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/macros/json_diagnostic_positions.md

@@ -35,9 +35,6 @@ Note that enabling this macro increases the size of every JSON value by two `std
 overhead to parsing, copying JSON value objects, and the generation of error messages for exceptions. It also causes
 these values to be reported in those error messages.
 
-If [`JSON_DIAGNOSTICS`](json_diagnostics.md) is also set, the message contains the path and the byte range, such as
-`(/1) (bytes 4-8)`. An exception about the root value has no path and only the range, such as `(bytes 0-4)`.
-
 ## Default definition
 
 The default value is `0` (position diagnostics are switched off).

include/nlohmann/detail/exceptions.hpp

@@ -198,19 +198,18 @@ class exception : public std::exception
             // all other parent types (primitives) contribute no token
         }
 
-        // the root value has no path, but still has a byte range
+        if (tokens.empty())
-        std::string prefix;
-        if (!tokens.empty())
         {
-            const auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
+            return "";
+        }
+
+        auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
                                    [](const std::string & a, const std::string & b)
         {
             return concat(a, '/', detail::escape(b));
         });
-            prefix = concat('(', str, ") ");
-        }
 
-        return concat(prefix, get_byte_positions(leaf_element));
+        return concat('(', str, ") ", get_byte_positions(leaf_element));
 #else
         return get_byte_positions(leaf_element);
 #endif
@@ -223,8 +222,7 @@ class exception : public std::exception
     template<typename BasicJsonType>
     static std::string get_byte_positions(const BasicJsonType* leaf_element)
     {
-        // a value-initialized iterator has no value (invalid_iterator.212)
+        if ((leaf_element->start_pos() != std::string::npos) && (leaf_element->end_pos() != std::string::npos))
-        if (leaf_element != nullptr && leaf_element->start_pos() != std::string::npos && leaf_element->end_pos() != std::string::npos)
         {
             return concat("(bytes ", std::to_string(leaf_element->start_pos()), "-", std::to_string(leaf_element->end_pos()), ") ");
         }

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/errors.hpp

@@ -234,7 +234,8 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (with JSON_DIAGNOSTICS, only
+/// if there is a path)
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -255,11 +256,12 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
-    // a value that is not found leaves no tokens, like the root
+    const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
-    static_cast<void>(edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens));
+    if (!found || tokens.empty())
-    if (!tokens.empty())
     {
-        // the root value has no path, but still has a byte range
+        // context is still empty; returning it keeps the copy elided (-Wnrvo)
+        return context;
+    }
     std::string path;
     for (const std::string& token : tokens)
     {
@@ -267,7 +269,6 @@ std::string diagnostics(const error_site site)
         path += detail::escape(token);
     }
     context = concat('(', path, ") ");
-    }
 #endif
 #if JSON_DIAGNOSTIC_POSITIONS
     std::size_t start = 0;

single_include/nlohmann/json.hpp

@@ -5695,19 +5695,18 @@ class exception : public std::exception
             // all other parent types (primitives) contribute no token
         }
 
-        // the root value has no path, but still has a byte range
+        if (tokens.empty())
-        std::string prefix;
-        if (!tokens.empty())
         {
-            const auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
+            return "";
+        }
+
+        auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
                                    [](const std::string & a, const std::string & b)
         {
             return concat(a, '/', detail::escape(b));
         });
-            prefix = concat('(', str, ") ");
-        }
 
-        return concat(prefix, get_byte_positions(leaf_element));
+        return concat('(', str, ") ", get_byte_positions(leaf_element));
 #else
         return get_byte_positions(leaf_element);
 #endif
@@ -5720,8 +5719,7 @@ class exception : public std::exception
     template<typename BasicJsonType>
     static std::string get_byte_positions(const BasicJsonType* leaf_element)
     {
-        // a value-initialized iterator has no value (invalid_iterator.212)
+        if ((leaf_element->start_pos() != std::string::npos) && (leaf_element->end_pos() != std::string::npos))
-        if (leaf_element != nullptr && leaf_element->start_pos() != std::string::npos && leaf_element->end_pos() != std::string::npos)
         {
             return concat("(bytes ", std::to_string(leaf_element->start_pos()), "-", std::to_string(leaf_element->end_pos()), ") ");
         }
@@ -18476,11 +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;
             }
@@ -18504,7 +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.
     */
@@ -18563,6 +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
     {
@@ -19827,14 +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
@@ -20735,12 +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

@@ -5076,7 +5076,8 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (with JSON_DIAGNOSTICS, only
+/// if there is a path)
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -5097,11 +5098,12 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
-    // a value that is not found leaves no tokens, like the root
+    const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
-    static_cast<void>(edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens));
+    if (!found || tokens.empty())
-    if (!tokens.empty())
     {
-        // the root value has no path, but still has a byte range
+        // context is still empty; returning it keeps the copy elided (-Wnrvo)
+        return context;
+    }
     std::string path;
     for (const std::string& token : tokens)
     {
@@ -5109,7 +5111,6 @@ std::string diagnostics(const error_site site)
         path += detail::escape(token);
     }
     context = concat('(', path, ") ");
-    }
 #endif
 #if JSON_DIAGNOSTIC_POSITIONS
     std::size_t start = 0;

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-diagnostic-positions.cpp

@@ -193,28 +193,6 @@ TEST_CASE("Better diagnostics with positions")
         check_conversion(300);
     }
 
-    SECTION("exception about the root value (#5987)")
-    {
-        // the root has no path, but still has a byte range
-        const json root = json::parse("true");
-        const json nested = json::parse("[1, true]");
-        const json constructed = true;
-#if JSON_DIAGNOSTICS
-        CHECK_THROWS_WITH_AS(root.get<std::string>(),
-                             "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean", json::type_error);
-        CHECK_THROWS_WITH_AS(nested[1].get<std::string>(),
-                             "[json.exception.type_error.302] (/1) (bytes 4-8) type must be string, but is boolean", json::type_error);
-#else
-        CHECK_THROWS_WITH_AS(root.get<std::string>(),
-                             "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean", json::type_error);
-        CHECK_THROWS_WITH_AS(nested[1].get<std::string>(),
-                             "[json.exception.type_error.302] (bytes 4-8) type must be string, but is boolean", json::type_error);
-#endif
-        // a value without positions gets no range and no stray whitespace
-        CHECK_THROWS_WITH_AS(constructed.get<std::string>(),
-                             "[json.exception.type_error.302] type must be string, but is boolean", json::type_error);
-    }
-
     SECTION("JSON patch add to primitive parent (#4292)")
     {
         // the JSON Patch "add" target /foo/bar/baz has a string parent
@@ -265,14 +243,3 @@ TEST_CASE("values read from a binary format have no positions")
         check_no_positions(j);
     }
 }
-
-TEST_CASE("comparing a value-initialized iterator throws invalid_iterator.212")
-{
-    // such an iterator has no value to take the byte positions from; the
-    // comparison used to dereference the null pointer instead of throwing
-    json j = {1, 2};
-    json::iterator it{};
-    CHECK_THROWS_WITH_AS(it == j.begin(), "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
-    CHECK_THROWS_WITH_AS(it < j.begin(), "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
-    CHECK_THROWS_WITH_AS(j.begin() == it, "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
-}

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

@@ -300,27 +300,6 @@ TEST_CASE("json_view materialize() source positions")
             static_cast<void>(j.at("list").at(1).get<int>());
         }));
     }
-
-    SECTION("exception about the root value (#5987)")
-    {
-        const json_document root = json_document::parse("true");
-        const json_document nested = json_document::parse("[1, true]");
-        CHECK(json_view_test::exception_of_call([&]
-        {
-            static_cast<void>(root.root().get<std::string>());
-        }) == "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean");
-#if JSON_DIAGNOSTICS
-        CHECK(json_view_test::exception_of_call([&]
-        {
-            static_cast<void>(nested.root()[1].get<std::string>());
-        }) == "[json.exception.type_error.302] (/1) (bytes 4-8) type must be string, but is boolean");
-#else
-        CHECK(json_view_test::exception_of_call([&]
-        {
-            static_cast<void>(nested.root()[1].get<std::string>());
-        }) == "[json.exception.type_error.302] (bytes 4-8) type must be string, but is boolean");
-#endif
-    }
 #endif
 
     SECTION("edited documents")
@@ -542,7 +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);
@@ -571,8 +551,12 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         expected_zz += "(bytes 12-35) key 'zz' not found";
         CHECK(exception_of_call([&] { static_cast<void>(d.root().at(json::json_pointer("/people/0/zz"))); }) == expected_zz);
 
-        // the root has no path, but still its bytes (#5987)
+        // the root has no path, and with JSON_DIAGNOSTICS then no bytes either (as basic_json)
-        const std::string expected_missing = "[json.exception.out_of_range.403] (bytes 0-79) key 'missing' not found";
+        std::string expected_missing = "[json.exception.out_of_range.403] ";
+#if !JSON_DIAGNOSTICS
+        expected_missing += "(bytes 0-79) ";
+#endif
+        expected_missing += "key 'missing' not found";
         CHECK(exception_of_call([&] { static_cast<void>(d.root().at("missing")); }) == expected_missing);
     }
 

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);
+    }
+}