CBOR/MessagePack readers: leave one-element arrays to the general path

enter_cbor_array and enter_msgpack_array called the out-of-line scalar
run for every non-empty array. When the array's element is an object or
an array, as on every level of [[...]] or the single ring of a GeoJSON
polygon, the call reads nothing; it made 1,000 arrays nested in each
other cost 4 % more instructions (GCC 13) and up to 8 % more time (Apple
clang) than without the run. #5975 had fixed that with an inline
pre-check, which was later dropped after measuring canada only.

The run is now entered only for arrays of two or more elements: the same
comparison as before, so no other row changes. Arrays of one scalar,
which the run read faster, now take the general path; they are rare in
documents (one in citm_catalog, none in twitter or canada). The new
benchmark FromBinaryShape/singles measures them, next to
FromBinaryShape/nested.

Instructions per repetition, new/old, GCC 13 callgrind: nested arrays
0.973 (CBOR) and 0.971 (MessagePack), arrays of one scalar 1.037 and
1.021, every other row within 0.15 %.

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

.github/workflows/cancel_closed_pr_runs.yml

@@ -24,7 +24,7 @@ jobs:
     permissions:
       actions: write
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     steps:
       - name: Harden Runner

.github/workflows/check_amalgamation.yml

@@ -19,7 +19,7 @@ permissions:
 jobs:
   save:
     if: github.event_name == 'pull_request'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/check_docs_links.yml

@@ -16,7 +16,7 @@ concurrency:
 jobs:
   check_docs_links:
     if: github.repository == 'nlohmann/json'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     timeout-minutes: 30
     steps:
       - name: Harden Runner

.github/workflows/comment_check_amalgamation.yml

@@ -12,7 +12,7 @@ jobs:
   comment:
     # push runs on develop have no PR to comment on (and no "pr" artifact)
     if: ${{ github.event.workflow_run.conclusion == 'failure' && github.event.workflow_run.event == 'pull_request' }}
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     permissions:
       contents: read
       actions: read

.github/workflows/dependency-review.yml

@@ -18,7 +18,7 @@ permissions:
 
 jobs:
   dependency-review:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/flawfinder.yml

@@ -24,7 +24,7 @@ on:
 jobs:
   flawfinder:
     name: Flawfinder
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     permissions:
       actions: read
       contents: read

.github/workflows/labeler.yml

@@ -19,7 +19,7 @@ jobs:
       contents: read
       pull-requests: write
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     steps:
       - name: Harden Runner

.github/workflows/publish_documentation.yml

@@ -34,7 +34,7 @@ jobs:
       contents: write
 
     if: github.repository == 'nlohmann/json'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     steps:
       - name: Harden Runner
         uses: step-security/harden-runner@dc2769abcc0fcfbadfc1df54081c1608579ef6b2 # v2.22.2

.github/workflows/scorecards.yml

@@ -24,7 +24,7 @@ permissions:
 jobs:
   analysis:
     name: Scorecard analysis
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     permissions:
       # Needed to upload the results to code-scanning dashboard.
       security-events: write

.github/workflows/stale.yml

@@ -8,7 +8,7 @@ permissions:
 
 jobs:
   stale:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
 
     permissions:
       issues: write

.github/workflows/ubuntu.yml

@@ -18,7 +18,7 @@ concurrency:
 
 jobs:
   ci_test_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: gcc:latest
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -130,7 +130,7 @@ jobs:
         run: cmake --build build --target ${{ matrix.target }}
 
   ci_static_analysis_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: silkeh/clang:22
     strategy:
       matrix:
@@ -149,7 +149,7 @@ jobs:
         run: cmake --build build --target ${{ matrix.target }}
 
   ci_cmake_options:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: ubuntu:24.04
     strategy:
       matrix:
@@ -209,7 +209,7 @@ jobs:
           fail-on-error: false
 
   ci_test_compilers_gcc_old:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         compiler: ['4.8', '4.9', '5', '6']
@@ -251,7 +251,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_g++-${{ matrix.compiler }}
 
   ci_test_compilers_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         # older GCC docker images (4, 5, 6) fail to check out code
@@ -269,7 +269,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_default
 
   ci_test_compilers_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         compiler: ['3.4', '3.5', '3.6', '3.7', '3.8', '3.9', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14', '15-bullseye', '16', '17', '18', '19', '20', '21', '22', 'latest']
@@ -289,7 +289,7 @@ jobs:
         run: cmake --build build --target ci_test_compiler_default
 
   ci_test_standards_gcc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: gcc:latest
     strategy:
       matrix:
@@ -306,7 +306,7 @@ jobs:
         run: cmake --build build --target ci_test_gcc_cxx${{ matrix.standard }}
 
   ci_test_standards_clang:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: silkeh/clang:latest
     strategy:
       matrix:
@@ -330,7 +330,7 @@ jobs:
         if: ${{ matrix.stdlib == 'libstdcxx' }}
 
   ci_cuda_example:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     strategy:
       fail-fast: false
       matrix:
@@ -356,7 +356,7 @@ jobs:
     strategy:
       matrix:
         container: ['gcc:latest', 'silkeh/clang:latest']
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: ${{ matrix.container }}
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -383,7 +383,7 @@ jobs:
         run: cmake --build build --target ci_module_cpp20
 
   ci_icpc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     # Intel discontinued the classic icc/icpc compiler in oneAPI 2024.0; this is
     # Intel's own last officially published image that still includes it.
     container: intel/oneapi-hpckit:2023.2.1-devel-ubuntu22.04
@@ -402,7 +402,7 @@ jobs:
         run: cmake --build build --target ci_icpc
 
   ci_icpx:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: intel/oneapi-hpckit:latest
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -416,7 +416,7 @@ jobs:
         run: cmake --build build --target ci_icpx
 
   ci_nvhpc:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-26.04
     container: nvcr.io/nvidia/nvhpc:25.5-devel-cuda12.9-ubuntu22.04
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1

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

@@ -120,16 +120,6 @@ overload (3).
     See [Number conversion](../../features/types/number_handling.md#number-conversion)
     for more information.
 
-!!! note "Booleans as numbers"
-
-    A JSON boolean converts to `#!cpp 0` or `#!cpp 1` for every arithmetic type **except** [`number_integer_t`](number_integer_t.md),
-    [`number_unsigned_t`](number_unsigned_t.md) and [`number_float_t`](number_float_t.md) (by default `#!cpp std::int64_t`,
-    `#!cpp std::uint64_t`, and `#!cpp double`), for which `#!cpp get<T>()` throws
-    [`type_error.302`](../../home/exceptions.md#jsonexceptiontype_error302) ("type must be number, but is boolean"). So
-    `#!cpp json(true).get<int>()` is `#!cpp 1`, while `#!cpp json(true).get<std::int64_t>()` and
-    `#!cpp json(true).get<double>()` throw. This is the behavior of all 3.x versions;
-    [`basic_json_view::get<T>()`](../basic_json_view/get.md) behaves the same.
-
 !!! note "`std::optional` conversions"
 
     Prior to version 3.13.0, `#!cpp get<std::optional<T>>()` (and other conversions to `std::optional<T>`) failed to

docs/mkdocs/docs/api/basic_json_view/get.md

@@ -11,8 +11,7 @@ For the types below, the conversion works directly on the flat index — no `Bas
 
 - `#!cpp bool`
 - arithmetic types other than `#!cpp bool` (for a boolean, `#!cpp 0`/`#!cpp 1`, exactly as for
-  [`BasicJsonType::get<T>()`](../basic_json/get.md#notes), except for `number_integer_t`, `number_unsigned_t` and
+  [`BasicJsonType::get<T>()`](../basic_json/get.md))
-  `number_float_t`, which throw `type_error.302` for a boolean, as `BasicJsonType::get<T>()` does)
 - `#!cpp std::nullptr_t`
 - `#!cpp std::basic_string<char, Traits, Alloc>` (including `string_t`) — a copy of the string
 - [`string_view_t`](index.md#member-types) — **no copy**: the returned view points into the document's

include/nlohmann/detail/input/binary_reader.hpp

@@ -467,11 +467,13 @@ class binary_reader
 
             const std::size_t element_type_parse_position = chars_read;
             // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on: they are skipped unless
+            // and those names are not passed on: they are skipped, and only
-            // error_handler_t::strict must reject ill-formed UTF-8 in them
+            // checked if error_handler_t::strict must reject ill-formed UTF-8
             const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
+            if (JSON_HEDLEY_UNLIKELY(!(is_object || error_handler != error_handler_t::strict
+                                       ? get_bson_cstr(key, is_object)
+                                       : check_bson_cstr(key, std::integral_constant<bool, bulk_scan> {}))))
             {
                 return false;
             }
@@ -495,7 +497,7 @@ class binary_reader
     @param[in] store  whether the characters are needed; if not (the names of
                       an array's elements), they are skipped and @a result may
                       be left unchanged, and they are not checked against
-                      @ref error_handler
+                      @ref error_handler (@ref check_bson_cstr checks them)
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
@@ -554,6 +556,42 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief skip a C-style string that error_handler_t::strict must check
+
+    The names of an array's elements are not passed on. On contiguous input,
+    a well-formed name is checked in place and skipped without being copied.
+    Otherwise (no \\x00-byte in the input that can be scanned, or ill-formed
+    UTF-8), it is read by @ref get_bson_cstr, which reports the error.
+
+    @param[in,out] result  an empty string, which may receive the name
+    @return whether the name was read and is well-formed
+    */
+    bool check_bson_cstr(string_t& result, std::true_type /*bulk*/)
+    {
+        const std::size_t remaining = ia.bulk_remaining();
+        if (remaining != 0)
+        {
+            const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
+            const std::size_t length = find_zero_byte(data, remaining);
+            if (length != remaining && JSON_HEDLEY_LIKELY(valid_utf8_string(data, length)))
+            {
+                // consume the string and its \x00-byte, as get_bson_cstr does
+                ia.bulk_skip(length + 1);
+                chars_read += length + 1;
+                current = 0x00;
+                return true;
+            }
+        }
+        return get_bson_cstr(result);
+    }
+
+    /// input that is not contiguous: the name is read and checked byte by byte
+    bool check_bson_cstr(string_t& result, std::false_type /*bulk*/)
+    {
+        return get_bson_cstr(result);
+    }
+
     /// input that is not contiguous: C-style strings are read byte by byte
     bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
@@ -1818,14 +1856,18 @@ class binary_reader
 
     Only the start of an array is tried, which covers arrays of numbers
     (e.g. coordinates) but costs arrays of other values only one call, not one
-    per element.
+    per element. An array of one element is not tried at all: that element is
+    mostly an object or an array (`[[...]]`, the single ring of a GeoJSON
+    polygon), for which the call would find no scalar, while a single scalar,
+    which the run would read faster, is rare. The benchmarks
+    `FromBinaryShape/nested` and `FromBinaryShape/singles` show both sides.
 
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_cbor_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_cbor_value
@@ -2726,12 +2768,16 @@ class binary_reader
     /*!
     @brief open a MessagePack array and read the scalars it begins with (see
            @ref parse_msgpack_scalar_run)
+
+    An array of one element is not tried, for the reason given at
+    @ref enter_cbor_array.
+
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_msgpack_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_msgpack_value

include/nlohmann/detail/view/value.hpp

@@ -33,37 +33,12 @@ namespace view
 template<typename T>
 struct value_tag {};
 
-/// whether basic_json reads T with a dedicated from_json() overload that does
-/// not accept a boolean: exactly number_integer_t, number_unsigned_t and
-/// number_float_t (the other arithmetic types convert a boolean to 0 or 1)
-template<typename T, typename BasicJsonType>
-struct rejects_boolean : std::integral_constant < bool,
-    std::is_same<T, typename BasicJsonType::number_integer_t>::value
-    || std::is_same<T, typename BasicJsonType::number_unsigned_t>::value
-    || std::is_same<T, typename BasicJsonType::number_float_t>::value >
-{};
-
-/// a boolean as T: 0 or 1
-template<typename T>
-NLOHMANN_VIEW_ALWAYS_INLINE T boolean_as(const document_data& /*d*/, const node& n, std::false_type /*rejects*/)
-{
-    return static_cast<T>((n.flags & node_flags::is_true) != 0);
-}
-
-/// a boolean as number_integer_t, number_unsigned_t or number_float_t: type_error.302, as in basic_json
-template<typename T>
-[[noreturn]] NLOHMANN_VIEW_ALWAYS_INLINE T boolean_as(const document_data& d, const node& n, std::true_type /*rejects*/)
-{
-    throw_type_error(error_site(&d, &n), exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
-}
-
 /*!
 @brief the number or boolean of a node converted to an arithmetic type
 
 As basic_json's get<T>() for arithmetic types: integers and floats are
-converted with static_cast, booleans give 0 or 1 (but throw type_error.302 for
+converted with static_cast, booleans give 0 or 1, and other types throw
-number_integer_t, number_unsigned_t and number_float_t, as basic_json does),
+type_error.302.
-and other types throw type_error.302.
 */
 template<typename T, typename BasicJsonType>
 NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const node& n)
@@ -77,7 +52,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::number_float:
             return static_cast<T>(float_value<typename BasicJsonType::number_float_t>(d, n));
         case value_t::boolean:
-            return boolean_as<T>(d, n, rejects_boolean<T, BasicJsonType> {});
+            return static_cast<T>((n.flags & node_flags::is_true) != 0);
         case value_t::null:
         case value_t::object:
         case value_t::array:

single_include/nlohmann/json.hpp

@@ -18474,11 +18474,13 @@ class binary_reader
 
             const std::size_t element_type_parse_position = chars_read;
             // an array's elements are named "0", "1", ... in the wire format,
-            // and those names are not passed on: they are skipped unless
+            // and those names are not passed on: they are skipped, and only
-            // error_handler_t::strict must reject ill-formed UTF-8 in them
+            // checked if error_handler_t::strict must reject ill-formed UTF-8
             const bool is_object = container_stack.back().is_object;
             key.clear();
-            if (JSON_HEDLEY_UNLIKELY(!get_bson_cstr(key, is_object || error_handler == error_handler_t::strict)))
+            if (JSON_HEDLEY_UNLIKELY(!(is_object || error_handler != error_handler_t::strict
+                                       ? get_bson_cstr(key, is_object)
+                                       : check_bson_cstr(key, std::integral_constant<bool, bulk_scan> {}))))
             {
                 return false;
             }
@@ -18502,7 +18504,7 @@ class binary_reader
     @param[in] store  whether the characters are needed; if not (the names of
                       an array's elements), they are skipped and @a result may
                       be left unchanged, and they are not checked against
-                      @ref error_handler
+                      @ref error_handler (@ref check_bson_cstr checks them)
     @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
@@ -18561,6 +18563,42 @@ class binary_reader
         return true;
     }
 
+    /*!
+    @brief skip a C-style string that error_handler_t::strict must check
+
+    The names of an array's elements are not passed on. On contiguous input,
+    a well-formed name is checked in place and skipped without being copied.
+    Otherwise (no \\x00-byte in the input that can be scanned, or ill-formed
+    UTF-8), it is read by @ref get_bson_cstr, which reports the error.
+
+    @param[in,out] result  an empty string, which may receive the name
+    @return whether the name was read and is well-formed
+    */
+    bool check_bson_cstr(string_t& result, std::true_type /*bulk*/)
+    {
+        const std::size_t remaining = ia.bulk_remaining();
+        if (remaining != 0)
+        {
+            const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
+            const std::size_t length = find_zero_byte(data, remaining);
+            if (length != remaining && JSON_HEDLEY_LIKELY(valid_utf8_string(data, length)))
+            {
+                // consume the string and its \x00-byte, as get_bson_cstr does
+                ia.bulk_skip(length + 1);
+                chars_read += length + 1;
+                current = 0x00;
+                return true;
+            }
+        }
+        return get_bson_cstr(result);
+    }
+
+    /// input that is not contiguous: the name is read and checked byte by byte
+    bool check_bson_cstr(string_t& result, std::false_type /*bulk*/)
+    {
+        return get_bson_cstr(result);
+    }
+
     /// input that is not contiguous: C-style strings are read byte by byte
     bool get_bson_cstr_bulk(string_t& /*result*/, const bool /*store*/, std::false_type /*bulk*/) const noexcept
     {
@@ -19825,14 +19863,18 @@ class binary_reader
 
     Only the start of an array is tried, which covers arrays of numbers
     (e.g. coordinates) but costs arrays of other values only one call, not one
-    per element.
+    per element. An array of one element is not tried at all: that element is
+    mostly an object or an array (`[[...]]`, the single ring of a GeoJSON
+    polygon), for which the call would find no scalar, while a single scalar,
+    which the run would read faster, is rare. The benchmarks
+    `FromBinaryShape/nested` and `FromBinaryShape/singles` show both sides.
 
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_cbor_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_cbor_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_cbor_value
@@ -20733,12 +20775,16 @@ class binary_reader
     /*!
     @brief open a MessagePack array and read the scalars it begins with (see
            @ref parse_msgpack_scalar_run)
+
+    An array of one element is not tried, for the reason given at
+    @ref enter_cbor_array.
+
     @param[in] len  the number of elements
     @return whether the SAX parser accepted the array and the values read
     */
     bool enter_msgpack_array(const std::size_t len)
     {
-        return enter_array(len) && (len == 0 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
+        return enter_array(len) && (len <= 1 || parse_msgpack_scalar_run(std::integral_constant<bool, bulk_scan> {}));
     }
 
     /// input that is not contiguous: every value is read by parse_msgpack_value

single_include/nlohmann/json_view.hpp

@@ -10067,37 +10067,12 @@ namespace view
 template<typename T>
 struct value_tag {};
 
-/// whether basic_json reads T with a dedicated from_json() overload that does
-/// not accept a boolean: exactly number_integer_t, number_unsigned_t and
-/// number_float_t (the other arithmetic types convert a boolean to 0 or 1)
-template<typename T, typename BasicJsonType>
-struct rejects_boolean : std::integral_constant < bool,
-    std::is_same<T, typename BasicJsonType::number_integer_t>::value
-    || std::is_same<T, typename BasicJsonType::number_unsigned_t>::value
-    || std::is_same<T, typename BasicJsonType::number_float_t>::value >
-{};
-
-/// a boolean as T: 0 or 1
-template<typename T>
-NLOHMANN_VIEW_ALWAYS_INLINE T boolean_as(const document_data& /*d*/, const node& n, std::false_type /*rejects*/)
-{
-    return static_cast<T>((n.flags & node_flags::is_true) != 0);
-}
-
-/// a boolean as number_integer_t, number_unsigned_t or number_float_t: type_error.302, as in basic_json
-template<typename T>
-[[noreturn]] NLOHMANN_VIEW_ALWAYS_INLINE T boolean_as(const document_data& d, const node& n, std::true_type /*rejects*/)
-{
-    throw_type_error(error_site(&d, &n), exception_id::type_mismatch, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
-}
-
 /*!
 @brief the number or boolean of a node converted to an arithmetic type
 
 As basic_json's get<T>() for arithmetic types: integers and floats are
-converted with static_cast, booleans give 0 or 1 (but throw type_error.302 for
+converted with static_cast, booleans give 0 or 1, and other types throw
-number_integer_t, number_unsigned_t and number_float_t, as basic_json does),
+type_error.302.
-and other types throw type_error.302.
 */
 template<typename T, typename BasicJsonType>
 NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const node& n)
@@ -10111,7 +10086,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::number_float:
             return static_cast<T>(float_value<typename BasicJsonType::number_float_t>(d, n));
         case value_t::boolean:
-            return boolean_as<T>(d, n, rejects_boolean<T, BasicJsonType> {});
+            return static_cast<T>((n.flags & node_flags::is_true) != 0);
         case value_t::null:
         case value_t::object:
         case value_t::array:

tests/benchmarks/src/benchmarks.cpp

@@ -629,6 +629,22 @@ static json make_containers()
     return j;
 }
 
+/// many arrays of one number each: one-element arrays are left to the general
+/// path (CBOR and MessagePack), which reads a lone number slower than the loop
+/// for arrays of scalars would
+static json make_singles()
+{
+    json data = json::array();
+    for (std::size_t i = 0; i < 100000; ++i)
+    {
+        data.push_back(json::array({i}));
+    }
+
+    json j = json::object();
+    j["data"] = std::move(data);
+    return j;
+}
+
 /// one flat array of numbers: the scalar decoding path, which must not move
 static json make_scalars()
 {
@@ -676,6 +692,8 @@ BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson_optimized, make_container
 BENCHMARK_CAPTURE(FromBinaryShape, containers / bjdata, make_containers, binary_format::bjdata);
 BENCHMARK_CAPTURE(FromBinaryShape, containers / bson, make_containers, binary_format::bson);
 BENCHMARK_CAPTURE(FromBinaryShape, containers / bon8, make_containers, binary_format::bon8);
+BENCHMARK_CAPTURE(FromBinaryShape, singles / cbor, make_singles, binary_format::cbor);
+BENCHMARK_CAPTURE(FromBinaryShape, singles / msgpack, make_singles, binary_format::msgpack);
 // BSON names every array element, so a large array measures key generation
 // rather than scalar decoding and is left out here
 BENCHMARK_CAPTURE(FromBinaryShape, scalars / cbor, make_scalars, binary_format::cbor);

tests/src/unit-bson.cpp

@@ -23,6 +23,7 @@ using nlohmann::json;
 #include <cstdint>
 #include <fstream>
 #include <limits>
+#include <list>
 #include <sstream>
 #include <vector>
 #include "make_test_data_available.hpp"
@@ -1199,6 +1200,31 @@ TEST_CASE("BSON keys from contiguous and stream input")
             from_stream = e.what();
         }
         CHECK(from_vector == from_stream);
+
+        // error_handler_t::strict checks the array element names in place on
+        // contiguous input and byte by byte otherwise; the names are
+        // well-formed, so both give the same value or error as above
+        std::string strict_from_vector;
+        std::string strict_from_list;
+        try
+        {
+            strict_from_vector = json::from_bson(input, true, true, json::error_handler_t::strict).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            strict_from_vector = e.what();
+        }
+        try
+        {
+            const std::list<std::uint8_t> list(input.begin(), input.end());
+            strict_from_list = json::from_bson(list.begin(), list.end(), true, true, json::error_handler_t::strict).dump();
+        }
+        catch (const json::parse_error& e)
+        {
+            strict_from_list = e.what();
+        }
+        CHECK(strict_from_vector == from_vector);
+        CHECK(strict_from_list == from_vector);
     }
 }
 
@@ -1227,6 +1253,18 @@ TEST_CASE("BSON array element names")
 
     std::istringstream stream(std::string(reinterpret_cast<const char*>(bson.data()), bson.size()));
     CHECK(json::from_bson(stream) == expected);
+
+    // input that is not contiguous reads the names byte by byte and must reject
+    // the same name
+    const std::list<std::uint8_t> list(bson.begin(), bson.end());
+    CHECK_THROWS_WITH_AS(_ = json::from_bson(list.begin(), list.end(), true, true, json::error_handler_t::strict), "[json.exception.parse_error.113] parse error at byte 14: syntax error while parsing BSON key: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+
+    // without exceptions, the rejected name ends the parse
+    CHECK(json::from_bson(bson, true, false, json::error_handler_t::strict).is_discarded());
+
+    // well-formed names pass the check without being stored
+    const json valid = {{"a", {true, false, {{"k", json::array({1, 2})}}}}};
+    CHECK(json::from_bson(json::to_bson(valid), true, true, json::error_handler_t::strict) == valid);
 }
 #endif
 

tests/src/unit-cbor.cpp

@@ -2520,6 +2520,34 @@ TEST_CASE("CBOR arrays of scalars from contiguous and non-contiguous input")
     }
 }
 
+TEST_CASE("CBOR arrays of one element from contiguous and non-contiguous input")
+{
+    // contiguous input leaves an array of one element to the general path
+    // rather than to the loop that reads arrays of scalars; both inputs must
+    // still give the same events, value, or error for the complete document
+    // and for every truncation of it, with enough bytes after each array that
+    // the loop could have been entered
+    const json j = json::parse(R"({"a": [[[[1.5]]]], "b": [7], "c": [{"x": 2.5}], "d": ["s"], "e": [[1, 2]], "f": [null], "g": 1.25})");
+    const std::vector<std::uint8_t> bytes = json::to_cbor(j);
+
+    CHECK(json::from_cbor(bytes) == j);
+
+    for (std::size_t length = 0; length <= bytes.size(); ++length)
+    {
+        CAPTURE(length)
+        const std::vector<std::uint8_t> contiguous(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length));
+        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
+
+        CHECK(json::from_cbor(contiguous, true, false).dump() == json::from_cbor(bytewise.begin(), bytewise.end(), true, false).dump());
+
+        SaxEventLogger from_contiguous;
+        SaxEventLogger from_bytewise;
+        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::cbor, true, false)
+              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::cbor, true, false));
+        CHECK(from_contiguous.events == from_bytewise.events);
+    }
+}
+
 TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
 {
     // Reading an indefinite-length string or byte array used to call itself

tests/src/unit-conversions1.cpp

@@ -1260,44 +1260,6 @@ TEST_CASE("value conversion")
     #undef JSON_HAS_CPP_17
 #endif
 
-TEST_CASE("get<T>() of a boolean (#5988)")
-{
-    // a boolean converts to 0/1 for every arithmetic type except number_integer_t, number_unsigned_t and
-    // number_float_t, whose dedicated from_json() overloads throw
-    const json t = true;
-    const json f = false;
-
-    SECTION("0 and 1")
-    {
-        // long and unsigned long are left out: they are std::int64_t and std::uint64_t on some platforms
-        CHECK(t.get<bool>() == true);
-        CHECK(f.get<bool>() == false);
-        CHECK(t.get<char>() == 1);
-        CHECK(t.get<signed char>() == 1);
-        CHECK(t.get<unsigned char>() == 1);
-        CHECK(t.get<short>() == 1); // NOLINT(google-runtime-int)
-        CHECK(t.get<unsigned short>() == 1); // NOLINT(google-runtime-int)
-        CHECK(t.get<int>() == 1);
-        CHECK(t.get<unsigned>() == 1);
-        CHECK(t.get<float>() == 1.0F);
-        CHECK(t.get<long double>() == 1.0L);
-        CHECK(f.get<int>() == 0);
-        CHECK(f.get<float>() == 0.0F);
-    }
-
-#if !defined(JSON_NOEXCEPTION)
-    SECTION("number_integer_t, number_unsigned_t and number_float_t throw")
-    {
-        CHECK_THROWS_WITH_AS(t.get<json::number_integer_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-        CHECK_THROWS_WITH_AS(t.get<json::number_unsigned_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-        CHECK_THROWS_WITH_AS(t.get<json::number_float_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-        CHECK_THROWS_WITH_AS(f.get<json::number_integer_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-        CHECK_THROWS_WITH_AS(f.get<json::number_unsigned_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-        CHECK_THROWS_WITH_AS(f.get<json::number_float_t>(), "[json.exception.type_error.302] type must be number, but is boolean", json::type_error&);
-    }
-#endif
-}
-
 #ifdef JSON_HAS_CPP_14
     #undef JSON_HAS_CPP_14
 #endif

tests/src/unit-json_view.cpp

@@ -1551,85 +1551,6 @@ TEST_CASE("json_view values")
     }
 }
 
-namespace
-{
-// get<T>() of a boolean: the same value or the same exception in basic_json and in the view (#5988)
-template<typename T>
-void check_boolean_get_parity()
-{
-    for (const bool b :
-            {
-                true, false
-            })
-    {
-        const std::string text = b ? "true" : "false";
-        const json j = json::parse(text);
-        const json_document d = json_document::parse(text);
-        CAPTURE(text)
-#if !defined(JSON_NOEXCEPTION)
-        T dom_value {};
-        T view_value{};
-        const std::string dom_error = json_view_test::exception_of_call([&] { dom_value = j.get<T>(); });
-        const std::string view_error = json_view_test::exception_of_call([&] { view_value = d.root().template get<T>(); });
-        CHECK(dom_error == view_error);
-        if (dom_error.empty())
-        {
-            CHECK(dom_value == view_value);
-            CHECK(view_value == static_cast<T>(b));
-        }
-#else
-        // without exceptions, the combinations that throw (number_integer_t, number_unsigned_t, number_float_t)
-        // cannot be run: JSON_THROW aborts
-        const bool throws = std::is_same<T, json::number_integer_t>::value
-                            || std::is_same<T, json::number_unsigned_t>::value
-                            || std::is_same<T, json::number_float_t>::value;
-        if (!throws)
-        {
-            CHECK(j.get<T>() == d.root().template get<T>());
-        }
-#endif
-    }
-}
-} // namespace
-
-TEST_CASE("json_view get<T>() of a boolean (#5988)")
-{
-    check_boolean_get_parity<bool>();
-    check_boolean_get_parity<char>();
-    check_boolean_get_parity<signed char>();
-    check_boolean_get_parity<unsigned char>();
-    check_boolean_get_parity<short>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<unsigned short>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<int>();
-    check_boolean_get_parity<unsigned>();
-    check_boolean_get_parity<long>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<unsigned long>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<long long>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<unsigned long long>(); // NOLINT(google-runtime-int)
-    check_boolean_get_parity<std::int64_t>();
-    check_boolean_get_parity<std::uint64_t>();
-    check_boolean_get_parity<float>();
-    check_boolean_get_parity<double>();
-    check_boolean_get_parity<long double>();
-
-#if !defined(JSON_NOEXCEPTION)
-    SECTION("the exceptions of the exact number types")
-    {
-        const json_document d = json_document::parse("true");
-        CHECK_THROWS_WITH_AS(d.root().get<json::number_integer_t>(), json_view_test::message("type_error.302", "", 0, 4, "type must be number, but is boolean").c_str(), json::type_error&);
-        CHECK_THROWS_WITH_AS(d.root().get<json::number_unsigned_t>(), json_view_test::message("type_error.302", "", 0, 4, "type must be number, but is boolean").c_str(), json::type_error&);
-        CHECK_THROWS_WITH_AS(d.root().get<json::number_float_t>(), json_view_test::message("type_error.302", "", 0, 4, "type must be number, but is boolean").c_str(), json::type_error&);
-        CHECK(d.root().get<int>() == 1);
-        // get_to() and value() go through get<T>()
-        json::number_float_t x = 0;
-        CHECK_THROWS_AS(d.root().get_to(x), json::type_error&);
-        const json_document o = json_document::parse("{\"b\":true}");
-        CHECK_THROWS_AS(static_cast<void>(o.root().value("b", 0.0)), json::type_error&);
-        CHECK(o.root().value("b", 0) == 1);
-    }
-#endif
-}
-
 TEST_CASE("json_view JSON pointers")
 {
     SECTION("every value of generated documents")

tests/src/unit-json_view_builder.cpp

@@ -692,7 +692,7 @@ TEST_CASE("json_view builder: fraction digits")
             check_same(number);
             check_same("[" + number + "]");
             std::string pair;
-            pair.reserve(number.size() * 2 + 3);
+            pair.reserve((number.size() * 2) + 3);
             pair += '[';
             pair += number;
             pair += ',';

tests/src/unit-json_view_positions.cpp

@@ -521,7 +521,8 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         std::string text = "7";
         for (int level = 0; level < 40; ++level)
         {
-            text = R"([[1, [2]], )" + text + R"(, {"k": [3, {"l": [4]}]}, [5, [6, [7]]]])";
+            text.insert(0, R"([[1, [2]], )");
+            text += R"(, {"k": [3, {"l": [4]}]}, [5, [6, [7]]]])";
         }
         CAPTURE(text)
         const json j = json::parse(text);

tests/src/unit-msgpack.cpp

@@ -2311,3 +2311,31 @@ TEST_CASE("MessagePack arrays of scalars from contiguous and non-contiguous inpu
               == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack));
     }
 }
+
+TEST_CASE("MessagePack arrays of one element from contiguous and non-contiguous input")
+{
+    // contiguous input leaves an array of one element to the general path
+    // rather than to the loop that reads arrays of scalars; both inputs must
+    // still give the same events, value, or error for the complete document
+    // and for every truncation of it, with enough bytes after each array that
+    // the loop could have been entered
+    const json j = json::parse(R"({"a": [[[[1.5]]]], "b": [7], "c": [{"x": 2.5}], "d": ["s"], "e": [[1, 2]], "f": [null], "g": 1.25})");
+    const std::vector<std::uint8_t> bytes = json::to_msgpack(j);
+
+    CHECK(json::from_msgpack(bytes) == j);
+
+    for (std::size_t length = 0; length <= bytes.size(); ++length)
+    {
+        CAPTURE(length)
+        const std::vector<std::uint8_t> contiguous(bytes.begin(), bytes.begin() + static_cast<std::ptrdiff_t>(length));
+        const std::list<std::uint8_t> bytewise(contiguous.begin(), contiguous.end());
+
+        CHECK(json::from_msgpack(contiguous, true, false).dump() == json::from_msgpack(bytewise.begin(), bytewise.end(), true, false).dump());
+
+        SaxEventLogger from_contiguous;
+        SaxEventLogger from_bytewise;
+        CHECK(json::sax_parse(contiguous, &from_contiguous, json::input_format_t::msgpack, true, false)
+              == json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, json::input_format_t::msgpack, true, false));
+        CHECK(from_contiguous.events == from_bytewise.events);
+    }
+}