), &endptr);
-
-            if (substitute)
-            {
-                // get_string() hands the token to the SAX interface with '.'
-                token_buffer[decimal_point_position] = '.';
-            }
-
-            if (JSON_HEDLEY_LIKELY(endptr == token_buffer.data() + token_buffer.size()))
-            {
-                return;
-            }
-
-            // retry only if the locale changed; otherwise, this would loop forever
-            const char current_decimal_point = get_decimal_point();
-            if (current_decimal_point == decimal_point)
-            {
-                return;
-            }
-            decimal_point = current_decimal_point;
-        }
-    }
-
     /*!
     @brief contiguous fast path for scanning a number
 
     Parses the whole number token straight from the input buffer, avoiding the
     per-character get()/add() of scan_number(). On success it fills token_buffer
-    (as scan_number() does) and
+    (with the locale decimal point substituted, as scan_number() does) and
     returns the token type. On anything it does not fully recognize as a
     well-formed number it makes no state change and returns
     token_type::uninitialized, so the caller falls back to scan_number(), which
@@ -10847,11 +10804,16 @@ scan_number_done:
         }
 #endif
 
-        // materialize the token exactly as scan_number() would. reset() already
-        // cleared token_buffer, so append() fills it (assign() is avoided
-        // because custom string_t types need not provide it)
+        // materialize the token exactly as scan_number() would, substituting the
+        // locale decimal point so convert_number()'s strtof fallback stays valid.
+        // reset() already cleared token_buffer, so append() fills it (assign() is
+        // avoided because custom string_t types need not provide it)
         token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
-        decimal_point_position = dot_index;
+        if (dot_index != std::string::npos)
+        {
+            token_buffer[dot_index] = static_cast<typename string_t::value_type>(decimal_point_char);
+            decimal_point_position = dot_index;
+        }
 
         ia.bulk_skip(len - 1);
         position.chars_read_total += (len - 1);
@@ -11118,7 +11080,11 @@ scan_number_done:
     /// return current string value (implicitly resets the token; useful only once)
     string_t& get_string()
     {
-        // a number token holds '.' regardless of the locale (#4084)
+        // translate decimal points from locale back to '.' (#4084)
+        if (decimal_point_char != '.' && decimal_point_position != std::string::npos)
+        {
+            token_buffer[decimal_point_position] = '.';
+        }
         return token_buffer;
     }
 
@@ -11414,7 +11380,9 @@ scan_number_done:
     number_unsigned_t value_unsigned = 0;
     number_float_t value_float = 0;
 
-    /// the position of the decimal point in token_buffer
+    /// the decimal point
+    const char_int_type decimal_point_char = '.';
+    /// the position of the decimal point in the input
     std::size_t decimal_point_position = std::string::npos;
 
     /// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
@@ -14091,80 +14059,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a CBOR object key
-
-    RFC 8949 allows any data item as a map key, but only strings have a
-    counterpart in JSON. A key of any other type is rejected with a message
-    naming that type, rather than the one @ref get_cbor_string gives for a
-    malformed string.
-
-    @param[out] result  created key
-
-    @return whether key creation completed
-    */
-    bool get_cbor_object_key(string_t& result)
-    {
-        // EOF and major type 3 (text string) are left to get_cbor_string
-        if (current == char_traits<char_type>::eof() || (static_cast<unsigned int>(current) & 0xE0u) == 0x60u)
-        {
-            return get_cbor_string(result);
-        }
-
-        const char* found = nullptr;
-        switch (static_cast<unsigned int>(current) >> 5u)
-        {
-            case 0:
-                found = "an unsigned integer";
-                break;
-            case 1:
-                found = "a negative integer";
-                break;
-            case 2:
-                found = "a byte string";
-                break;
-            case 4:
-                found = "an array";
-                break;
-            case 5:
-                found = "a map";
-                break;
-            case 6:
-                found = "a tag";
-                break;
-            default: // major type 7
-                switch (current)
-                {
-                    case 0xF4:
-                    case 0xF5:
-                        found = "a boolean";
-                        break;
-                    case 0xF6:
-                        found = "null";
-                        break;
-                    case 0xF7:
-                        found = "undefined";
-                        break;
-                    case 0xF9:
-                    case 0xFA:
-                    case 0xFB:
-                        found = "a floating-point number";
-                        break;
-                    case 0xFF:
-                        found = "a break stop code";
-                        break;
-                    default:
-                        found = "a simple value";
-                        break;
-                }
-                break;
-        }
-
-        auto last_token = get_token_string();
-        return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
-                                exception_message(input_format_t::cbor, concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
-    }
-
     /*!
     @brief reads a definite-length CBOR byte array
 
@@ -14409,7 +14303,7 @@ 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(!get_cbor_string(key) || !sax->key(key)))
                     {
                         return false;
                     }
@@ -14910,98 +14804,6 @@ class binary_reader
         }
     }
 
-    /*!
-    @brief reads a MessagePack object key
-
-    The MessagePack specification allows any type as a map key, but only
-    strings have a counterpart in JSON. A key of any other type is rejected
-    with a message naming that type, rather than the one @ref
-    get_msgpack_string gives for a malformed string.
-
-    @param[out] result  created key
-
-    @return whether key creation completed
-    */
-    bool get_msgpack_object_key(string_t& result)
-    {
-        const char* found = nullptr;
-        switch (current)
-        {
-            case 0xC0:
-                found = "nil";
-                break;
-            case 0xC2:
-            case 0xC3:
-                found = "a boolean";
-                break;
-            case 0xCA:
-            case 0xCB:
-                found = "a float";
-                break;
-            case 0xC4:
-            case 0xC5:
-            case 0xC6:
-                found = "a bin";
-                break;
-            case 0xC7:
-            case 0xC8:
-            case 0xC9:
-            case 0xD4:
-            case 0xD5:
-            case 0xD6:
-            case 0xD7:
-            case 0xD8:
-                found = "an ext";
-                break;
-            case 0xCC:
-            case 0xCD:
-            case 0xCE:
-            case 0xCF:
-            case 0xD0:
-            case 0xD1:
-            case 0xD2:
-            case 0xD3:
-                found = "an integer";
-                break;
-            case 0xDC:
-            case 0xDD:
-                found = "an array";
-                break;
-            case 0xDE:
-            case 0xDF:
-                found = "a map";
-                break;
-            default:
-                // fixint, fixmap, and fixarray; strings, EOF, and the unused
-                // byte 0xC1 are left to get_msgpack_string
-                if (current == char_traits<char_type>::eof())
-                {
-                    return get_msgpack_string(result);
-                }
-                if (current <= 0x7F || current >= 0xE0)
-                {
-                    found = "an integer";
-                }
-                else if (current <= 0x8F)
-                {
-                    found = "a map";
-                }
-                else if (current <= 0x9F)
-                {
-                    found = "an array";
-                }
-                else
-                {
-                    return get_msgpack_string(result);
-                }
-                break;
-        }
-
-        auto last_token = get_token_string();
-        return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
-                                exception_message(input_format_t::msgpack, concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
-    }
-
     /*!
     @brief reads a MessagePack byte array
 
@@ -15164,7 +14966,7 @@ class binary_reader
                 {
                     get();
                     key.clear();
-                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_object_key(key) || !sax->key(key)))
+                    if (JSON_HEDLEY_UNLIKELY(!get_msgpack_string(key) || !sax->key(key)))
                     {
                         return false;
                     }

tests/src/unit-cbor.cpp

@@ -1830,51 +1830,10 @@ TEST_CASE("CBOR")
         SECTION("invalid string in map")
         {
             json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
             CHECK(json::from_cbor(std::vector<uint8_t>({0xa1, 0xff, 0x01}), true, false).is_discarded());
         }
 
-        SECTION("non-string key (see #2766 and #3381)")
-        {
-            // only text strings map to JSON object keys; any other key is
-            // rejected with a message naming its type
-            const std::vector<std::pair<std::vector<std::uint8_t>, std::string>> cases =
-            {
-                {{0xA1, 0x01, 0x01}, "an unsigned integer; last byte: 0x01"},
-                {{0xA1, 0x20, 0x01}, "a negative integer; last byte: 0x20"},
-                {{0xA1, 0x41, 0x61, 0x01}, "a byte string; last byte: 0x41"},
-                {{0xA1, 0x80, 0x01}, "an array; last byte: 0x80"},
-                {{0xA1, 0xA0, 0x01}, "a map; last byte: 0xA0"},
-                {{0xA1, 0xC0, 0x61, 0x61, 0x01}, "a tag; last byte: 0xC0"},
-                {{0xA1, 0xF4, 0x01}, "a boolean; last byte: 0xF4"},
-                {{0xA1, 0xF5, 0x01}, "a boolean; last byte: 0xF5"},
-                {{0xA1, 0xF6, 0x01}, "null; last byte: 0xF6"},
-                {{0xA1, 0xF7, 0x01}, "undefined; last byte: 0xF7"},
-                {{0xA1, 0xF9, 0x3C, 0x00, 0x01}, "a floating-point number; last byte: 0xF9"},
-                {{0xA1, 0xFA, 0x3F, 0x80, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFA"},
-                {{0xA1, 0xFB, 0x3F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "a floating-point number; last byte: 0xFB"},
-                {{0xA1, 0xE0, 0x01}, "a simple value; last byte: 0xE0"},
-                {{0xA1, 0xF8, 0x20, 0x01}, "a simple value; last byte: 0xF8"},
-                // indefinite-length map
-                {{0xBF, 0x01, 0x01, 0xFF}, "an unsigned integer; last byte: 0x01"},
-            };
-
-            for (const auto& c : cases)
-            {
-                CAPTURE(c.first)
-                const std::string expected = "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found " + c.second;
-                json _;
-                CHECK_THROWS_WITH_AS(_ = json::from_cbor(c.first), expected.c_str(), json::parse_error&);
-                CHECK(json::from_cbor(c.first, true, false).is_discarded());
-            }
-
-            // a key of major type 3 with a reserved length is still reported as
-            // a malformed string, and a missing key as the end of input
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x7C, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C", json::parse_error&);
-        }
-
         SECTION("invalid UTF-8 in string (see #5529)")
         {
             // a two-character text string (major type 3) whose bytes are not
@@ -2325,7 +2284,7 @@ TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
     SECTION("a break marker outside an indefinite-length string is not a string")
     {
         // 0xFF only closes a string that was opened; on its own it is not one
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found a break stop code; last byte: 0xFF", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
     }
 }
 

tests/src/unit-class_lexer.cpp

@@ -666,7 +666,7 @@ TEST_CASE("parse_float_fast declines what it cannot convert exactly")
     // always safe: the caller then falls back to a slower, exact conversion.
     const auto fast = [](const std::string & s, double & out)
     {
-        return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), out);
+        return nlohmann::detail::parse_float_fast(s.data(), s.data() + s.size(), '.', out);
     };
     double out = 0;
 

tests/src/unit-locale-cpp.cpp

@@ -12,12 +12,7 @@
 #include <nlohmann/json.hpp>
 using nlohmann::json;
 
-#include <array>
 #include <clocale>
-#include <map>
-#include <string>
-#include <utility>
-#include <vector>
 
 struct ParserImpl final: public nlohmann::json_sax<json>
 {
@@ -180,208 +175,3 @@ TEST_CASE("locale-dependent test (LC_NUMERIC=de_DE)")
         MESSAGE("locale de_DE is not usable");
     }
 }
-
-namespace
-{
-// records the numbers of a flat array and switches LC_NUMERIC to the given
-// locale once the array opens - after the lexer was constructed, but before
-// any number in the array is lexed
-struct LocaleSwitchingSax final: public nlohmann::json_sax<json>
-{
-    explicit LocaleSwitchingSax(const char* switch_to)
-        : locale_after_open(switch_to)
-    {}
-
-    bool null() override
-    {
-        return true;
-    }
-    bool boolean(bool /*val*/) override
-    {
-        return true;
-    }
-    bool number_integer(json::number_integer_t /*val*/) override
-    {
-        return true;
-    }
-    bool number_unsigned(json::number_unsigned_t /*val*/) override
-    {
-        return true;
-    }
-    bool number_float(json::number_float_t val, const json::string_t& s) override
-    {
-        values.push_back(val);
-        strings.push_back(s);
-        return true;
-    }
-    bool string(json::string_t& /*val*/) override
-    {
-        return true;
-    }
-    bool binary(json::binary_t& /*val*/) override
-    {
-        return true;
-    }
-    bool start_object(std::size_t /*val*/) override
-    {
-        return true;
-    }
-    bool key(json::string_t& /*val*/) override
-    {
-        return true;
-    }
-    bool end_object() override
-    {
-        return true;
-    }
-    bool start_array(std::size_t /*val*/) override
-    {
-        switched = std::setlocale(LC_NUMERIC, locale_after_open.c_str()) != nullptr;
-        return true;
-    }
-    bool end_array() override
-    {
-        return true;
-    }
-    bool parse_error(std::size_t /*val*/, const std::string& /*val*/, const nlohmann::detail::exception& /*val*/) override
-    {
-        return false;
-    }
-
-    std::string locale_after_open;
-    bool switched = false;
-    std::vector<json::number_float_t> values {}; // NOLINT(readability-redundant-member-init)
-    std::vector<json::string_t> strings {}; // NOLINT(readability-redundant-member-init)
-};
-} // namespace
-
-TEST_CASE("locale changes between lexer construction and number conversion (#5198)")
-{
-    // The numbers are chosen so that the conversion also takes the strtod
-    // fallback, which honors the locale that is current at conversion time:
-    // too many significant digits for Clinger's fast path, an underflow that
-    // std::from_chars rejects, and a plain value.
-    const std::vector<std::string> numbers = {"3.14159265358979323846", "1.5e-400", "12.34", "-0.000123456789012345678"};
-    std::string text = "[";
-    for (const auto& n : numbers)
-    {
-        text += (text.size() == 1 ? "" : ",") + n;
-    }
-    text += "]";
-
-    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
-
-    // reference values, parsed without a locale switch
-    REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
-    const json expected = json::parse(text);
-    const long_double_json expected_ld = long_double_json::parse(text);
-
-    const std::array<std::pair<const char*, const char*>, 2> transitions =
-    {
-        {
-            {"C", "de_DE"},
-            {"de_DE", "C"}
-        }
-    };
-
-    for (const auto& transition : transitions)
-    {
-        CAPTURE(transition.first);
-        CAPTURE(transition.second);
-
-        if (std::setlocale(LC_NUMERIC, transition.first) == nullptr)
-        {
-            MESSAGE("locale is not usable");
-            continue;
-        }
-
-        // SAX parsing
-        {
-            LocaleSwitchingSax sax(transition.second);
-            CHECK(json::sax_parse(text, &sax));
-            if (sax.switched)
-            {
-                CHECK(sax.values == expected.get<std::vector<json::number_float_t>>());
-                CHECK(sax.strings == numbers);
-            }
-        }
-
-        // DOM parsing with a callback
-        {
-            bool switched = false;
-            const auto cb = [&](int /*depth*/, json::parse_event_t event, json& /*parsed*/)
-            {
-                if (event == json::parse_event_t::array_start)
-                {
-                    switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
-                }
-                return true;
-            };
-            const json j = json::parse(text, cb);
-            if (switched)
-            {
-                CHECK(j == expected);
-            }
-        }
-
-        // a long double goes through std::strtold unless std::from_chars supports it
-        {
-            bool switched = false;
-            const auto cb = [&](int /*depth*/, long_double_json::parse_event_t event, long_double_json& /*parsed*/)
-            {
-                if (event == long_double_json::parse_event_t::array_start)
-                {
-                    switched = std::setlocale(LC_NUMERIC, transition.second) != nullptr;
-                }
-                return true;
-            };
-            const long_double_json j = long_double_json::parse(text, cb);
-            if (switched)
-            {
-                CHECK(j == expected_ld);
-            }
-        }
-    }
-
-    std::setlocale(LC_NUMERIC, "C");
-}
-
-TEST_CASE("locale with a multi-byte decimal point")
-{
-    // Some locales use a decimal point that is not a single character, e.g.
-    // U+066B ARABIC DECIMAL SEPARATOR (two bytes in UTF-8). It cannot be
-    // substituted in place for '.', so the strtod fallback stops early. The
-    // conversion must still terminate rather than retry forever.
-    const std::array<const char*, 6> names = {{"ar_EG.UTF-8", "ar_SA.UTF-8", "fa_IR.UTF-8", "ps_AF.UTF-8", "ar_EG", "fa_IR"}};
-    bool tested = false;
-    for (const char* name : names)
-    {
-        if (std::setlocale(LC_NUMERIC, name) == nullptr)
-        {
-            continue;
-        }
-        const std::string decimal_point = std::localeconv()->decimal_point;
-        if (decimal_point.size() < 2)
-        {
-            continue;
-        }
-        CAPTURE(name);
-        tested = true;
-
-        // too many significant digits for Clinger's fast path, and an underflow
-        // that std::from_chars rejects: both reach the strtod fallback
-        json j;
-        CHECK_NOTHROW(j = json::parse("[3.14159265358979323846, 1.5e-400, -0.000123456789012345678]"));
-        CHECK(j.is_array());
-        CHECK(json::accept("3.14159265358979323846"));
-
-        // a value the locale-independent paths convert is not affected
-        CHECK(json::parse("12.5") == 12.5);
-    }
-    if (!tested)
-    {
-        MESSAGE("no locale with a multi-byte decimal point is usable");
-    }
-
-    std::setlocale(LC_NUMERIC, "C");
-}

tests/src/unit-msgpack.cpp

@@ -1551,69 +1551,10 @@ TEST_CASE("MessagePack")
         SECTION("invalid string in map")
         {
             json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found an integer; last byte: 0xFF", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack string: expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0xFF", json::parse_error&);
             CHECK(json::from_msgpack(std::vector<uint8_t>({0x81, 0xff, 0x01}), true, false).is_discarded());
         }
 
-        SECTION("non-string key (see #3381)")
-        {
-            // only strings map to JSON object keys; any other key is rejected
-            // with a message naming its type
-            const std::vector<std::pair<std::vector<std::uint8_t>, std::string>> cases =
-            {
-                {{0x81, 0xC0, 0x01}, "nil; last byte: 0xC0"},
-                {{0x81, 0xC2, 0x01}, "a boolean; last byte: 0xC2"},
-                {{0x81, 0xC3, 0x01}, "a boolean; last byte: 0xC3"},
-                {{0x81, 0xCA, 0x3F, 0x80, 0x00, 0x00, 0x01}, "a float; last byte: 0xCA"},
-                {{0x81, 0xCB, 0x3F, 0xF0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "a float; last byte: 0xCB"},
-                {{0x81, 0xC4, 0x00, 0x01}, "a bin; last byte: 0xC4"},
-                {{0x81, 0xC5, 0x00, 0x00, 0x01}, "a bin; last byte: 0xC5"},
-                {{0x81, 0xC6, 0x00, 0x00, 0x00, 0x00, 0x01}, "a bin; last byte: 0xC6"},
-                {{0x81, 0xC7, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC7"},
-                {{0x81, 0xC8, 0x00, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC8"},
-                {{0x81, 0xC9, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an ext; last byte: 0xC9"},
-                {{0x81, 0xD4, 0x01, 0x00, 0x01}, "an ext; last byte: 0xD4"},
-                {{0x81, 0xD5, 0x01, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD5"},
-                {{0x81, 0xD6, 0x01, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD6"},
-                {{0x81, 0xD7, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD7"},
-                {{0x81, 0xD8, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}, "an ext; last byte: 0xD8"},
-                {{0x81, 0xCC, 0x01, 0x01}, "an integer; last byte: 0xCC"},
-                {{0x81, 0xCD, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCD"},
-                {{0x81, 0xCE, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCE"},
-                {{0x81, 0xCF, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xCF"},
-                {{0x81, 0xD0, 0x01, 0x01}, "an integer; last byte: 0xD0"},
-                {{0x81, 0xD1, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD1"},
-                {{0x81, 0xD2, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD2"},
-                {{0x81, 0xD3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01}, "an integer; last byte: 0xD3"},
-                {{0x81, 0x00, 0x01}, "an integer; last byte: 0x00"},
-                {{0x81, 0x7F, 0x01}, "an integer; last byte: 0x7F"},
-                {{0x81, 0xE0, 0x01}, "an integer; last byte: 0xE0"},
-                {{0x81, 0x80, 0x01}, "a map; last byte: 0x80"},
-                {{0x81, 0x8F, 0x01}, "a map; last byte: 0x8F"},
-                {{0x81, 0xDE, 0x00, 0x00, 0x01}, "a map; last byte: 0xDE"},
-                {{0x81, 0xDF, 0x00, 0x00, 0x00, 0x00, 0x01}, "a map; last byte: 0xDF"},
-                {{0x81, 0x90, 0x01}, "an array; last byte: 0x90"},
-                {{0x81, 0x9F, 0x01}, "an array; last byte: 0x9F"},
-                {{0x81, 0xDC, 0x00, 0x00, 0x01}, "an array; last byte: 0xDC"},
-                {{0x81, 0xDD, 0x00, 0x00, 0x00, 0x00, 0x01}, "an array; last byte: 0xDD"},
-            };
-
-            for (const auto& c : cases)
-            {
-                CAPTURE(c.first)
-                const std::string expected = "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack object key: only string keys are supported, but found " + c.second;
-                json _;
-                CHECK_THROWS_WITH_AS(_ = json::from_msgpack(c.first), expected.c_str(), json::parse_error&);
-                CHECK(json::from_msgpack(c.first, true, false).is_discarded());
-            }
-
-            json _;
-            // the unused byte 0xC1 is still reported as a malformed string
-            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81, 0xC1, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing MessagePack string: expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0xC1", json::parse_error&);
-            // a missing key is still reported as the end of input
-            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing MessagePack string: unexpected end of input", json::parse_error&);
-        }
-
         SECTION("invalid UTF-8 in string (see #5529)")
         {
             // a fixstr of length 2 (0xA0 | 2) whose bytes are not valid UTF-8

tests/src/unit-regression1.cpp

@@ -1018,7 +1018,7 @@ TEST_CASE("regression tests 1")
         };
 
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR object key: only string keys are supported, but found an array; last byte: 0x98", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x98", json::parse_error&);
 
         // related test case: nonempty UTF-8 string (indefinite length)
         std::vector<uint8_t> const vec1 {0x7f, 0x61, 0x61};
@@ -1065,7 +1065,7 @@ TEST_CASE("regression tests 1")
         };
 
         json _;
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec1), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR object key: only string keys are supported, but found a map; last byte: 0xB4", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec1), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xB4", json::parse_error&);
 
         // related test case: double-precision
         std::vector<uint8_t> const vec2
@@ -1077,7 +1077,7 @@ TEST_CASE("regression tests 1")
             0x96, 0x96, 0xb4, 0xb4, 0xfa, 0x94, 0x94, 0x61,
             0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0xfb
         };
-        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec2), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR object key: only string keys are supported, but found a map; last byte: 0xB4", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(vec2), "[json.exception.parse_error.113] parse error at byte 13: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xB4", json::parse_error&);
     }
 
     SECTION("issue #452 - Heap-buffer-overflow (OSS-Fuzz issue 585)")