Fix old clang: do not declare the defaulted document_data() noexcept

With the nested struct object_index, clang 4 (and, by the same bug, the
clang 3.x of ci_test_compilers_clang) rejects the explicitly noexcept
defaulted constructor: "default member initializer for 'indexes' needed
within definition of enclosing class 'document_data' outside of member
functions". Nothing depends on the constructor being noexcept, so let it
take the implicit exception specification.

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

.github/labeler.yml

@@ -52,6 +52,7 @@ labels:
     - "single_include/nlohmann/json_view\\.hpp"
     - "tests/src/unit-json_view.*"
     - "tests/src/fuzzer-parse_json_view\\.cpp"
+    - "tests/benchmarks/json_view/.*"
     - "tools/amalgamate/config_json_view\\.json"
     - "docs/mkdocs/docs/features/json_view\\.md"
     - "docs/mkdocs/docs/api/basic_json_(document|view)/.*"

.github/workflows/json_view_benchmarks.yml

@@ -0,0 +1,78 @@
+name: "json_view benchmarks"
+
+# On demand only: runs the comparison of json_view with yyjson, simdjson, and
+# Boost.JSON (tests/benchmarks/json_view/compare.py) on GitHub-hosted runners,
+# for numbers from x86-64 and AArch64 Linux. It runs when started by hand, or
+# when a pull request gets the label "benchmark" (on both architectures, with
+# GCC and the default settings). Shared runners are noisy: the results show
+# where json_view stands, but published numbers need a quiet machine (see
+# tests/benchmarks/json_view/README.md).
+
+on:
+  pull_request:
+    types: [labeled]
+  workflow_dispatch:
+    inputs:
+      runner:
+        description: "Runner image"
+        type: choice
+        options:
+          - ubuntu-24.04
+          - ubuntu-24.04-arm
+        default: ubuntu-24.04
+      compiler:
+        description: "Compiler"
+        type: choice
+        options:
+          - g++
+          - clang++
+        default: g++
+      native:
+        description: "Compile for the runner's CPU (-march=native)"
+        type: boolean
+        default: false
+      rounds:
+        description: "Rounds of bench_view"
+        type: number
+        default: 30
+
+permissions:
+  contents: read
+
+jobs:
+  compare:
+    if: github.event_name == 'workflow_dispatch' || github.event.label.name == 'benchmark'
+    strategy:
+      matrix:
+        runner: ${{ fromJSON(github.event_name == 'workflow_dispatch' && format('["{0}"]', inputs.runner) || '["ubuntu-24.04", "ubuntu-24.04-arm"]') }}
+    runs-on: ${{ matrix.runner }}
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+
+      - name: Download test data
+        run: |
+          cmake -S . -B build -DJSON_BuildTests=On
+          cmake --build build --target download_test_data
+
+      - name: Run the comparison
+        env:
+          CXX: ${{ inputs.compiler || 'g++' }}
+          CC: ${{ inputs.compiler == 'clang++' && 'clang' || 'gcc' }}
+          ROUNDS: ${{ inputs.rounds || 30 }}
+          NATIVE: ${{ inputs.native && '--native' || '' }}
+        run: python3 tests/benchmarks/json_view/compare.py --data build/test_files --download --rounds "$ROUNDS" $NATIVE
+
+      - name: Summary
+        run: cat tests/benchmarks/json_view/results/*.md >> "$GITHUB_STEP_SUMMARY"
+
+      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: json_view-benchmarks-${{ matrix.runner }}-${{ inputs.compiler || 'g++' }}
+          path: tests/benchmarks/json_view/results/

BUILD.bazel

@@ -67,6 +67,7 @@ cc_library(
         "include/nlohmann/detail/string_utils.hpp",
         "include/nlohmann/detail/value_t.hpp",
         "include/nlohmann/detail/view/builder.hpp",
+        "include/nlohmann/detail/view/compare.hpp",
         "include/nlohmann/detail/view/document_data.hpp",
         "include/nlohmann/detail/view/errors.hpp",
         "include/nlohmann/detail/view/input.hpp",
@@ -77,8 +78,11 @@ cc_library(
         "include/nlohmann/detail/view/materialize.hpp",
         "include/nlohmann/detail/view/node.hpp",
         "include/nlohmann/detail/view/number.hpp",
+        "include/nlohmann/detail/view/object_index.hpp",
         "include/nlohmann/detail/view/pointer.hpp",
         "include/nlohmann/detail/view/scan.hpp",
+        "include/nlohmann/detail/view/serializer.hpp",
+        "include/nlohmann/detail/view/simd.hpp",
         "include/nlohmann/detail/view/string_ref.hpp",
         "include/nlohmann/detail/view/value.hpp",
         "include/nlohmann/json.hpp",

README.md

@@ -1405,6 +1405,7 @@ THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR I
 - The class contains parts of [Google Abseil](https://github.com/abseil/abseil-cpp) which is licensed under the [Apache 2.0 License](https://opensource.org/licenses/Apache-2.0).
 - The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors
 - The view's parser (`<nlohmann/json_view.hpp>`) contains techniques and code adapted from [yyjson](https://github.com/ibireme/yyjson) by YaoYuan, which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above): table-driven decoding of `\u` escapes and fixed-offset unrolled checks.
+- The view's parser (`<nlohmann/json_view.hpp>`) validates non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors
 
 <img align="right" src="https://git.fsfe.org/reuse/reuse-ci/raw/branch/master/reuse-horizontal.png" alt="REUSE Software">
 

docs/docset/docSet.sql

@@ -150,6 +150,7 @@ INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::cbegin', 'Me
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::cend', 'Method', 'api/basic_json_view/cend/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::contains', 'Method', 'api/basic_json_view/contains/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::count', 'Method', 'api/basic_json_view/count/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::dump', 'Method', 'api/basic_json_view/dump/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::empty', 'Method', 'api/basic_json_view/empty/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::end', 'Method', 'api/basic_json_view/end/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::find', 'Method', 'api/basic_json_view/find/index.html');
@@ -172,9 +173,13 @@ INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::is_string',
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::is_structured', 'Method', 'api/basic_json_view/is_structured/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::items', 'Method', 'api/basic_json_view/items/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::materialize', 'Method', 'api/basic_json_view/materialize/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::number_format', 'Enum', 'api/basic_json_view/number_format/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::number_token', 'Method', 'api/basic_json_view/number_token/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::operator bool', 'Method', 'api/basic_json_view/operator_bool/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::operator<<', 'Operator', 'api/basic_json_view/operator_ltlt/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::operator[]', 'Operator', 'api/basic_json_view/operator[]/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::operator==', 'Operator', 'api/basic_json_view/operator_eq/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::operator!=', 'Operator', 'api/basic_json_view/operator_ne/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::size', 'Method', 'api/basic_json_view/size/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::source_offset', 'Method', 'api/basic_json_view/source_offset/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('basic_json_view::type', 'Method', 'api/basic_json_view/type/index.html');
@@ -302,3 +307,5 @@ INSERT INTO searchIndex(name, type, path) VALUES ('NLOHMANN_JSON_SERIALIZE_ENUM'
 INSERT INTO searchIndex(name, type, path) VALUES ('NLOHMANN_JSON_VERSION_MAJOR', 'Macro', 'api/macros/nlohmann_json_version_major/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('NLOHMANN_JSON_VERSION_MINOR', 'Macro', 'api/macros/nlohmann_json_version_major/index.html');
 INSERT INTO searchIndex(name, type, path) VALUES ('NLOHMANN_JSON_VERSION_PATCH', 'Macro', 'api/macros/nlohmann_json_version_major/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('JSON_VIEW_NO_SIMD', 'Macro', 'api/macros/json_view_no_simd/index.html');
+INSERT INTO searchIndex(name, type, path) VALUES ('JSON_VIEW_USE_SSSE3', 'Macro', 'api/macros/json_view_use_ssse3/index.html');

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

@@ -86,6 +86,8 @@ Binary values are serialized as an object containing two keys:
 
 - [to_string](to_string.md) returns a string representation of a JSON value
 - [operator<<](../operator_ltlt.md) serialize to stream
+- [`basic_json_view::dump`](../basic_json_view/dump.md) the corresponding function of `basic_json_view`, serializing
+  directly from a flat index without building a `basic_json` value
 - [Serialization](../../features/serialization.md) - the serialization article
 
 ## Version history

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

@@ -166,6 +166,8 @@ Linear.
 
 - [operator!=](operator_ne.md) compare for inequality
 - [operator<=>](operator_spaceship.md) comparison: 3-way (C++20)
+- [basic_json_view::operator==](../basic_json_view/operator_eq.md) - the same comparison on a zero-copy view, without
+  building a `basic_json` value for it
 
 ## Version history
 

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

@@ -89,6 +89,12 @@ Linear.
     --8<-- "examples/operator__notequal__nullptr_t.output"
     ```
 
+## See also
+
+- [operator==](operator_eq.md) compare for equality
+- [basic_json_view::operator!=](../basic_json_view/operator_ne.md) - the same comparison on a zero-copy view, without
+  building a `basic_json` value for it
+
 ## Version history
 
 1. Added in version 1.0.0. Added C++20 member functions in version 3.11.0. Changed in version 3.13.0 to remove 

docs/mkdocs/docs/api/basic_json_view/at.md

@@ -74,6 +74,8 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics
 1. Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after
    another, in document order, stopping at the first match. Each comparison first checks the key's length --
    already known from the index, without reading the key bytes -- before comparing its content.
+   Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time
+   on average.
 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the
    index (unlike `BasicJsonType`'s array, which is random-access).
 3. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at

docs/mkdocs/docs/api/basic_json_view/contains.md

@@ -35,6 +35,8 @@ No-throw guarantee: this function never throws exceptions.
 1. Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after
    another, in document order, stopping at the first match. Each comparison first checks the key's length -- already
    known from the index, without reading the key bytes -- before comparing its content.
+   Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time
+   on average.
 2. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at
    that level or the index into the array -- as for [`operator[]`](operator[].md#complexity) and
    [`at`](at.md#complexity) with a JSON pointer.

docs/mkdocs/docs/api/basic_json_view/count.md

@@ -26,6 +26,8 @@ No-throw guarantee: this function never throws exceptions.
 Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after
 another, in document order, stopping at the first match. Each comparison first checks the key's length -- already
 known from the index, without reading the key bytes -- before comparing its content.
+Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time on
+average.
 
 ## Notes
 

docs/mkdocs/docs/api/basic_json_view/dump.md

@@ -0,0 +1,102 @@
+# <small>nlohmann::basic_json_view::</small>dump
+
+```cpp
+string_t dump(const int indent = -1,
+              const char indent_char = ' ',
+              const bool ensure_ascii = false,
+              const number_format numbers = number_format::shortest) const;
+```
+
+Serializes this value (and its subtree) directly from the flat index, without ever building a `BasicJsonType` value
+first. With the default `#!cpp numbers == number_format::shortest`, the result is the same string
+[`BasicJsonType::dump`](../basic_json/dump.md) would produce for the value
+[`BasicJsonType::parse()`](../basic_json/parse.md) builds from the same source text, called with the same `indent`,
+`indent_char`, and `ensure_ascii` -- except that members of an object appear in document order rather than sorted by
+key, and *every* occurrence of a repeated key is written rather than only the last one (see
+[Notes on duplicate keys](operator[].md#notes)). For a `json_view` (whose `BasicJsonType` is not ordered), this means
+`dump()` can print an object's members in a different order than [`materialize()`](materialize.md)`.dump()` of the
+same subtree.
+
+## Parameters
+
+`indent` (in)
+:   If `indent` is nonnegative, array elements and object members are pretty-printed with that indent level. An
+    indent level of `0` only inserts newlines. `-1` (the default) selects the most compact representation.
+
+`indent_char` (in)
+:   The character used for indentation if `indent` is greater than `0`. The default is ` ` (space).
+
+`ensure_ascii` (in)
+:   If `ensure_ascii` is `#!cpp true`, all non-ASCII characters in the output are escaped with `\uXXXX` sequences, and
+    the result consists of ASCII characters only.
+
+`numbers` (in)
+:   how to write numbers, see [`number_format`](number_format.md): `shortest` (the default) writes them the way
+    [`BasicJsonType::dump`](../basic_json/dump.md) would; `source` copies every number exactly as it appears in the
+    source text.
+
+## Return value
+
+string containing the serialization of this value, or `#!cpp "<discarded>"` if the view is
+[discarded](is_discarded.md).
+
+## Exception safety
+
+Strong exception safety: if an exception is thrown, there are no changes to the view or the document it refers to.
+
+## Exceptions
+
+May throw `#!cpp std::bad_alloc` if allocating the output string fails. Unlike
+[`BasicJsonType::dump`](../basic_json/dump.md), there is no `error_handler` parameter and no
+[`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316): the view only ever holds text the parser
+already validated as UTF-8, so there is nothing to replace or ignore.
+
+## Complexity
+
+Linear in the size of the output text.
+
+## Notes
+
+The walk over the subtree is iterative, so the nesting depth it can write is limited by available memory only, not by
+the call stack -- as for [`materialize()`](materialize.md).
+
+Strings are escaped by the same rules as [`BasicJsonType::dump`](../basic_json/dump.md). With
+`#!cpp numbers == number_format::shortest`, floats are written with the library's shortest round-trip conversion,
+exactly as [`BasicJsonType::dump`](../basic_json/dump.md) would (e.g. `#!cpp 1.5`, `#!cpp 100.0`, `#!cpp 1e+100`), and
+integers are copied from the source text -- already canonical in JSON, so this matches their shortest form too --
+except that `#!cpp -0` is written as `#!cpp 0`, the way [`BasicJsonType::parse()`](../basic_json/parse.md) reads it.
+`#!cpp number_format::source` copies every number exactly as written in the source text instead, with no exception
+for `#!cpp -0` -- `#!cpp 1.50`, `#!cpp 1E2`, `#!cpp -0.0`, `#!cpp -0`, or all digits of an integer literal with more
+digits than any number type holds (such a literal is itself classified as a float, see
+[What is different](../../features/json_view.md#what-is-different)) -- something `BasicJsonType` cannot do, since
+parsing already reduces every number to its parsed value.
+
+## Examples
+
+??? example
+
+    The example below forwards a single record out of a larger batch, and re-serializes a configuration file, both
+    without ever building a `BasicJsonType` value for the surrounding array or for the parts of it that were not
+    needed. It also shows that [`materialize()`](materialize.md)`.dump()` of the configuration sorts its keys, where
+    `dump()` on the view keeps the order they appear in the source text.
+
+    ```cpp
+    --8<-- "examples/basic_json_view__dump.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/basic_json_view__dump.output"
+    ```
+
+## See also
+
+- [`number_format`](number_format.md) - how `dump()` writes numbers
+- [operator<<](operator_ltlt.md) - serialize this value to a stream
+- [materialize](materialize.md) - build a `BasicJsonType` value, e.g. to use `BasicJsonType::dump`'s `error_handler`
+- [`BasicJsonType::dump`](../basic_json/dump.md) - the corresponding function of `basic_json`
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_view/find.md

@@ -28,6 +28,8 @@ No-throw guarantee: this function never throws exceptions.
 Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after
 another, in document order, stopping at the first match. Each comparison first checks the key's length -- already
 known from the index, without reading the key bytes -- before comparing its content.
+Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time on
+average.
 
 ## Notes
 

docs/mkdocs/docs/api/basic_json_view/index.md

@@ -20,11 +20,12 @@ Moving the document itself does not invalidate its views: the index is heap-allo
 `basic_json_document` object.
 
 `basic_json_view` provides the read-only part of the `BasicJsonType` interface: the type-inspection functions, element
-access, lookup, iteration, and conversion -- [`get<T>()`](get.md), [`get_string()`](get_string.md),
+access, lookup, iteration, conversion, and comparison -- [`get<T>()`](get.md), [`get_string()`](get_string.md),
 [`number_token()`](number_token.md), and [`materialize()`](materialize.md) to build the `BasicJsonType` value of a
 subtree on demand. [`operator[]`](operator%5B%5D.md), [`at`](at.md), [`contains`](contains.md), and
-[`value`](value.md) also accept a [`json_pointer`](../json_pointer/index.md). It does not (yet) provide `dump()` or
+[`value`](value.md) also accept a [`json_pointer`](../json_pointer/index.md). [`operator==`](operator_eq.md) and
-comparison.
+[`operator!=`](operator_ne.md) compare two views, or a view and a `BasicJsonType` value, without ever building a
+`BasicJsonType` value for a view; no ordering comparison (`#!cpp operator<`) is provided.
 
 ## Template parameters
 
@@ -47,6 +48,7 @@ comparison.
 - **iterator**, **const_iterator** - a forward iterator over the elements of an array or the member values of an
   object, in document order; both names refer to the same type, since a view is always read-only
 - **item** - a (key, value) pair produced by [`items()`](items.md)
+- [**number_format**](number_format.md) - how [`dump()`](dump.md) writes numbers
 
 ## Member functions
 
@@ -106,6 +108,16 @@ comparison.
 - [**number_token**](number_token.md) - get a number's token text without a copy
 - [**materialize**](materialize.md) - build the `BasicJsonType` value of this subtree
 
+### Comparison
+
+- [**operator==**](operator_eq.md) - comparison: equal
+- [**operator!=**](operator_ne.md) - comparison: not equal
+
+### Serialization
+
+- [**dump**](dump.md) - serialize to a JSON-formatted string
+- [**operator<<**](operator_ltlt.md) - serialize to stream
+
 ### Source access
 
 - [**source_offset**](source_offset.md) - byte offset of this value in the document's source text

docs/mkdocs/docs/api/basic_json_view/number_format.md

@@ -0,0 +1,51 @@
+# <small>nlohmann::basic_json_view::</small>number_format
+
+```cpp
+enum class number_format {
+    shortest,
+    source
+};
+```
+
+This enumeration is used in [`dump`](dump.md) to choose how numbers are written. Two values are differentiated:
+
+shortest
+:   integers are copied from the source text -- already canonical in JSON -- except that `#!cpp -0` becomes
+    `#!cpp 0`, the way [`BasicJsonType::parse()`](../basic_json/parse.md) reads it; floats are written with the
+    library's shortest round-trip conversion, exactly as [`BasicJsonType::dump()`](../basic_json/dump.md) would (e.g.
+    `#!cpp 1.5`, `#!cpp 100.0`, `#!cpp 1e+100`)
+
+source
+:   every number is copied exactly as it appears in the source text -- `#!cpp 1.50`, `#!cpp 1E2`, `#!cpp -0`, all
+    digits of an integer literal with more digits than any number type holds -- something `BasicJsonType` cannot do,
+    since parsing already reduces every number to its parsed value
+
+## Examples
+
+??? example
+
+    The example below writes back a price list received from a supplier: with `number_format::shortest` (the
+    default), a trailing zero and scientific notation are normalized away and a long account number that overflows
+    every number type is rounded, the same way `#!cpp materialize().dump()` (or `basic_json::dump()`) would;
+    `number_format::source` keeps every number exactly as it was written in the source text instead.
+
+    ```cpp
+    --8<-- "examples/basic_json_view__number_format.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/basic_json_view__number_format.output"
+    ```
+
+## See also
+
+- [dump](dump.md) - serialize to a JSON-formatted string
+- [number_token](number_token.md) - get a single number's token text without dumping the whole value
+- [`BasicJsonType::error_handler_t`](../basic_json/error_handler_t.md) - the analogous enumeration for
+  `BasicJsonType::dump`'s decoding-error behavior
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_view/operator[].md

@@ -76,6 +76,8 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics
    another, in document order, stopping at the first match. Each comparison first checks the key's length --
    already known from the index, without reading the key bytes -- before comparing its content, so a key of a
    different length than `key` is rejected without touching the source text.
+   Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time
+   on average.
 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the
    index (unlike `BasicJsonType`'s array, which is random-access).
 3. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at

docs/mkdocs/docs/api/basic_json_view/operator_eq.md

@@ -0,0 +1,107 @@
+# <small>nlohmann::basic_json_view::</small>operator==
+
+```cpp
+// (1)
+bool operator==(const basic_json_view& lhs, const basic_json_view& rhs);
+
+// (2)
+bool operator==(const basic_json_view& lhs, const BasicJsonType& rhs);
+bool operator==(const BasicJsonType& lhs, const basic_json_view& rhs);
+```
+
+1. Compares two views for equality: whether the values [`BasicJsonType::parse()`](../basic_json/parse.md) would
+   produce for `lhs` and `rhs` are equal, according to `BasicJsonType`'s [`operator==`](../basic_json/operator_eq.md).
+2. Compares a view and a `BasicJsonType` value for equality, in either order: whether the value `parse()` would
+   produce for the view and the other operand are equal, according to `BasicJsonType`'s
+   [`operator==`](../basic_json/operator_eq.md).
+
+Neither overload builds a `BasicJsonType` value for a view to do the comparison (see [Notes](#notes) below). Numbers
+compare by value across their types (`#!cpp 1 == 1.0`), and an object compares by its members, with duplicate keys
+resolved exactly as `parse()` resolves them -- the last value, at the position of the first occurrence of the key.
+
+## Parameters
+
+`lhs` (in)
+:   first value to consider
+
+`rhs` (in)
+:   second value to consider
+
+## Return value
+
+whether the values `lhs` and `rhs` are equal
+
+## Exception safety
+
+Strong exception safety: if an exception is thrown, there are no changes to either operand, or to the document(s) a
+view refers to.
+
+## Exceptions
+
+May throw `#!cpp std::bad_alloc`. Unlike the other comparison and most other `basic_json_view` functions,
+`operator==` is not `#!cpp noexcept`: resolving an object's members needs a temporary array to sort them by key (see
+[Complexity](#complexity) below), and that allocation can fail.
+
+## Complexity
+
+Linear in the size of the compared values: every number, string, array element, and object member is visited at most
+once, and the walk is iterative, so the nesting depth it can compare is limited by available memory only, not by the
+call stack (as for [`materialize()`](materialize.md)). Resolving an object's members takes an additional O(n log n)
+in the number of members at that level, since they are sorted by key to detect and resolve duplicates before being
+compared. Two arrays of different [`size()`](size.md) are rejected without visiting either one's elements.
+
+## Notes
+
+Only a single number, boolean, or `#!cpp null` value is ever materialized into a `BasicJsonType`, to reuse its
+`operator==` -- for numbers, so that values written differently in the source text but equal in value (e.g. an
+integer and a floating-point literal) still compare equal, following the same rules `BasicJsonType` does for special
+values such as `#!cpp NaN`. Constructing one of these scalars never allocates. Strings are compared directly, without
+allocating, either from the source text on both sides or, for overload 2, against `BasicJsonType`'s own string.
+Arrays and objects are never materialized at all; only their elements or members are visited, one pair at a time.
+
+!!! info "How objects are compared"
+
+    For a [`json_view`](../json_view.md) (`BasicJsonType::object_t` is `#!cpp std::map`), members are compared by
+    key, regardless of the order they appear in the source text. For an
+    [`ordered_json_view`](../ordered_json_view.md) (`object_t` is `ordered_map`), they are compared in the order
+    they occur, so the very same two objects with their members reordered can compare equal as `json_view`s but not
+    as `ordered_json_view`s. This is exactly how [`json`](../json.md) and [`ordered_json`](../ordered_json.md)
+    compare, see ["Comparing different `basic_json` specializations"](../basic_json/operator_eq.md#notes).
+
+!!! info "Discarded views"
+
+    A [discarded](is_discarded.md) view compares the same way a discarded `BasicJsonType` value does, which is
+    governed by
+    [`JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON`](../macros/json_use_legacy_discarded_value_comparison.md): by
+    default, a discarded view is never equal to anything, not even another discarded view.
+
+No ordering comparison (`#!cpp operator<`) is provided for `basic_json_view`; [`materialize()`](materialize.md) is
+the way to get a `BasicJsonType` value that supports it.
+
+## Examples
+
+??? example
+
+    The example below checks whether a newly received configuration differs from the previous one, and whether a
+    received document matches what a test expects -- directly on views, without ever materializing a `BasicJsonType`
+    value for either side.
+
+    ```cpp
+    --8<-- "examples/basic_json_view__operator_eq.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/basic_json_view__operator_eq.output"
+    ```
+
+## See also
+
+- [operator!=](operator_ne.md) - compare for inequality
+- [materialize](materialize.md) - build a `BasicJsonType` value, e.g. to keep comparing after the document is gone
+- [`BasicJsonType::operator==`](../basic_json/operator_eq.md) - the corresponding function of `basic_json`
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_view/operator_ltlt.md

@@ -0,0 +1,74 @@
+# <small>nlohmann::basic_json_view::</small>operator<<
+
+```cpp
+std::ostream& operator<<(std::ostream& o, const basic_json_view& v);
+```
+
+Not available when [`JSON_NO_IO`](../macros/json_no_io.md) is defined.
+
+Serializes the given view `v` to the output stream `o`, using [`dump`](dump.md) -- exactly as
+`#!cpp operator<<(std::ostream&, const basic_json&)` does for a `basic_json` value.
+
+- The indentation of the output can be controlled with the member variable `width` of the output stream `o`. For
+  instance, using the manipulator `std::setw(4)` on `o` sets the indentation level to `4`, and the serialization
+  result is the same as calling `#!cpp v.dump(4)`. A `width` of `0` or less (the default) selects the most compact
+  representation, as `#!cpp v.dump(-1)` does.
+- The indentation character can be controlled with the member variable `fill` of the output stream `o`. For instance,
+  the manipulator `std::setfill('\t')` sets indentation to use a tab character rather than the default space
+  character.
+- As for `basic_json`, `o`'s `width` is reset to `0` after this call, whether or not it was greater than `0` before.
+
+Numbers are always written as `#!cpp v.dump()` writes them by default, i.e. as with
+[`number_format::shortest`](number_format.md); there is no way to select `#!cpp number_format::source` through the
+stream.
+
+## Parameters
+
+`o` (in, out)
+:   stream to write to
+
+`v` (in)
+:   view to serialize
+
+## Return value
+
+the stream `o`
+
+## Exceptions
+
+May throw `#!cpp std::bad_alloc`, propagated from [`dump`](dump.md#exceptions). Unlike
+`#!cpp operator<<(std::ostream&, const basic_json&)`, there is no UTF-8 decoding step that could throw
+[`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316), and no `error_handler` to choose between --
+see the [Exceptions](dump.md#exceptions) of `dump`.
+
+## Complexity
+
+Linear, as [`dump`](dump.md#complexity).
+
+## Examples
+
+??? example
+
+    The example below writes one record out of a larger batch straight to a log stream -- compact for a one-line
+    entry, and pretty-printed with `std::setw`/`std::setfill` for a readable dump -- without ever building a
+    `BasicJsonType` value for the record, or for the rest of the batch.
+
+    ```cpp
+    --8<-- "examples/basic_json_view__operator_ltlt.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/basic_json_view__operator_ltlt.output"
+    ```
+
+## See also
+
+- [dump](dump.md) - serialize to a JSON-formatted string
+- [`operator<<(std::ostream&)`](../operator_ltlt.md) - the corresponding operator for `basic_json`
+- [`JSON_NO_IO`](../macros/json_no_io.md) - switch off functions relying on certain C++ I/O headers
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_view/operator_ne.md

@@ -0,0 +1,82 @@
+# <small>nlohmann::basic_json_view::</small>operator!=
+
+```cpp
+// (1)
+bool operator!=(const basic_json_view& lhs, const basic_json_view& rhs);
+
+// (2)
+bool operator!=(const basic_json_view& lhs, const BasicJsonType& rhs);
+bool operator!=(const BasicJsonType& lhs, const basic_json_view& rhs);
+```
+
+1. Compares two views for inequality. Returns `#!cpp !(lhs == rhs)`, see [operator==](operator_eq.md).
+2. Compares a view and a `BasicJsonType` value for inequality, in either order. Returns `#!cpp !(lhs == rhs)` (or,
+   for the reversed order, `#!cpp !(rhs == lhs)`), see [operator==](operator_eq.md).
+
+Since `operator!=` is defined as the negation of [`operator==`](operator_eq.md), it follows the same rules for
+special cases: for instance, since a [discarded](is_discarded.md) view is never equal to anything by default (see
+[operator=='s Notes](operator_eq.md#notes)), it is never *unequal* to anything either -- `#!cpp discarded != discarded`
+is also `#!cpp false`, exactly as for a discarded `BasicJsonType` value.
+
+## Parameters
+
+`lhs` (in)
+:   first value to consider
+
+`rhs` (in)
+:   second value to consider
+
+## Return value
+
+whether the values `lhs` and `rhs` are not equal
+
+## Exception safety
+
+Strong exception safety: if an exception is thrown, there are no changes to either operand, or to the document(s) a
+view refers to.
+
+## Exceptions
+
+May throw `#!cpp std::bad_alloc`, propagated from [`operator==`](operator_eq.md#exceptions). Unlike most other
+`basic_json_view` functions, `operator!=` is not `#!cpp noexcept`.
+
+## Complexity
+
+Linear, as [`operator==`](operator_eq.md#complexity).
+
+## Notes
+
+See the [Notes](operator_eq.md#notes) of `operator==` -- in particular for how an object's members are compared
+(order matters for [`ordered_json_view`](../ordered_json_view.md) but not for [`json_view`](../json_view.md)) and
+for how discarded views compare.
+
+No ordering comparison (`#!cpp operator<`) is provided for `basic_json_view`; [`materialize()`](materialize.md) is
+the way to get a `BasicJsonType` value that supports it.
+
+## Examples
+
+??? example
+
+    The example below asserts, as a test would, that a received document differs from an unwanted value, and shows
+    that -- as for [`json`](../json.md)/[`ordered_json`](../ordered_json.md) -- reordering an object's members is
+    detected as a difference for an `ordered_json_view` but not for a `json_view`.
+
+    ```cpp
+    --8<-- "examples/basic_json_view__operator_ne.cpp"
+    ```
+
+    Output:
+
+    ```json
+    --8<-- "examples/basic_json_view__operator_ne.output"
+    ```
+
+## See also
+
+- [operator==](operator_eq.md) - compare for equality
+- [materialize](materialize.md) - build a `BasicJsonType` value, e.g. to keep comparing after the document is gone
+- [`BasicJsonType::operator!=`](../basic_json/operator_ne.md) - the corresponding function of `basic_json`
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/basic_json_view/value.md

@@ -70,6 +70,8 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics
 1. Linear in the number of members: as for [`operator[]`](operator[].md#complexity), members are compared one after
    another, in document order, stopping at the first match. Plus the complexity of converting the found member to
    `T` (see [`get`](get.md)).
+   Objects with 128 or more members get a hash index while parsing, so that a lookup in them takes constant time
+   on average.
 2. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at
    that level or the index into the array -- as for the [`operator[]`](operator[].md#complexity) and
    [`at`](at.md#complexity) overloads that take a JSON pointer. Plus the complexity of converting the resolved value

docs/mkdocs/docs/api/macros/index.md

@@ -34,6 +34,8 @@ header. See also the [macro overview page](../../features/macros.md).
 - [**JSON_SKIP_UNSUPPORTED_COMPILER_CHECK**](json_skip_unsupported_compiler_check.md) - do not warn about unsupported compilers
 - [**JSON_USE_GLOBAL_UDLS**](json_use_global_udls.md) - place user-defined string literals (UDLs) into the global namespace
 - [**JSON_USE_SIMDUTF**](json_use_simdutf.md) - use the simdutf library to accelerate UTF-8 validation
+- [**JSON_VIEW_NO_SIMD**](json_view_no_simd.md) - use only portable code in the parser of `json_view.hpp`
+- [**JSON_VIEW_USE_SSSE3**](json_view_use_ssse3.md) - validate non-ASCII strings with SSSE3 in the parser of `json_view.hpp`
 
 ## Library version
 

docs/mkdocs/docs/api/macros/json_view_no_simd.md

@@ -0,0 +1,50 @@
+# JSON_VIEW_NO_SIMD
+
+```cpp
+#define JSON_VIEW_NO_SIMD
+```
+
+When defined, the parser of [`basic_json_document`](../basic_json_document/index.md) (`<nlohmann/json_view.hpp>`)
+uses only portable C++ to scan strings. By default, it scans long runs of string bytes 16 at a time with NEON on
+AArch64 (with GCC and Clang) and SSE2 on x86-64, which are part of the baseline instruction sets of these
+architectures, and validates non-ASCII text with NEON (or SSSE3, see
+[`JSON_VIEW_USE_SSSE3`](json_view_use_ssse3.md)).
+
+The same input is accepted or rejected either way, with the same values, and errors are reported the same way; only
+the speed differs. The macro exists for platforms whose compilers lack the intrinsics headers, and to test the portable
+code.
+
+!!! warning "Define consistently"
+
+    The macro selects between two definitions of the same inline functions. It must therefore be defined identically for
+    **every** translation unit that includes `<nlohmann/json_view.hpp>`; prefer a compile definition on the target.
+
+## Default definition
+
+By default, `#!cpp JSON_VIEW_NO_SIMD` is not defined, and the vector code is used where available.
+
+```cpp
+#undef JSON_VIEW_NO_SIMD
+```
+
+## Examples
+
+??? example
+
+    The code below uses the portable string scanning of the view.
+
+    ```cpp
+    #define JSON_VIEW_NO_SIMD
+    #include <nlohmann/json_view.hpp>
+
+    ...
+    ```
+
+## See also
+
+- [JSON_VIEW_USE_SSSE3](json_view_use_ssse3.md) - validate non-ASCII strings with SSSE3 on x86-64
+- [json_view](../../features/json_view.md) - the zero-copy view
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/macros/json_view_use_ssse3.md

@@ -0,0 +1,49 @@
+# JSON_VIEW_USE_SSSE3
+
+```cpp
+#define JSON_VIEW_USE_SSSE3
+```
+
+When defined on x86-64, the parser of [`basic_json_document`](../basic_json_document/index.md)
+(`<nlohmann/json_view.hpp>`) validates non-ASCII text in strings with SSSE3, 16 bytes at a time, using the "lookup4"
+algorithm of [simdjson](https://github.com/simdjson/simdjson). Without it, non-ASCII text is validated one UTF-8
+sequence at a time on x86-64; on AArch64, the vector check uses NEON and is always on.
+
+SSSE3 is not part of the x86-64 baseline, so the code must be compiled for it: define the macro only together with a
+compiler option that enables SSSE3 (e.g. `-mssse3`, or `-march=` with a CPU that has it), and only for programs that
+run on such CPUs. The same input is accepted or rejected either way; only the speed of non-ASCII text differs.
+
+!!! warning "Define consistently"
+
+    The macro selects between two definitions of the same inline functions. It must therefore be defined identically,
+    with the same compiler options, for **every** translation unit that includes `<nlohmann/json_view.hpp>`; mixing
+    translation units that define it with ones that do not is an ODR violation. Prefer a compile definition on the
+    target.
+
+## Default definition
+
+By default, `#!cpp JSON_VIEW_USE_SSSE3` is not defined.
+
+```cpp
+#undef JSON_VIEW_USE_SSSE3
+```
+
+## Examples
+
+??? example
+
+    With CMake, for a program that only runs on CPUs with SSSE3:
+
+    ```cmake
+    target_compile_definitions(your_target PRIVATE JSON_VIEW_USE_SSSE3)
+    target_compile_options(your_target PRIVATE -mssse3)
+    ```
+
+## See also
+
+- [JSON_VIEW_NO_SIMD](json_view_no_simd.md) - use only portable code in the view's parser
+- [JSON_USE_SIMDUTF](json_use_simdutf.md) - validate UTF-8 with simdutf in `basic_json`'s parser
+
+## Version history
+
+- Added in version 3.13.0.

docs/mkdocs/docs/api/operator_ltlt.md

@@ -84,6 +84,8 @@ Linear.
 ## See also
 
 - [dump](basic_json/dump.md) - serialize to a JSON-formatted string
+- [`basic_json_view::operator<<`](basic_json_view/operator_ltlt.md) - the corresponding operator for
+  `basic_json_view`
 - [Serialization](../features/serialization.md) - the serialization article
 
 ## Version history

docs/mkdocs/docs/examples/basic_json_view__dump.cpp

@@ -0,0 +1,25 @@
+#include <iostream>
+#include <nlohmann/json_view.hpp>
+
+using json_document = nlohmann::json_document;
+using json_view = nlohmann::json_view;
+
+int main()
+{
+    // a large batch of sensor readings -- forward just the one that changed,
+    // without ever building a basic_json value for the batch or for the
+    // readings that are not needed
+    const json_document batch = json_document::parse(R"(
+      [{"id": 1, "temp": 21.5}, {"id": 2, "temp": 87.3}, {"id": 3, "temp": 21.7}]
+    )");
+    const json_view readings = batch.root();
+    std::cout << readings[1].dump() << '\n';
+
+    // a configuration file -- dump() on the view keeps the member order of
+    // the source text; a json value's object_t is std::map, so
+    // materialize().dump() of the very same view sorts the keys instead
+    const json_document config = json_document::parse(
+                                     R"({"name": "cache", "host": "db1", "port": 6379, "timeout": 30})");
+    std::cout << config.root().dump(2) << "\n\n";
+    std::cout << config.root().materialize().dump(2) << '\n';
+}

docs/mkdocs/docs/examples/basic_json_view__dump.output

@@ -0,0 +1,14 @@
+{"id":2,"temp":87.3}
+{
+  "name": "cache",
+  "host": "db1",
+  "port": 6379,
+  "timeout": 30
+}
+
+{
+  "host": "db1",
+  "name": "cache",
+  "port": 6379,
+  "timeout": 30
+}

docs/mkdocs/docs/examples/basic_json_view__number_format.cpp

@@ -0,0 +1,28 @@
+#include <iostream>
+#include <nlohmann/json_view.hpp>
+
+using json_document = nlohmann::json_document;
+using json_view = nlohmann::json_view;
+
+int main()
+{
+    // a price list received from a supplier feed -- prices and account
+    // numbers must be forwarded exactly, e.g. into an invoice
+    const json_document doc = json_document::parse(R"(
+      [{"sku": "A1", "price": 19.90, "account_id": 12345678901234567890123456},
+       {"sku": "A2", "price": 1E2, "account_id": 98765432109876543210987654}]
+    )");
+    const json_view list = doc.root();
+
+    // number_format::shortest (the default) writes numbers the way
+    // basic_json::dump() would: "19.90" becomes "19.9", "1E2" becomes
+    // "100.0", and each account number -- far beyond any 64-bit integer --
+    // is rounded to the nearest double, exactly as materialize().dump()
+    // (or a plain nlohmann::json) would round it
+    std::cout << list.dump() << '\n';
+
+    // number_format::source copies every number exactly as it was written
+    // in the source text instead -- something basic_json cannot do at all,
+    // since parsing already reduces every number to its parsed value
+    std::cout << list.dump(-1, ' ', false, json_view::number_format::source) << '\n';
+}

docs/mkdocs/docs/examples/basic_json_view__number_format.output

@@ -0,0 +1,2 @@
+[{"sku":"A1","price":19.9,"account_id":1.2345678901234568e+25},{"sku":"A2","price":100.0,"account_id":9.876543210987655e+25}]
+[{"sku":"A1","price":19.90,"account_id":12345678901234567890123456},{"sku":"A2","price":1E2,"account_id":98765432109876543210987654}]

docs/mkdocs/docs/examples/basic_json_view__operator_eq.cpp

@@ -0,0 +1,30 @@
+#include <iostream>
+#include <nlohmann/json_view.hpp>
+
+using json_document = nlohmann::json_document;
+using json = nlohmann::json;
+
+int main()
+{
+    // two snapshots of a polled configuration endpoint -- compare them
+    // directly as views, without ever building a nlohmann::json value for
+    // either one
+    const json_document previous = json_document::parse(
+                                       R"({"name": "cache", "port": 6379, "timeout": 30})");
+    const json_document current = json_document::parse(
+                                      R"({"port": 6379.0, "timeout": 30, "name": "cache"})");
+
+    // same members, reordered, and 6379 written as a float -- operator==
+    // treats them the same way BasicJsonType::operator== would
+    std::cout << std::boolalpha << (previous.root() == current.root()) << '\n';
+
+    // an actually changed value is detected the same way
+    const json_document changed = json_document::parse(
+                                      R"({"name": "cache", "port": 6380, "timeout": 30})");
+    std::cout << (previous.root() == changed.root()) << '\n';
+
+    // comparing a view directly against an expected json value -- handy in a
+    // test, without materializing the received document at all
+    const json expected = {{"name", "cache"}, {"port", 6379}, {"timeout", 30}};
+    std::cout << (previous.root() == expected) << '\n';
+}

docs/mkdocs/docs/examples/basic_json_view__operator_eq.output

@@ -0,0 +1,3 @@
+true
+false
+true

docs/mkdocs/docs/examples/basic_json_view__operator_ltlt.cpp

@@ -0,0 +1,26 @@
+#include <iostream>
+#include <iomanip>
+#include <nlohmann/json_view.hpp>
+
+using json_document = nlohmann::json_document;
+using json_view = nlohmann::json_view;
+
+int main()
+{
+    // one order out of a large incoming batch -- write it straight to a log
+    // stream without ever building a basic_json value for it, or for the
+    // rest of the batch
+    const json_document doc = json_document::parse(R"(
+      [{"id": 1, "item": "cable"}, {"id": 2, "item": "adapter"}]
+    )");
+    const json_view orders = doc.root();
+
+    // compact, for a one-line log entry
+    std::cout << orders[1] << '\n';
+
+    // std::setw sets the indentation level, exactly as for basic_json
+    std::cout << std::setw(2) << orders[1] << "\n\n";
+
+    // std::setfill changes the indentation character
+    std::cout << std::setw(1) << std::setfill('\t') << orders[1] << '\n';
+}

docs/mkdocs/docs/examples/basic_json_view__operator_ltlt.output

@@ -0,0 +1,10 @@
+{"id":2,"item":"adapter"}
+{
+  "id": 2,
+  "item": "adapter"
+}
+
+{
+	"id": 2,
+	"item": "adapter"
+}

docs/mkdocs/docs/examples/basic_json_view__operator_ne.cpp

@@ -0,0 +1,28 @@
+#include <iostream>
+#include <nlohmann/json_view.hpp>
+
+using json_document = nlohmann::json_document;
+using ordered_json_document = nlohmann::ordered_json_document;
+using json = nlohmann::json;
+
+int main()
+{
+    // assert, as a test would, that a received document differs from an
+    // unwanted shape -- without ever materializing it into a json value just
+    // to compare
+    const json_document received = json_document::parse(
+                                       R"({"status": "ok", "code": 200})");
+    const json unwanted = {{"status", "error"}, {"code", 500}};
+    std::cout << std::boolalpha << (received.root() != unwanted) << '\n';
+
+    // json (std::map) compares object members regardless of order ...
+    const json_document a = json_document::parse(R"({"a": 1, "b": 2})");
+    const json_document b = json_document::parse(R"({"b": 2, "a": 1})");
+    std::cout << (a.root() != b.root()) << '\n';
+
+    // ... but ordered_json (ordered_map) compares them in the order they
+    // appear, so the very same reordering is detected as a difference
+    const ordered_json_document oa = ordered_json_document::parse(R"({"a": 1, "b": 2})");
+    const ordered_json_document ob = ordered_json_document::parse(R"({"b": 2, "a": 1})");
+    std::cout << (oa.root() != ob.root()) << '\n';
+}

docs/mkdocs/docs/examples/basic_json_view__operator_ne.output

@@ -0,0 +1,3 @@
+true
+false
+true

docs/mkdocs/docs/features/json_view.md

@@ -139,8 +139,12 @@ whenever any of the other conditions above was not met.
   element access and lookup functions never carry the JSON Pointer path `JSON_DIAGNOSTICS` would otherwise add: the
   view has no `basic_json` value to point at, so the exception is created without one, regardless of how
   `BasicJsonType` was built.
-- **`dump()` and comparison are not (yet) provided** by `basic_json_view`. For now,
+- **Ordering comparisons are not provided** by `basic_json_view` -- there is no `#!cpp operator<`.
-  [`materialize()`](../api/basic_json_view/materialize.md) is the way to get a value you can do those things with.
+  [`operator==`](../api/basic_json_view/operator_eq.md) and [`operator!=`](../api/basic_json_view/operator_ne.md) are
+  provided, though: two views, or a view and a `BasicJsonType` value, compare equal exactly when
+  [`materialize()`](../api/basic_json_view/materialize.md) or [`parse()`](../api/basic_json/parse.md) would produce
+  equal values for them, without ever building a tree to do it. For ordering, too,
+  [`materialize()`](../api/basic_json_view/materialize.md) is the way to get a value you can compare.
 
 ## Getting values out without copying
 
@@ -166,6 +170,23 @@ Two conversions never copy at all:
 
 Both results are only valid as long as the view -- and, for a string with no escapes, the borrowed source text -- is.
 
+## Writing a view back
+
+[`dump()`](../api/basic_json_view/dump.md) serializes a view directly from the flat index, without ever building a
+`basic_json` value. An object's members are written in document order, not sorted by key, and *every* occurrence of a
+repeated key is written, not only the last one -- the same two ways [iteration](#what-is-different) already differs
+from a [`materialize()`](../api/basic_json_view/materialize.md)d value, see above. `#!cpp materialize().dump()` gives
+a different result in both respects for a `json_view`.
+
+By default, numbers are written the way [`basic_json::dump()`](../api/basic_json/dump.md) would.
+[`number_format::source`](../api/basic_json_view/number_format.md) instead copies every number exactly as it was
+written in the source text -- a price like `#!cpp 19.90`, a long order or account ID with more digits than any number
+type holds, or a high-precision coordinate -- something `basic_json` cannot do at all, since parsing already reduces
+a number to its parsed `#!cpp double`/`#!cpp int64_t` value.
+
+[`operator<<`](../api/basic_json_view/operator_ltlt.md) writes a view to a stream the way `basic_json`'s does, using
+the stream's `width`/`fill` for indentation.
+
 ## Choosing between `json`, `ordered_json`, the SAX interface, and `json_view`
 
 | | [`json`](../api/json.md) / [`ordered_json`](../api/ordered_json.md) | [SAX interface](parsing/sax_interface.md) | [`json_document`](../api/json_document.md) / [`json_view`](../api/json_view.md) |

docs/mkdocs/docs/home/architecture.md

@@ -196,7 +196,7 @@ packet-beta
 |-------|---------|------------|-------------------------------------------------------------------------------------------------------------------------------|
 | 0     | `kind`  | `uint8_t`  | the type, numbered as [`value_t`](../api/basic_json/value_t.md): 0 null, 1 object, 2 array, 3 string, 4 boolean, 5 signed integer, 6 unsigned integer, 7 float |
 | 1     | `flags` | `uint8_t`  | bits 0-1: where a string's bytes are (0: the source text, 1: the buffer of decoded strings, for strings with escapes); bit 2: the value of a boolean |
-| 2-3   | `extra` | `uint16_t` | numbers: the number of integer digits (low byte) and fraction digits (high byte), 255 for more; otherwise 0                      |
+| 2-3   | `extra` | `uint16_t` | numbers: the number of integer digits (low byte) and fraction digits (high byte), 255 for more; objects: the number of their hash index (1-based), or 0; otherwise 0 |
 | 4-7   | `off`   | `uint32_t` | where the value starts: the first byte after a string's opening quote (or its position in the buffer of decoded strings), the first byte of a number or literal, the bracket of an array or object |
 | 8-11  | `len`   | `uint32_t` | strings: the length after decoding; floats and literals: the length of the token; arrays and objects: the number of elements |
 | 12-15 | `next`  | `uint32_t` | arrays and objects: the number of nodes of the subtree, including the node itself                                              |
@@ -211,6 +211,11 @@ packet-beta
   subtree is `next` nodes further for an array or object, and the next node otherwise (`document_data::after`). Views
   step from element to element this way and skip whole subtrees in constant time.
 - **Offsets** are 32 bits wide, so a document is limited to 4 GiB (`out_of_range.416`).
+- **Large objects** (128 members or more) get a hash index after parsing
+  ([`detail/view/object_index.hpp`](https://github.com/nlohmann/json/blob/develop/include/nlohmann/detail/view/object_index.hpp)):
+  an open-addressing table whose slots hold the distance from the object's node to a key's node, so that a lookup does
+  not compare every key. The object's `extra` holds the number of its table. Only 65,535 tables fit into `extra`;
+  objects beyond them are searched linearly.
 
 For example, `#!json {"a": [1, 2.5]}` becomes five nodes. Each node's elements follow it, and `next` leads from an
 array or object past its subtree:

docs/mkdocs/docs/home/license.md

@@ -23,3 +23,5 @@ The class contains a copy of [Hedley](https://nemequ.github.io/hedley/) from Eva
 The class contains an adapted version of the Eisel-Lemire algorithm, its table of powers of five, and its digit comparison for long numbers from [fast_float](https://github.com/fastfloat/fast_float) by Daniel Lemire and contributors, which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here), the Apache 2.0 License, and the Boost Software License. Copyright © 2021 The fast_float authors
 
 The view's parser (`<nlohmann/json_view.hpp>`) contains techniques and code adapted from [yyjson](https://github.com/ibireme/yyjson) by YaoYuan, which is licensed under the [MIT License](https://opensource.org/licenses/MIT) (see above): table-driven decoding of `\u` escapes and fixed-offset unrolled checks.
+
+The view's parser (`<nlohmann/json_view.hpp>`) validates non-ASCII strings with the vector UTF-8 check of [simdjson](https://github.com/simdjson/simdjson) by Daniel Lemire, Geoff Langdale, John Keiser, and contributors (its "lookup4" algorithm and tables, after J. Keiser and D. Lemire, "Validating UTF-8 In Less Than One Instruction Per Byte", 2021), which is available under the [MIT License](https://opensource.org/licenses/MIT) (used here) and the Apache 2.0 License. Copyright &copy; 2018-2025 The simdjson authors

docs/mkdocs/mkdocs.yml

@@ -253,6 +253,7 @@ nav:
           - 'cend': api/basic_json_view/cend.md
           - 'contains': api/basic_json_view/contains.md
           - 'count': api/basic_json_view/count.md
+          - 'dump': api/basic_json_view/dump.md
           - 'empty': api/basic_json_view/empty.md
           - 'end': api/basic_json_view/end.md
           - 'find': api/basic_json_view/find.md
@@ -275,9 +276,13 @@ nav:
           - 'is_structured': api/basic_json_view/is_structured.md
           - 'items': api/basic_json_view/items.md
           - 'materialize': api/basic_json_view/materialize.md
+          - 'number_format': api/basic_json_view/number_format.md
           - 'number_token': api/basic_json_view/number_token.md
           - 'operator bool': api/basic_json_view/operator_bool.md
+          - 'operator<<': api/basic_json_view/operator_ltlt.md
           - 'operator[]': api/basic_json_view/operator[].md
+          - 'operator==': api/basic_json_view/operator_eq.md
+          - 'operator!=': api/basic_json_view/operator_ne.md
           - 'size': api/basic_json_view/size.md
           - 'source_offset': api/basic_json_view/source_offset.md
           - 'type': api/basic_json_view/type.md
@@ -364,6 +369,8 @@ nav:
           - 'JSON_USE_IMPLICIT_CONVERSIONS': api/macros/json_use_implicit_conversions.md
           - 'JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON': api/macros/json_use_legacy_discarded_value_comparison.md
           - 'JSON_USE_SIMDUTF': api/macros/json_use_simdutf.md
+          - 'JSON_VIEW_NO_SIMD': api/macros/json_view_no_simd.md
+          - 'JSON_VIEW_USE_SSSE3': api/macros/json_view_use_ssse3.md
           - 'NLOHMANN_DEFINE_DERIVED_TYPE_INTRUSIVE, NLOHMANN_DEFINE_DERIVED_TYPE_INTRUSIVE_WITH_DEFAULT, NLOHMANN_DEFINE_DERIVED_TYPE_INTRUSIVE_ONLY_SERIALIZE, NLOHMANN_DEFINE_DERIVED_TYPE_NON_INTRUSIVE, NLOHMANN_DEFINE_DERIVED_TYPE_NON_INTRUSIVE_WITH_DEFAULT, NLOHMANN_DEFINE_DERIVED_TYPE_NON_INTRUSIVE_ONLY_SERIALIZE': api/macros/nlohmann_define_derived_type.md
           - 'NLOHMANN_DEFINE_TYPE_INTRUSIVE, NLOHMANN_DEFINE_TYPE_INTRUSIVE_WITH_DEFAULT, NLOHMANN_DEFINE_TYPE_INTRUSIVE_ONLY_SERIALIZE': api/macros/nlohmann_define_type_intrusive.md
           - 'NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE, NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE_WITH_DEFAULT, NLOHMANN_DEFINE_TYPE_NON_INTRUSIVE_ONLY_SERIALIZE': api/macros/nlohmann_define_type_non_intrusive.md

include/nlohmann/detail/view/builder.hpp

@@ -116,6 +116,13 @@ class builder
     frame shallow[64]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays): not initialized on purpose; filled as containers open
     std::vector<frame> deep{};
 
+    /// remember an object to index after parsing (out of line, so that the
+    /// parse loop only has a call for it)
+    NLOHMANN_VIEW_NOINLINE void note_large_object(std::uint32_t idx)
+    {
+        doc.large_objects.push_back(idx);
+    }
+
     NLOHMANN_VIEW_NOINLINE bool fail(error_code c, const unsigned char* at) noexcept
     {
         m_failure.code = c;
@@ -503,7 +510,7 @@ class builder
     switch (cur())                                                                              \
     {                                                                                           \
         case '"':                                                                               \
-            if (NLOHMANN_VIEW_UNLIKELY(!string())) { return false; }                      \
+            if (NLOHMANN_VIEW_UNLIKELY(!string<true>())) { return false; }                \
             goto NEXT;                                                                          \
         case '{':                                                                               \
             open(value_t::object);                                                              \
@@ -587,7 +594,7 @@ obj_key:
             {
                 return fail(error_code::expected_key);
             }
-            if (NLOHMANN_VIEW_UNLIKELY(!string()))
+            if (NLOHMANN_VIEW_UNLIKELY(!string<false>()))
             {
                 return false;
             }
@@ -628,19 +635,27 @@ obj_next:
                 if (enabled(TrailingCommas) && cur() == '}')
                 {
                     ++p;
-                    goto close_container;
+                    goto close_object;
                 }
                 goto obj_key;
             }
             if (cur() == '}')
             {
                 ++p;
-                goto close_container;
+                goto close_object;
             }
             return fail(error_code::expected_object_end);
 
 #undef NLOHMANN_VIEW_VALUE
 
+close_object:
+            // a large object gets a hash index (objects only, so that closing
+            // an array pays nothing for this)
+            if (NLOHMANN_VIEW_UNLIKELY(cur_count >= document_data::index_min_members))
+            {
+                cold.note_large_object(cur_idx);
+            }
+
 close_container:
             close();
             if (NLOHMANN_VIEW_UNLIKELY(depth == 0))
@@ -690,7 +705,7 @@ root_done:
             switch (cur())
             {
                 case '"':
-                    return string();
+                    return string<true>();
                 case 't':
                     return literal("true", 4, value_t::boolean, node_flags::is_true);
                 case 'f':
@@ -977,12 +992,13 @@ indent_done:
             return true;
         }
 
-        /// a string (value or key) at p
+        /// a string at p: a value (Value) or a key
+        template<bool Value>
         NLOHMANN_VIEW_ALWAYS_INLINE bool string()
         {
             ++p; // opening quote
             const unsigned char* const s = p;
-            p = scan_string_run(p, e);
+            p = scan_string_run<Value>(p, e);
             if (NLOHMANN_VIEW_LIKELY(p != e && *p == '"'))
             {
                 emit(value_t::string, 0, 0, static_cast<std::size_t>(s - b), static_cast<std::uint64_t>(p - s));

include/nlohmann/detail/view/compare.hpp

@@ -0,0 +1,317 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <algorithm> // sort, stable_sort
+#include <cstddef> // size_t
+#include <string> // string
+#include <utility> // move, pair
+#include <vector> // vector
+
+#include <nlohmann/json.hpp>
+#include <nlohmann/detail/view/macro_scope.hpp>
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+namespace view
+{
+
+// Equality of views, and of views with basic_json values, with the semantics
+// of basic_json's operator== applied to the values parse() would produce:
+// numbers compare by value across their types, an object is compared by its
+// members with duplicate keys resolved as parse() resolves them (the last
+// value, at the position of the first occurrence), and in document order if
+// the object type keeps an order (ordered_json), by key otherwise.
+
+/// one side of a comparison: a view
+template<typename BasicJsonType, typename View>
+class view_side
+{
+  public:
+    using string_view_t = typename View::string_view_t;
+
+    explicit view_side(const View& v) noexcept
+        : m_view(v)
+    {}
+
+    value_t type() const noexcept
+    {
+        return m_view.type();
+    }
+
+    std::size_t size() const noexcept
+    {
+        return m_view.size();
+    }
+
+    string_view_t string() const
+    {
+        return m_view.get_string();
+    }
+
+    /// a number, boolean, or null as a basic_json value (no allocation)
+    BasicJsonType scalar() const
+    {
+        switch (m_view.type())
+        {
+            case value_t::number_integer:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
+            case value_t::number_unsigned:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
+            case value_t::number_float:
+                return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
+            case value_t::boolean:
+                return BasicJsonType(m_view.template get<bool>());
+            case value_t::null:
+            case value_t::object:
+            case value_t::array:
+            case value_t::string:
+            case value_t::binary:
+            case value_t::discarded:
+            default:
+                return BasicJsonType(nullptr);
+        }
+    }
+
+    void elements(std::vector<view_side>& out) const
+    {
+        out.reserve(m_view.size());
+        for (const View e : m_view)
+        {
+            out.emplace_back(e);
+        }
+    }
+
+    /// the members as parse() keeps them: one per key, the last value at the
+    /// position of the first occurrence; in that order, or sorted by key
+    void members(std::vector<std::pair<string_view_t, view_side>>& out, bool ordered) const
+    {
+        struct member
+        {
+            string_view_t key;
+            View value;
+            std::size_t position;
+        };
+        std::vector<member> all;
+        all.reserve(m_view.size());
+        std::size_t position = 0;
+        for (auto it = m_view.begin(); it != m_view.end(); ++it)
+        {
+            all.push_back(member{it.key(), it.value(), position++});
+        }
+        std::stable_sort(all.begin(), all.end(), [](const member & a, const member & b)
+        {
+            return a.key < b.key;
+        });
+        std::vector<member> unique;
+        unique.reserve(all.size());
+        for (std::size_t i = 0; i < all.size();)
+        {
+            std::size_t last = i;
+            while (last + 1 < all.size() && all[last + 1].key == all[i].key)
+            {
+                ++last;
+            }
+            unique.push_back(member{all[i].key, all[last].value, all[i].position});
+            i = last + 1;
+        }
+        if (ordered)
+        {
+            std::sort(unique.begin(), unique.end(), [](const member & a, const member & b)
+            {
+                return a.position < b.position;
+            });
+        }
+        out.reserve(unique.size());
+        for (const member& m : unique)
+        {
+            out.emplace_back(m.key, view_side(m.value));
+        }
+    }
+
+  private:
+    View m_view;
+};
+
+/// the other side of a comparison: a basic_json value
+template<typename BasicJsonType, typename StringView>
+class json_side
+{
+  public:
+    using string_view_t = StringView;
+
+    explicit json_side(const BasicJsonType& j) noexcept
+        : m_json(&j)
+    {}
+
+    value_t type() const noexcept
+    {
+        return m_json->type();
+    }
+
+    std::size_t size() const noexcept
+    {
+        return m_json->size();
+    }
+
+    string_view_t string() const
+    {
+        const auto& s = m_json->template get_ref<const typename BasicJsonType::string_t&>();
+        return string_view_t(s.data(), s.size());
+    }
+
+    BasicJsonType scalar() const
+    {
+        return *m_json;
+    }
+
+    void elements(std::vector<json_side>& out) const
+    {
+        out.reserve(m_json->size());
+        for (const auto& e : *m_json)
+        {
+            out.emplace_back(e);
+        }
+    }
+
+    void members(std::vector<std::pair<string_view_t, json_side>>& out, bool ordered) const
+    {
+        out.reserve(m_json->size());
+        for (auto it = m_json->cbegin(); it != m_json->cend(); ++it)
+        {
+            out.emplace_back(string_view_t(it.key().data(), it.key().size()), json_side(it.value()));
+        }
+        if (!ordered)
+        {
+            std::sort(out.begin(), out.end(), [](const std::pair<string_view_t, json_side>& a, const std::pair<string_view_t, json_side>& b)
+            {
+                return a.first < b.first;
+            });
+        }
+    }
+
+  private:
+    const BasicJsonType* m_json;
+};
+
+/// whether two sides are equal; iterative, so that the nesting depth is
+/// limited by memory only
+template<typename BasicJsonType, typename A, typename B>
+bool equal(const A& a0, const B& b0)
+{
+    using string_view_t = typename A::string_view_t;
+    const bool ordered = is_ordered_map<typename BasicJsonType::object_t>::value;
+
+    struct frame
+    {
+        std::vector<A> elements_a{};
+        std::vector<B> elements_b{};
+        std::vector<std::pair<string_view_t, A>> members_a{};
+        std::vector<std::pair<string_view_t, B>> members_b{};
+        bool object = false;
+        std::size_t next = 0;
+    };
+    std::vector<frame> stack;
+    A a = a0;
+    B b = b0;
+    for (;;)
+    {
+        const value_t ta = a.type();
+        const value_t tb = b.type();
+        const bool numbers = (ta == value_t::number_integer || ta == value_t::number_unsigned || ta == value_t::number_float)
+                             && (tb == value_t::number_integer || tb == value_t::number_unsigned || tb == value_t::number_float);
+        if (ta == value_t::discarded || tb == value_t::discarded)
+        {
+            // basic_json decides (JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON)
+            if (ta != tb || !(BasicJsonType(value_t::discarded) == BasicJsonType(value_t::discarded)))
+            {
+                return false;
+            }
+        }
+        else
+        {
+            if (!numbers && ta != tb)
+            {
+                return false;
+            }
+            if (ta == value_t::string)
+            {
+                if (!(a.string() == b.string()))
+                {
+                    return false;
+                }
+            }
+            else if (ta == value_t::array || ta == value_t::object)
+            {
+                if (a.size() != b.size() && ta == value_t::array)
+                {
+                    return false;
+                }
+                frame f;
+                f.object = ta == value_t::object;
+                if (f.object)
+                {
+                    a.members(f.members_a, ordered);
+                    b.members(f.members_b, ordered);
+                    if (f.members_a.size() != f.members_b.size())
+                    {
+                        return false;
+                    }
+                }
+                else
+                {
+                    a.elements(f.elements_a);
+                    b.elements(f.elements_b);
+                }
+                stack.push_back(std::move(f));
+            }
+            else if (!(a.scalar() == b.scalar())) // numbers (also of different types), null, boolean
+            {
+                return false;
+            }
+        }
+
+        // the next pair of values
+        for (;;)
+        {
+            if (stack.empty())
+            {
+                return true;
+            }
+            frame& f = stack.back();
+            const std::size_t count = f.object ? f.members_a.size() : f.elements_a.size();
+            if (f.next == count)
+            {
+                stack.pop_back();
+                continue;
+            }
+            if (f.object)
+            {
+                if (!(f.members_a[f.next].first == f.members_b[f.next].first))
+                {
+                    return false;
+                }
+                a = f.members_a[f.next].second;
+                b = f.members_b[f.next].second;
+            }
+            else
+            {
+                a = f.elements_a[f.next];
+                b = f.elements_b[f.next];
+            }
+            ++f.next;
+            break;
+        }
+    }
+}
+
+}  // namespace view
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/document_data.hpp

@@ -10,9 +10,11 @@
 
 #include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint32_t
 #include <cstring> // memcpy
 #include <new> // operator new, placement new
 #include <string> // string
+#include <vector> // vector
 
 #include <nlohmann/json.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
@@ -37,6 +39,17 @@ struct document_data
     std::size_t inline_cap = 0;
     std::string arena{}; ///< decoded strings that contained escapes // NOLINT(readability-redundant-member-init)
     std::string owned{}; ///< owned copy of the input, if any // NOLINT(readability-redundant-member-init)
+
+    // hash indexes of large objects (see object_index.hpp)
+    static constexpr std::uint32_t index_min_members = 128;
+    struct object_index
+    {
+        std::size_t start;  ///< first slot in index_slots
+        std::uint32_t mask; ///< slot count - 1 (a power of two minus one)
+    };
+    std::vector<object_index> indexes{}; // NOLINT(readability-redundant-member-init)
+    std::vector<std::uint32_t> index_slots{}; // NOLINT(readability-redundant-member-init)
+    std::vector<std::uint32_t> large_objects{}; ///< positions of the objects to index (noted while parsing) // NOLINT(readability-redundant-member-init)
     std::array<const char*, 4> base = {{nullptr, nullptr, nullptr, nullptr}}; ///< string bases: source, arena (indexed by flags & node_flags::storage)
     bool discarded = true;
 
@@ -64,7 +77,7 @@ struct document_data
         }
     };
 
-    document_data() noexcept = default;
+    document_data() = default;
     document_data(const document_data&) = delete;
     document_data(document_data&&) = delete;
     document_data& operator=(const document_data&) = delete;

include/nlohmann/detail/view/lookup.hpp

@@ -16,6 +16,7 @@
 #include <nlohmann/detail/view/document_data.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/object_index.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -85,6 +86,10 @@ class short_key
 /// nullptr; most keys are rejected by their length, from the index alone
 inline const node* find_member(const document_data& d, const node* object, const char* key, std::size_t n) noexcept
 {
+    if (NLOHMANN_VIEW_UNLIKELY(object->extra != 0))
+    {
+        return find_indexed(d, object, key, n); // a large object
+    }
     const node* const end = document_data::child_end(object);
     const auto* const k = reinterpret_cast<const unsigned char*>(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
     if (NLOHMANN_VIEW_LIKELY(n <= 16))

include/nlohmann/detail/view/macro_unscope.hpp

@@ -19,3 +19,8 @@
 #undef NLOHMANN_VIEW_THROW
 #undef NLOHMANN_VIEW_LITTLE_ENDIAN
 #undef NLOHMANN_VIEW_REPEAT16
+#undef NLOHMANN_VIEW_NEON
+#undef NLOHMANN_VIEW_SSE2
+#undef NLOHMANN_VIEW_SSSE3
+#undef NLOHMANN_VIEW_VECTOR
+#undef NLOHMANN_VIEW_VECTOR_UTF8

include/nlohmann/detail/view/materialize.hpp

@@ -81,7 +81,7 @@ BasicJsonType materialize(const document_data& d, const node* n)
                 ++n;
                 break;
             case value_t::number_float:
-                sax.number_float(float_value<typename BasicJsonType::number_float_t>(d.str(*n), *n), no_token);
+                sax.number_float(float_value<typename BasicJsonType::number_float_t>(d, *n), no_token);
                 ++n;
                 break;
             case value_t::boolean:

include/nlohmann/detail/view/number.hpp

@@ -9,11 +9,15 @@
 #pragma once
 
 #include <cstddef> // size_t
+#include <cstdint> // int64_t, uint64_t
 #include <string> // string
+#include <type_traits> // integral_constant
 
 #include <nlohmann/json.hpp>
+#include <nlohmann/detail/view/document_data.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/scan.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -62,6 +66,96 @@ NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
     return convert_float<FloatType>(first, last, dot, mantissa_end);
 }
 
+/*!
+@brief the digits of a float token with at most 19 digits, from its layout
+
+The digit layout recorded while parsing says where the integer digits, the
+fraction digits, and the exponent are, so the digits are read eight at a
+time without scanning.
+
+@param[in] p  first character of the token
+@param[in] e  end of the token
+@param[in] limit  end of the readable memory (the source text)
+*/
+NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char* p, const unsigned char* e, unsigned int_digits, unsigned frac_digits, const unsigned char* limit) noexcept
+{
+    const bool negative = *p == '-';
+    p += negative ? 1 : 0;
+    std::uint64_t w = parse_upto19(p, int_digits, limit);
+    p += int_digits;
+    std::int64_t q = 0;
+    if (frac_digits != 0)
+    {
+        w = (w * int_pow10(frac_digits)) + parse_upto19(p + 1, frac_digits, limit);
+        p += 1 + frac_digits;
+        q = -static_cast<std::int64_t>(frac_digits);
+    }
+    if (p != e)
+    {
+        // [eE][+-]digits; huge exponents saturate (the parser rejected overflow)
+        ++p;
+        const bool exp_negative = *p == '-';
+        p += (*p == '-' || *p == '+') ? 1 : 0;
+        std::int64_t exp_value = 0;
+        for (; p != e; ++p)
+        {
+            if (exp_value < 0x10000000)
+            {
+                exp_value = (exp_value * 10) + (*p - '0');
+            }
+        }
+        q += exp_negative ? -exp_value : exp_value;
+    }
+
+    float_significand d;
+    d.w = w;
+    d.exponent = q;
+    d.negative = negative;
+    return d;
+}
+
+/*!
+@brief the value of a float token with at most 19 digits, from its layout
+
+The result is correctly rounded by the lexer's conversion
+(detail::decimal_to_float(): Clinger's fast path where both operands are
+exact, else the Eisel-Lemire algorithm, which needs no fallback for up to 19
+digits), so it is the value parse() produces.
+*/
+template<typename FloatType>
+NLOHMANN_VIEW_ALWAYS_INLINE FloatType layout_float(const unsigned char* p, const unsigned char* e, unsigned int_digits, unsigned frac_digits, const unsigned char* limit) noexcept
+{
+    return decimal_to_float<FloatType>(layout_decimal(p, e, int_digits, frac_digits, limit));
+}
+
+/// the value of the float token of a node, as parse() converts it; floats and
+/// doubles with at most 19 digits are converted from the digit layout
+template<typename FloatType>
+FloatType float_value(const document_data& d, const node& n)
+{
+    return float_value<FloatType>(d, n, std::integral_constant<bool, has_native_float_format<FloatType>::value> {});
+}
+
+template<typename FloatType>
+FloatType float_value(const document_data& d, const node& n, std::true_type /*binary32 or binary64*/)
+{
+    const unsigned int_digits = n.extra & 0xFFu;
+    const unsigned frac_digits = n.extra >> 8u;
+    if (NLOHMANN_VIEW_LIKELY(int_digits + frac_digits <= 19)) // (255 marks "many")
+    {
+        // (a float token not written by an edit is in the text)
+        const auto* const first = reinterpret_cast<const unsigned char*>(d.src + n.off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        return layout_float<FloatType>(first, first + n.len, int_digits, frac_digits, reinterpret_cast<const unsigned char*>(d.src + d.size)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    }
+    return float_value<FloatType>(d.str(n), n);
+}
+
+template<typename FloatType>
+FloatType float_value(const document_data& d, const node& n, std::false_type /*other*/)
+{
+    return float_value<FloatType>(d.str(n), n);
+}
+
 }  // namespace view
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/object_index.hpp

@@ -0,0 +1,131 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <cstddef> // size_t
+#include <cstdint> // uint32_t, uint64_t
+#include <cstring> // memcmp
+
+#include <nlohmann/json.hpp>
+#include <nlohmann/detail/view/document_data.hpp>
+#include <nlohmann/detail/view/macro_scope.hpp>
+#include <nlohmann/detail/view/node.hpp>
+
+// Hash indexes of large objects, so that a lookup does not compare thousands
+// of keys (as Boost.JSON switches from a linear search to a hash table for
+// large objects). An object with document_data::index_min_members members or
+// more gets an open-addressing table after parsing; its node stores the
+// number of the table (1-based) in `extra`. A slot holds the offset of a key
+// node from its object node (0: empty). Of duplicate keys, the first is kept,
+// as for the linear search.
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+namespace view
+{
+
+/// hash of a key: its bytes, eight at a time, in a fixed byte order
+inline std::uint64_t key_hash(const char* s, std::size_t n) noexcept
+{
+    std::uint64_t h = 0x9E3779B97F4A7C15u * (n + 1);
+    const auto* p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+    while (n >= 8)
+    {
+        h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
+        h ^= h >> 29u;
+        p += 8;
+        n -= 8;
+    }
+    std::uint64_t w = 0;
+    for (std::size_t i = 0; i < n; ++i)
+    {
+        w |= static_cast<std::uint64_t>(p[i]) << (8u * i);
+    }
+    h = (h ^ w) * 0x94D049BB133111EBu;
+    return h ^ (h >> 31u);
+}
+
+/// build the table of a large object
+inline void build_object_index(document_data& d, node* obj)
+{
+    if (d.indexes.size() >= 0xFFFFu)
+    {
+        return; // LCOV_EXCL_LINE (the number must fit `extra`; more large objects are searched linearly)
+    }
+    std::size_t cap = 16;
+    while (cap < 2 * static_cast<std::size_t>(obj->len))
+    {
+        cap *= 2;
+    }
+    const std::size_t start = d.index_slots.size();
+    d.index_slots.resize(start + cap, 0);
+    std::uint32_t* const slots = d.index_slots.data() + start;
+    const std::size_t mask = cap - 1;
+    for (const node* k = document_data::first_child(obj), *end = document_data::child_end(obj); k != end; k = document_data::after(k + 1))
+    {
+        const char* const key = d.str(*k);
+        const std::uint64_t hash = key_hash(key, k->len); // (a cast of the call would be useless where std::uint64_t is std::size_t)
+        std::size_t i = static_cast<std::size_t>(hash) & mask;
+        bool duplicate = false;
+        while (slots[i] != 0)
+        {
+            const node* const other = obj + slots[i];
+            if (other->len == k->len && (k->len == 0 || std::memcmp(d.str(*other), key, k->len) == 0))
+            {
+                duplicate = true; // keep the first
+                break;
+            }
+            i = (i + 1) & mask;
+        }
+        if (!duplicate)
+        {
+            slots[i] = static_cast<std::uint32_t>(k - obj);
+        }
+    }
+    d.indexes.push_back(document_data::object_index{start, static_cast<std::uint32_t>(mask)});
+    obj->extra = static_cast<std::uint16_t>(d.indexes.size());
+}
+
+/// build the tables of the large objects the parser noted
+inline void build_object_indexes(document_data& d)
+{
+    for (const std::uint32_t i : d.large_objects)
+    {
+        build_object_index(d, d.tape + i);
+    }
+}
+
+/// the key node of the first member with this key of an indexed object, or
+/// nullptr
+inline const node* find_indexed(const document_data& d, const node* obj, const char* key, std::size_t n) noexcept
+{
+    const document_data::object_index& ix = d.indexes[obj->extra - 1u];
+    const std::uint32_t* const slots = d.index_slots.data() + ix.start;
+    const std::uint64_t hash = key_hash(key, n); // (a cast of the call would be useless where std::uint64_t is std::size_t)
+    std::size_t i = static_cast<std::size_t>(hash) & ix.mask;
+    for (;;)
+    {
+        const std::uint32_t s = slots[i];
+        if (s == 0)
+        {
+            return nullptr;
+        }
+        const node* const k = obj + s;
+        if (k->len == n && (n == 0 || std::memcmp(d.str(*k), key, n) == 0))
+        {
+            return k;
+        }
+        i = (i + 1) & ix.mask;
+    }
+}
+
+}  // namespace view
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/scan.hpp

@@ -16,6 +16,7 @@
 
 #include <nlohmann/json.hpp>
 #include <nlohmann/detail/view/macro_scope.hpp>
+#include <nlohmann/detail/view/simd.hpp>
 
 // Scanning primitives of the view's parser. The unrolled checks at fixed
 // offsets follow yyjson (https://github.com/ibireme/yyjson, MIT license): the
@@ -62,9 +63,12 @@ NLOHMANN_VIEW_ALWAYS_INLINE std::uint16_t load16(const unsigned char* p) noexcep
 
 /// Advance over plain string bytes and well-formed UTF-8. Stops at a quote,
 /// a backslash, a control character, ill-formed UTF-8, or the end. The first
-/// 16 bytes are checked one by one, so that the position advances by
+/// bytes are checked one by one, so that the position advances by constants
-/// constants in predicted branches (most strings are short); longer runs
+/// in predicted branches: 16 for keys, whose lengths repeat from record to
-/// continue eight bytes at a time.
+/// record, and 8 for string values (Value) where a vector loop follows, as
+/// their lengths vary more. Longer runs continue 16 bytes at a time with NEON
+/// or SSE2, else eight bytes at a time.
+template<bool Value = false>
 NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* scan_string_run(const unsigned char* p, const unsigned char* e) noexcept
 {
     const std::uint8_t* plain = string_plain();
@@ -73,9 +77,23 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* scan_string_run(const unsigned
         if (e - p >= 16)
         {
 #define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(plain[p[i]] != 0)) {} else { p += (i); goto stop; }
-            NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
+            NLOHMANN_VIEW_STEP(0) NLOHMANN_VIEW_STEP(1) NLOHMANN_VIEW_STEP(2) NLOHMANN_VIEW_STEP(3)
+            NLOHMANN_VIEW_STEP(4) NLOHMANN_VIEW_STEP(5) NLOHMANN_VIEW_STEP(6) NLOHMANN_VIEW_STEP(7)
+            if (!Value || !NLOHMANN_VIEW_VECTOR)
+            {
+                NLOHMANN_VIEW_STEP(8) NLOHMANN_VIEW_STEP(9) NLOHMANN_VIEW_STEP(10) NLOHMANN_VIEW_STEP(11)
+                NLOHMANN_VIEW_STEP(12) NLOHMANN_VIEW_STEP(13) NLOHMANN_VIEW_STEP(14) NLOHMANN_VIEW_STEP(15)
+                p += 8;
+            }
 #undef NLOHMANN_VIEW_STEP
-            p += 16;
+            p += 8;
+#if NLOHMANN_VIEW_VECTOR
+            p = vector_plain_run(p, e);
+            if (p != e && plain[*p] == 0)
+            {
+                goto stop;
+            }
+#else
             while (e - p >= 8)
             {
                 const std::uint64_t special = swar_string_special(read_eight_bytes(p));
@@ -86,6 +104,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* scan_string_run(const unsigned
                 }
                 p += 8;
             }
+#endif
             continue;
         }
         while (p != e && plain[*p] != 0)
@@ -101,6 +120,10 @@ stop:
         {
             return p; // quote, backslash, or control character
         }
+#if NLOHMANN_VIEW_VECTOR_UTF8
+        // non-ASCII: the vector check, out of line
+        return scan_string_vector(p, e, plain);
+#else
         // non-ASCII: a run of well-formed sequences (the library's check, so
         // that exactly what json::parse accepts is accepted)
         do
@@ -113,6 +136,7 @@ stop:
             p += n;
         }
         while (p != e && *p >= 0x80);
+#endif
     }
 }
 

include/nlohmann/detail/view/serializer.hpp

@@ -0,0 +1,419 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <algorithm> // max
+#include <array> // array
+#include <cmath> // isfinite
+#include <cstddef> // size_t
+#include <cstdint> // uint8_t, uint32_t
+#include <cstring> // memcpy, memset
+#include <limits> // numeric_limits
+#include <type_traits> // integral_constant
+#include <vector> // vector
+
+#include <nlohmann/json.hpp>
+#include <nlohmann/detail/view/document_data.hpp>
+#include <nlohmann/detail/view/macro_scope.hpp>
+#include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/number.hpp>
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+namespace view
+{
+
+/// append-only output buffer: writes through a raw pointer into a string that
+/// is resized ahead, and trimmed by finish()
+template<typename StringType>
+class output_buffer
+{
+  public:
+    output_buffer(StringType& out, std::size_t estimate)
+        : m_out(sized(out, estimate))
+        , m_pos(&m_out[0])
+        , m_end(m_pos + m_out.size())
+    {}
+
+    void finish()
+    {
+        m_out.resize(static_cast<std::size_t>(m_pos - m_out.data()));
+    }
+
+    NLOHMANN_VIEW_ALWAYS_INLINE void reserve(std::size_t n)
+    {
+        if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(m_end - m_pos) < n))
+        {
+            grow(n);
+        }
+    }
+
+    NLOHMANN_VIEW_ALWAYS_INLINE void put(char c)
+    {
+        reserve(1);
+        *m_pos++ = c;
+    }
+
+    NLOHMANN_VIEW_ALWAYS_INLINE void put(const char* s, std::size_t n)
+    {
+        reserve(n);
+        std::memcpy(m_pos, s, n);
+        m_pos += n;
+    }
+
+    void put_repeated(char c, std::size_t n)
+    {
+        reserve(n);
+        std::memset(m_pos, c, n);
+        m_pos += n;
+    }
+
+  private:
+    static StringType& sized(StringType& out, std::size_t estimate)
+    {
+        out.resize((std::max)(estimate, static_cast<std::size_t>(64)));
+        return out;
+    }
+
+    NLOHMANN_VIEW_NOINLINE void grow(std::size_t n)
+    {
+        const auto used = static_cast<std::size_t>(m_pos - m_out.data());
+        m_out.resize((std::max)(m_out.size() * 2, used + n + 256));
+        m_pos = &m_out[0] + used;
+        m_end = &m_out[0] + m_out.size();
+    }
+
+    StringType& m_out;
+    char* m_pos;
+    char* m_end;
+};
+
+/// how the view's dump() writes a value
+struct dump_style
+{
+    bool pretty = false;           ///< indent >= 0
+    std::size_t indent = 0;        ///< characters per level
+    char indent_char = ' ';
+    bool ensure_ascii = false;
+    bool source_numbers = false;   ///< copy number tokens from the source
+};
+
+/*!
+@brief write a view's subtree as basic_json::dump() writes the value
+
+The output of a subtree equals ordered_json::parse(text).dump() of it for
+the same arguments (members in document order): strings are escaped by the
+same rules, with the library's scanning kernels; floats are written with
+the library's conversion; integers are copied from the source, where they
+are canonical (except "-0", which parse() reads as 0). The walk is
+iterative, so the nesting depth is limited by memory only.
+*/
+template<typename BasicJsonType>
+class view_serializer
+{
+    using string_t = typename BasicJsonType::string_t;
+    using number_float_t = typename BasicJsonType::number_float_t;
+
+  public:
+    view_serializer(const document_data& d, string_t& out, std::size_t estimate, const dump_style& style)
+        : m_doc(d), m_out(out, estimate), m_style(style)
+    {}
+
+    void dump(const node* root)
+    {
+        struct frame
+        {
+            const node* pos; ///< next element, or key of the next member
+            const node* end;
+            bool object;
+            bool first;  ///< nothing written yet
+        };
+        std::vector<frame> stack;
+        const node* n = root;
+        for (;;)
+        {
+            // write the value at n
+            if (is_container(*n))
+            {
+                const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
+                if (n->len == 0)
+                {
+                    m_out.put(object ? "{}" : "[]", 2);
+                }
+                else
+                {
+                    m_out.put(object ? '{' : '[');
+                    stack.push_back(frame{document_data::first_child(n), document_data::child_end(n), object, true});
+                }
+            }
+            else
+            {
+                write_scalar(*n);
+            }
+
+            // go to the next value: close finished containers, then separate
+            for (;;)
+            {
+                if (stack.empty())
+                {
+                    m_out.finish();
+                    return;
+                }
+                frame& f = stack.back();
+                if (f.pos == f.end)
+                {
+                    const bool object = f.object;
+                    stack.pop_back();
+                    newline(stack.size());
+                    m_out.put(object ? '}' : ']');
+                    continue;
+                }
+                if (!f.first)
+                {
+                    m_out.put(',');
+                }
+                f.first = false;
+                newline(stack.size());
+                if (f.object)
+                {
+                    write_string(*f.pos);
+                    if (m_style.pretty)
+                    {
+                        m_out.put(": ", 2);
+                    }
+                    else
+                    {
+                        m_out.put(':');
+                    }
+                    n = f.pos + 1;
+                }
+                else
+                {
+                    n = f.pos;
+                }
+                f.pos = document_data::after(n);
+                break;
+            }
+        }
+    }
+
+  private:
+    void newline(std::size_t level)
+    {
+        if (m_style.pretty)
+        {
+            m_out.put('\n');
+            m_out.put_repeated(m_style.indent_char, level * m_style.indent);
+        }
+    }
+
+    void write_scalar(const node& n)
+    {
+        switch (static_cast<value_t>(n.kind))
+        {
+            case value_t::null:
+                m_out.put("null", 4);
+                break;
+            case value_t::boolean:
+                if ((n.flags & node_flags::is_true) != 0)
+                {
+                    m_out.put("true", 4);
+                }
+                else
+                {
+                    m_out.put("false", 5);
+                }
+                break;
+            case value_t::string:
+                write_string(n);
+                break;
+            case value_t::number_integer:
+            case value_t::number_unsigned:
+            {
+                const char* const token = m_doc.str(n);
+                const std::uint32_t len = number_length(n);
+                if (!m_style.source_numbers && len == 2 && token[0] == '-' && token[1] == '0')
+                {
+                    m_out.put('0'); // parse() reads -0 as the integer 0
+                }
+                else
+                {
+                    m_out.put(token, len);
+                }
+                break;
+            }
+            case value_t::number_float:
+                if (m_style.source_numbers)
+                {
+                    m_out.put(m_doc.str(n), n.len);
+                }
+                else
+                {
+                    write_float(float_value<number_float_t>(m_doc, n));
+                }
+                break;
+            case value_t::object:    // LCOV_EXCL_LINE (containers are written by dump())
+            case value_t::array:     // LCOV_EXCL_LINE
+            case value_t::binary:    // LCOV_EXCL_LINE (not in a document)
+            case value_t::discarded: // LCOV_EXCL_LINE
+            default:                 // LCOV_EXCL_LINE
+                break;               // LCOV_EXCL_LINE
+        }
+    }
+
+    /// as serializer::dump_float()
+    void write_float(number_float_t x)
+    {
+        if (!std::isfinite(x))
+        {
+            m_out.put("null", 4);
+            return;
+        }
+        write_float(x, std::integral_constant < bool,
+                    (std::numeric_limits<number_float_t>::is_iec559 && std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
+                    || (std::numeric_limits<number_float_t>::is_iec559 && std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024) > {});
+    }
+
+    void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
+    {
+        std::array<char, 64> buf{};
+        const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
+        m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
+    }
+
+    void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
+    {
+        // other types (e.g. long double) are rare: the library writes them
+        const string_t s = BasicJsonType(x).dump();
+        m_out.put(s.data(), s.size());
+    }
+
+    void write_string(const node& n)
+    {
+        const char* const s = m_doc.str(n);
+        m_out.put('"');
+        if ((n.flags & node_flags::escaped) == 0 && !m_style.ensure_ascii)
+        {
+            // a string without escape sequences has nothing to escape
+            m_out.put(s, n.len);
+        }
+        else if (m_style.ensure_ascii)
+        {
+            write_escaped<true>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        }
+        else
+        {
+            write_escaped<false>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+        }
+        m_out.put('"');
+    }
+
+    /// as serializer::dump_escaped() for valid UTF-8 (the view has no other)
+    template<bool EnsureAscii>
+    void write_escaped(const unsigned char* s, std::size_t n)
+    {
+        std::size_t i = 0;
+        while (i < n)
+        {
+            std::size_t run = 0;
+            if (!EnsureAscii)
+            {
+                run = string_bulk_run(s + i, n - i);
+            }
+            else if (is_ascii_copyable(s[i]))
+            {
+                run = find_ascii_copyable_run(s + i, n - i);
+            }
+            if (run != 0)
+            {
+                m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
+                i += run;
+                continue;
+            }
+            std::uint32_t codepoint = s[i];
+            std::size_t len = 1;
+            if (codepoint >= 0xC0)
+            {
+                len = 2;
+                if (codepoint >= 0xE0)
+                {
+                    len = codepoint >= 0xF0 ? 4 : 3;
+                }
+                codepoint &= 0xFFu >> (len + 1);
+                for (std::size_t k = 1; k < len; ++k)
+                {
+                    codepoint = (codepoint << 6u) | (s[i + k] & 0x3Fu);
+                }
+            }
+            write_codepoint<EnsureAscii>(codepoint, s + i, len);
+            i += len;
+        }
+    }
+
+    template<bool EnsureAscii>
+    void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
+    {
+        switch (codepoint)
+        {
+            case 0x08:
+                m_out.put("\\b", 2);
+                return;
+            case 0x09:
+                m_out.put("\\t", 2);
+                return;
+            case 0x0A:
+                m_out.put("\\n", 2);
+                return;
+            case 0x0C:
+                m_out.put("\\f", 2);
+                return;
+            case 0x0D:
+                m_out.put("\\r", 2);
+                return;
+            case 0x22:
+                m_out.put("\\\"", 2);
+                return;
+            case 0x5C:
+                m_out.put("\\\\", 2);
+                return;
+            default:
+                break;
+        }
+        if (codepoint <= 0x1F || (EnsureAscii && codepoint >= 0x7F))
+        {
+            if (codepoint <= 0xFFFF)
+            {
+                write_u_escape(codepoint);
+            }
+            else
+            {
+                write_u_escape(0xD7C0u + (codepoint >> 10u));
+                write_u_escape(0xDC00u + (codepoint & 0x3FFu));
+            }
+            return;
+        }
+        m_out.put(reinterpret_cast<const char*>(bytes), len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) LCOV_EXCL_LINE (printable characters are copied in runs)
+    }
+
+    void write_u_escape(std::uint32_t u)
+    {
+        static constexpr const char* hex = "0123456789abcdef";
+        const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
+        m_out.put(e.data(), e.size());
+    }
+
+    const document_data& m_doc;
+    output_buffer<string_t> m_out;
+    const dump_style m_style;
+};
+
+}  // namespace view
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/simd.hpp

@@ -0,0 +1,281 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-FileCopyrightText: 2018-2025 The simdjson authors <https://github.com/simdjson/simdjson>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <array> // array
+#include <cstddef> // size_t
+#include <cstdint> // uint8_t, uint64_t
+
+#include <nlohmann/json.hpp>
+#include <nlohmann/detail/view/macro_scope.hpp>
+
+// Vector code for long runs of string bytes. NEON (AArch64) and SSE2 (x86-64)
+// belong to the baseline instruction sets and are used by default. The vector
+// UTF-8 check needs NEON, or SSSE3 if JSON_VIEW_USE_SSSE3 is defined: SSSE3 is
+// not part of x86-64, so it must not depend on the flags of a translation unit
+// (two translation units with different flags would have different
+// definitions of the same inline functions). JSON_VIEW_NO_SIMD selects the
+// portable code.
+#if !defined(JSON_VIEW_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && NLOHMANN_VIEW_LITTLE_ENDIAN
+    #include <arm_neon.h>
+    #define NLOHMANN_VIEW_NEON 1
+#else
+    #define NLOHMANN_VIEW_NEON 0
+#endif
+#if !defined(JSON_VIEW_NO_SIMD) && !NLOHMANN_VIEW_NEON && (defined(__SSE2__) || defined(_M_X64) || (defined(_M_IX86_FP) && _M_IX86_FP >= 2))
+    #include <emmintrin.h>
+    #define NLOHMANN_VIEW_SSE2 1
+#else
+    #define NLOHMANN_VIEW_SSE2 0
+#endif
+#if NLOHMANN_VIEW_SSE2 && defined(JSON_VIEW_USE_SSSE3)
+    #include <tmmintrin.h>
+    #define NLOHMANN_VIEW_SSSE3 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#else
+    #define NLOHMANN_VIEW_SSSE3 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
+#endif
+#define NLOHMANN_VIEW_VECTOR (NLOHMANN_VIEW_NEON || NLOHMANN_VIEW_SSE2)
+#define NLOHMANN_VIEW_VECTOR_UTF8 (NLOHMANN_VIEW_NEON || NLOHMANN_VIEW_SSSE3)
+
+NLOHMANN_JSON_NAMESPACE_BEGIN
+namespace detail
+{
+namespace view
+{
+
+#if NLOHMANN_VIEW_VECTOR
+/*!
+@brief the first byte of a string run that is a quote, a backslash, a control
+character, or not ASCII, 16 bytes per step
+
+Stops at such a byte, or where fewer than 16 bytes are left (the caller tells
+the two apart). A signed compare with 0x20 finds control characters and
+non-ASCII bytes at once.
+*/
+NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
+{
+    while (e - p >= 16)
+    {
+#if NLOHMANN_VIEW_NEON
+        const uint8x16_t in = vld1q_u8(p);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
+                                            vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
+        // one nibble per byte (the usual NEON replacement of x86's movemask, see
+        // D. Kutenin, "Porting x86 vector bitmask optimizations to Arm NEON", 2022)
+        const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
+        if (bits != 0)
+        {
+            return p + (count_trailing_zeros(bits) >> 2u);
+        }
+#else
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p)));
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
+        const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
+        if (bits != 0)
+        {
+            return p + count_trailing_zeros(bits);
+        }
+#endif
+        p += 16;
+    }
+    return p;
+}
+#endif
+
+#if NLOHMANN_VIEW_VECTOR_UTF8
+/// Tables of the UTF-8 check of J. Keiser and D. Lemire, "Validating UTF-8 In
+/// Less Than One Instruction Per Byte" (2021), as in simdjson ("lookup4"): each
+/// maps a nibble (high and low nibble of the previous byte, high nibble of the
+/// current byte) to the errors it allows; a byte pair is ill-formed if all
+/// three have an error bit in common.
+template<typename Dummy = void>
+struct utf8_lookup4
+{
+    static constexpr std::uint8_t too_short = 1u << 0u, too_long = 1u << 1u, overlong_3 = 1u << 2u, too_large = 1u << 3u;
+    static constexpr std::uint8_t surrogate = 1u << 4u, overlong_2 = 1u << 5u, too_large_1000 = 1u << 6u, overlong_4 = 1u << 6u;
+    static constexpr std::uint8_t two_conts = 1u << 7u, carry = too_short | too_long | two_conts;
+    static const std::array<std::uint8_t, 16> byte_1_high;
+    static const std::array<std::uint8_t, 16> byte_1_low;
+    static const std::array<std::uint8_t, 16> byte_2_high;
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_high =
+{
+    {
+        too_long, too_long, too_long, too_long, too_long, too_long, too_long, too_long,
+        two_conts, two_conts, two_conts, two_conts,
+        too_short | overlong_2, too_short, too_short | overlong_3 | surrogate, too_short | too_large | too_large_1000 | overlong_4
+    }
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_low =
+{
+    {
+        carry | overlong_3 | overlong_2 | overlong_4, carry | overlong_2, carry, carry,
+        carry | too_large, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
+        carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
+        carry | too_large | too_large_1000, carry | too_large | too_large_1000 | surrogate, carry | too_large | too_large_1000, carry | too_large | too_large_1000
+    }
+};
+
+template<typename Dummy>
+const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_2_high =
+{
+    {
+        too_short, too_short, too_short, too_short, too_short, too_short, too_short, too_short,
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large_1000 | overlong_4),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
+        static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
+        too_short, too_short, too_short, too_short
+    }
+};
+
+/// the end of scan_string_vector from block, where the vector loop stopped
+/// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a
+/// time, from the start of a sequence that crosses into the block
+inline const unsigned char* scan_string_finish(const unsigned char* p, const unsigned char* block, const unsigned char* e, const std::uint8_t* plain) noexcept
+{
+    for (int i = 1; i <= 3 && block - i >= p; ++i)
+    {
+        const unsigned char c = block[-i];
+        if (c < 0x80)
+        {
+            break;
+        }
+        if (c >= 0xC0)
+        {
+            const int len = 2 + static_cast<int>(c >= 0xE0) + static_cast<int>(c >= 0xF0);
+            if (len > i)
+            {
+                block -= i;
+            }
+            break;
+        }
+    }
+    for (p = block; p != e;)
+    {
+        if (*p < 0x80)
+        {
+            if (plain[*p] == 0)
+            {
+                return p;
+            }
+            ++p;
+            continue;
+        }
+        const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
+        if (n == 0)
+        {
+            return p;
+        }
+        p += n;
+    }
+    return p;
+}
+
+/*!
+@brief the rest of a string from p (a character boundary), 16 bytes per step
+
+The first quote, backslash, or control character is found with vector
+compares, and the UTF-8 check covers the bytes up to it. Returns where the
+string scan stops, like scan_string_run: before ill-formed UTF-8 and for the
+last bytes of the input, the bytes are checked one sequence at a time. Out of
+line, so that no constants of the check occupy registers in the parse loop.
+*/
+NLOHMANN_VIEW_NOINLINE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
+{
+    using lookup = utf8_lookup4<>;
+    const unsigned char* block = p;
+#if NLOHMANN_VIEW_NEON
+    const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
+    const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
+    const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
+    uint8x16_t prev = vdupq_n_u8(0);
+    while (e - block >= 16)
+    {
+        const uint8x16_t in = vld1q_u8(block);
+        const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))), vcltq_u8(in, vdupq_n_u8(0x20)));
+        const uint8x16_t prev1 = vextq_u8(prev, in, 15);
+        const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
+        const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
+        const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
+        const std::uint64_t special_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
+        const std::uint64_t err_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(err, err)), 4)), 0);
+        if (special_bits != 0)
+        {
+            // errors up to the special byte count (an incomplete sequence
+            // before a quote shows at the quote); the bytes after it do not
+            const unsigned k = static_cast<unsigned>(count_trailing_zeros(special_bits)) >> 2u;
+            const std::uint64_t upto = k == 15 ? ~std::uint64_t{0} :
+                                       (std::uint64_t{1} << (4u * (k + 1u))) - 1u;
+            if ((err_bits & upto) == 0)
+            {
+                return block + k;
+            }
+            break;
+        }
+        if (err_bits != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#else
+    // the same with SSSE3 (pshufb for the table lookups; nibbles from 16-bit
+    // shifts, as there are no byte shifts)
+    const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data())));
+    const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data())));
+    const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data())));
+    const __m128i nibble = _mm_set1_epi8(0x0F);
+    const __m128i zero = _mm_setzero_si128();
+    __m128i prev = zero;
+    while (e - block >= 16)
+    {
+        const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block)));
+        const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
+                                             _mm_cmpeq_epi8(_mm_subs_epu8(in, _mm_set1_epi8(0x1F)), zero)); // in < 0x20
+        const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
+        const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
+                                         _mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
+                                         _mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
+        const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
+                                            _mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
+        const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
+        const auto special_bits = static_cast<unsigned>(_mm_movemask_epi8(special));
+        const auto err_bits = ~static_cast<unsigned>(_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero))) & 0xFFFFu;
+        if (special_bits != 0)
+        {
+            const unsigned k = static_cast<unsigned>(count_trailing_zeros(static_cast<std::uint64_t>(special_bits)));
+            if ((err_bits & ((2u << k) - 1u)) == 0)
+            {
+                return block + k;
+            }
+            break;
+        }
+        if (err_bits != 0)
+        {
+            break;
+        }
+        prev = in;
+        block += 16;
+    }
+#endif
+    return scan_string_finish(p, block, e, plain);
+}
+#endif
+
+}  // namespace view
+}  // namespace detail
+NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/detail/view/value.hpp

@@ -49,7 +49,7 @@ NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const nod
         case value_t::number_integer:
             return static_cast<T>(static_cast<typename BasicJsonType::number_integer_t>(static_cast<std::int64_t>(integer_bits(n))));
         case value_t::number_float:
-            return static_cast<T>(float_value<typename BasicJsonType::number_float_t>(d.str(n), n));
+            return static_cast<T>(float_value<typename BasicJsonType::number_float_t>(d, n));
         case value_t::boolean:
             return static_cast<T>((n.flags & node_flags::is_true) != 0);
         case value_t::null:

include/nlohmann/json_view.hpp

@@ -25,10 +25,14 @@
 #define INCLUDE_NLOHMANN_JSON_VIEW_HPP_
 
 #include <cstddef> // size_t
+#include <cstdint> // uint32_t
 #include <cstring> // memcpy, strlen
 #include <iterator> // distance, input_iterator_tag, iterator_traits
 #include <map> // map
 #include <memory> // unique_ptr
+#ifndef JSON_NO_IO
+    #include <ostream> // ostream
+#endif
 #include <string> // string
 #include <tuple> // tuple_element, tuple_size
 #include <type_traits> // decay, enable_if, integral_constant, is_arithmetic, is_base_of, is_integral, is_same, remove_cv, remove_extent
@@ -44,6 +48,7 @@
 #endif
 
 #include <nlohmann/detail/view/builder.hpp>
+#include <nlohmann/detail/view/compare.hpp>
 #include <nlohmann/detail/view/document_data.hpp>
 #include <nlohmann/detail/view/errors.hpp>
 #include <nlohmann/detail/view/input.hpp>
@@ -52,7 +57,9 @@
 #include <nlohmann/detail/view/macro_scope.hpp>
 #include <nlohmann/detail/view/materialize.hpp>
 #include <nlohmann/detail/view/node.hpp>
+#include <nlohmann/detail/view/object_index.hpp>
 #include <nlohmann/detail/view/pointer.hpp>
+#include <nlohmann/detail/view/serializer.hpp>
 #include <nlohmann/detail/view/string_ref.hpp>
 #include <nlohmann/detail/view/value.hpp>
 
@@ -547,6 +554,96 @@ class basic_json_view
         return {m_doc->str(*m_node), detail::view::number_length(*m_node)};
     }
 
+    ///////////////////
+    // serialization //
+    ///////////////////
+
+    /// how dump() writes numbers
+    enum class number_format
+    {
+        /// as basic_json::dump(): integers canonically, floats with the
+        /// library's shortest round-trip digits ("1.5", "100.0", "1e+100")
+        shortest,
+        /// the number text of the source as it is ("1.50", "1E2", "-0", all
+        /// digits of a long integer)
+        source,
+    };
+
+    /// the text of this value; with number_format::shortest, the output of
+    /// ordered_json::parse(text).dump() with the same arguments (members in
+    /// document order, all of them should a key occur more than once)
+    string_t dump(const int indent = -1, const char indent_char = ' ', const bool ensure_ascii = false,
+                  const number_format numbers = number_format::shortest) const
+    {
+        string_t out;
+        if (m_node == nullptr)
+        {
+            out = "<discarded>"; // as basic_json::dump() of a discarded value
+            return out;
+        }
+        detail::view::dump_style style;
+        style.pretty = indent >= 0;
+        style.indent = indent >= 0 ? static_cast<std::size_t>(indent) : 0;
+        style.indent_char = indent_char;
+        style.ensure_ascii = ensure_ascii;
+        style.source_numbers = numbers == number_format::source;
+        // the compact text is about as long as the source text of the value
+        const std::size_t estimate = source_extent() + (style.pretty ? source_extent() / 2 : 0) + 64;
+        detail::view::view_serializer<BasicJsonType>(*m_doc, out, estimate, style).dump(m_node);
+        return out;
+    }
+
+#ifndef JSON_NO_IO
+    /// as operator<< of basic_json: a stream width > 0 is the indentation,
+    /// the fill character the indentation character
+    friend std::ostream& operator<<(std::ostream& o, const basic_json_view& v)
+    {
+        const bool pretty = o.width() > 0;
+        const auto indentation = pretty ? o.width() : 0;
+        o.width(0);
+        const string_t s = v.dump(pretty ? static_cast<int>(indentation) : -1, o.fill());
+        return o.write(s.data(), static_cast<std::streamsize>(s.size()));
+    }
+#endif
+
+    ////////////////
+    // comparison //
+    ////////////////
+
+    /// whether the values parse() would produce for two views are equal, as
+    /// by BasicJsonType's operator== (numbers by value, objects by their
+    /// members with duplicate keys resolved as parse() resolves them)
+    friend bool operator==(const basic_json_view& a, const basic_json_view& b)
+    {
+        return detail::view::equal<BasicJsonType>(side(a), side(b));
+    }
+
+    friend bool operator!=(const basic_json_view& a, const basic_json_view& b)
+    {
+        return !(a == b);
+    }
+
+    /// whether the value parse() would produce for a view equals a value
+    friend bool operator==(const basic_json_view& a, const BasicJsonType& j)
+    {
+        return detail::view::equal<BasicJsonType>(side(a), json_side_t(j));
+    }
+
+    friend bool operator==(const BasicJsonType& j, const basic_json_view& a)
+    {
+        return a == j;
+    }
+
+    friend bool operator!=(const basic_json_view& a, const BasicJsonType& j)
+    {
+        return !(a == j);
+    }
+
+    friend bool operator!=(const BasicJsonType& j, const basic_json_view& a)
+    {
+        return !(a == j);
+    }
+
     /////////////////
     // materialize //
     /////////////////
@@ -579,6 +676,30 @@ class basic_json_view
         : m_doc(d), m_node(n)
     {}
 
+    using json_side_t = detail::view::json_side<BasicJsonType, string_view_t>;
+
+    static detail::view::view_side<BasicJsonType, basic_json_view> side(const basic_json_view& v) noexcept
+    {
+        return detail::view::view_side<BasicJsonType, basic_json_view>(v);
+    }
+
+    /// the number of source bytes of this value (estimated for values with
+    /// decoded strings)
+    std::size_t source_extent() const noexcept
+    {
+        const node* const next = document_data::after(m_node);
+        const bool in_source = (m_node->flags & detail::view::node_flags::storage) == 0;
+        if (!in_source)
+        {
+            return m_node->len;
+        }
+        if (next != m_doc->tape + m_doc->tape_size && (next->flags & detail::view::node_flags::storage) == 0 && next->off >= m_node->off)
+        {
+            return next->off - m_node->off;
+        }
+        return m_doc->size - m_node->off;
+    }
+
     /// the value of the first member with this key, or a discarded view
     /// (object required)
     NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view lookup(string_view_t key) const noexcept
@@ -806,7 +927,9 @@ class basic_json_document
         }
         return sizeof(document_data) + (m_data->inline_cap * sizeof(detail::view::node))
                + (m_data->tape != m_data->inline_tape ? m_data->tape_cap * sizeof(detail::view::node) : 0)
-               + m_data->arena.capacity() + m_data->owned.capacity();
+               + m_data->arena.capacity() + m_data->owned.capacity()
+               + (m_data->indexes.capacity() * sizeof(document_data::object_index)) + (m_data->index_slots.capacity() * sizeof(std::uint32_t))
+               + (m_data->large_objects.capacity() * sizeof(std::uint32_t));
     }
 
     /// release unused capacity of the index and the decoded strings; like
@@ -876,6 +999,9 @@ class basic_json_document
         d.size = size;
         d.tape_size = 0;
         d.arena.clear();
+        d.indexes.clear();
+        d.index_slots.clear();
+        d.large_objects.clear();
         d.discarded = true;
         detail::view::parse_failure failure;
         bool ok = false;
@@ -891,6 +1017,7 @@ class basic_json_document
         {
             d.base[0] = d.src;
             d.base[1] = d.arena.data();
+            detail::view::build_object_indexes(d);
             d.discarded = false;
             return;
         }

tests/CMakeLists.txt

@@ -324,6 +324,26 @@ json_test_add_test_for(src/unit-diagnostic-positions.cpp
     MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
 )
 
+# the json_view parser again with the portable string scanning instead of
+# NEON/SSE2, and on x86-64 with the SSSE3 UTF-8 check (JSON_VIEW_USE_SSSE3)
+json_test_set_test_options(test-json_view_builder_portable
+    COMPILE_DEFINITIONS JSON_VIEW_NO_SIMD
+)
+json_test_add_test_for(src/unit-json_view_builder.cpp
+    NAME test-json_view_builder_portable
+    MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
+)
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64|amd64)$" AND NOT MSVC)
+    json_test_set_test_options(test-json_view_builder_ssse3
+        COMPILE_DEFINITIONS JSON_VIEW_USE_SSSE3
+        COMPILE_OPTIONS -mssse3
+    )
+    json_test_add_test_for(src/unit-json_view_builder.cpp
+        NAME test-json_view_builder_ssse3
+        MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
+    )
+endif()
+
 # *DO NOT* use json_test_set_test_options() below this line
 
 #############################################################################

tests/benchmarks/README.md

@@ -21,6 +21,7 @@ Micro-benchmarks for parsing, serialization and the binary formats, written with
 | `ViewParseIndented` | as `ParseIndented`, with a reused `json_document` |
 | `ViewAccept` | validate with `json_document::accept`; compare with `Accept` |
 | `ViewMaterialize` | convert a parsed `json_document` into a `json` value |
+| `ViewDump` | serialize a parsed `json_document`; compare with `Dump` |
 
 The input files are those of [nativejson-benchmark](https://github.com/miloyip/nativejson-benchmark) (`canada`,
 `citm_catalog`, `twitter`), a large `jeopardy` file, and number-heavy files (`floats`, `signed_ints`, ...).

tests/benchmarks/json_view/.gitignore

@@ -0,0 +1 @@
+build/

tests/benchmarks/json_view/README.md

@@ -0,0 +1,73 @@
+# json_view compared with other libraries
+
+The in-tree benchmarks in [`tests/benchmarks`](../README.md) measure `json_document` against `json::parse` only. The
+programs here compare it with [yyjson](https://github.com/ibireme/yyjson),
+[simdjson](https://github.com/simdjson/simdjson), and [Boost.JSON](https://github.com/boostorg/json): the question
+users ask when they pick a library. They are not built by CMake or run by CI.
+
+## Reproducing the numbers
+
+`compare.py` builds both programs against `include/` of this checkout, runs them, and writes the results together with
+everything needed to reproduce them to `results/<date>-<host>.md` (and `.csv`): the date, the commit, the CPU, the
+OS, the compiler, the flags, and the versions of all libraries.
+
+```sh
+python3 tests/benchmarks/json_view/compare.py --data <json_test_data directory> [--native] [--rounds 30]
+```
+
+- `--data` is the downloaded [test data](https://github.com/nlohmann/json_test_data), e.g. the `test_files` directory
+  of a CMake build directory. It needs `nativejson-benchmark/{twitter,citm_catalog,canada}.json` and
+  `jeopardy/jeopardy.json`.
+- The other libraries come from the system: pkg-config, or Homebrew (`brew install yyjson simdjson boost`). With
+  `--download`, pinned releases are downloaded instead and checked against their SHA-256. Without Boost headers (or
+  with `--no-boost`), the Boost.JSON columns are skipped, and the results say so.
+- `--corpus file...` adds files to the corpus benchmark, e.g. those of
+  [simdjson-data](https://github.com/simdjson/simdjson-data) or the
+  [yyjson benchmark](https://github.com/ibireme/yyjson_benchmark).
+- Only the Python 3 standard library is used; a C++17 compiler is needed (`CXX` and `CC` are honored).
+
+For numbers worth publishing, use a quiet machine (see [Getting stable numbers](../README.md#getting-stable-numbers)),
+the default 30 rounds or more, and `--native` only if the other libraries were built for the same CPU.
+
+### On GitHub-hosted runners
+
+The workflow [json_view benchmarks](../../../.github/workflows/json_view_benchmarks.yml) runs `compare.py --download`
+on demand: by hand (Actions → "json_view benchmarks" → "Run workflow"), on an x86-64 or AArch64 Ubuntu runner with GCC
+or Clang, or when a pull request gets the label `benchmark`, on both architectures with GCC. The results appear as the
+job summary and as an artifact. Shared runners are noisy, so these numbers show
+where `json_view` stands on another architecture; they are not meant for publication.
+
+## What is measured
+
+`bench_view.cpp` runs four workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
+JSON-RPC request (`rpc`):
+
+| workload | what it does |
+|---|---|
+| parse | build and free a document |
+| traverse | parse, then visit every value, convert every number, touch every string and key |
+| select | parse, then read a few fields per record (e.g. id, user name, and retweet count of each tweet) |
+| dump | serialize a parsed document (compact) |
+
+`bench_corpus.cpp` runs parse, traverse, and dump on any list of files, so that no library is tuned to a handful of
+documents.
+
+Before anything is timed, all engines must accept each document and agree on the traversal: the number of values, the
+bytes of all strings and keys, and the sum of all numbers. All engines run interleaved in every round, and the best
+round is reported, as time and as a factor of the `json_view` time (below 1 means faster than `json_view`).
+
+The engines do not all offer the same features, which the numbers should be read with:
+
+| engine | document | random access | editable | notes |
+|---|---|---|---|---|
+| `json_view` | immutable index into the text | yes | no | a fresh document per parse; "reused" parses into the same document |
+| yyjson | immutable (`yyjson_read`) | yes | via a mutable copy | |
+| simdjson DOM | immutable, parser reused | yes | no | |
+| simdjson On-Demand | none: forward-only, lazy | no | no | only traverse and select |
+| Boost.JSON | owning, mutable DOM | yes | yes | monotonic resource |
+| `json::parse` | owning, mutable DOM | yes | yes | |
+
+## Published results
+
+Results are only published with the file `compare.py` wrote, which names the machine and the versions; see
+`results/`. Numbers from one machine and compiler do not carry over to another: rerun the script.

tests/benchmarks/json_view/bench_corpus.cpp

@@ -0,0 +1,326 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+// Corpus benchmark: the read-only workloads of bench_view.cpp on any list of
+// JSON files (for example the benchmark sets of simdjson and yyjson).
+//
+//   ./bench_corpus [--rounds N] file...
+//
+// For every file, all engines must accept it and agree on a traversal (value
+// count, string bytes, sum of numbers) before anything is timed. Workloads:
+// parse (build and free a document), traverse (visit every value, convert
+// every number), dump (compact), and for json_view also dump with the source
+// number text. Results go to bench_corpus.csv.
+#include <nlohmann/json_view.hpp>
+
+#if JSON_VIEW_BENCH_BOOST
+    #include <boost/json.hpp>
+    #include <boost/json/src.hpp>
+#endif
+#include <simdjson.h>
+#include <yyjson.h>
+
+#include <algorithm>
+#include <chrono>
+#include <cmath>
+#include <cstdio>
+#include <cstring>
+#include <fstream>
+#include <functional>
+#include <sstream>
+#include <string>
+#include <vector>
+
+using nlohmann::json;
+using nlohmann::json_document;
+using nlohmann::json_view;
+
+static volatile double g_sink;
+
+struct stats
+{
+    double num = 0;
+    std::size_t str = 0, nodes = 0;
+};
+
+static void walk(json_view v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case json::value_t::object:
+            for (auto it = v.begin(); it != v.end(); ++it)
+            {
+                st.str += it.key().size();
+                walk(*it, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const json_view e : v)
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += v.get_string().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(v.get<std::int64_t>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(v.get<std::uint64_t>());
+            break;
+        case json::value_t::number_float:
+            st.num += v.get<double>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(yyjson_val* v, stats& st)
+{
+    ++st.nodes;
+    switch (yyjson_get_type(v))
+    {
+        case YYJSON_TYPE_OBJ:
+        {
+            std::size_t idx, max;
+            yyjson_val* k, * val;
+            yyjson_obj_foreach(v, idx, max, k, val)
+            {
+                st.str += yyjson_get_len(k);
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_ARR:
+        {
+            std::size_t idx, max;
+            yyjson_val* val;
+            yyjson_arr_foreach(v, idx, max, val)
+            {
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_STR:
+            st.str += yyjson_get_len(v);
+            break;
+        case YYJSON_TYPE_NUM:
+            st.num += yyjson_is_sint(v) ? static_cast<double>(yyjson_get_sint(v)) : yyjson_is_uint(v) ? static_cast<double>(yyjson_get_uint(v)) : yyjson_get_real(v);
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(simdjson::dom::element e, stats& st)
+{
+    ++st.nodes;
+    switch (e.type())
+    {
+        case simdjson::dom::element_type::OBJECT:
+            for (auto f : simdjson::dom::object(e))
+            {
+                st.str += f.key.size();
+                walk(f.value, st);
+            }
+            break;
+        case simdjson::dom::element_type::ARRAY:
+            for (auto c : simdjson::dom::array(e))
+            {
+                walk(c, st);
+            }
+            break;
+        case simdjson::dom::element_type::STRING:
+            st.str += std::string_view(e).size();
+            break;
+        case simdjson::dom::element_type::INT64:
+            st.num += static_cast<double>(int64_t(e));
+            break;
+        case simdjson::dom::element_type::UINT64:
+            st.num += static_cast<double>(uint64_t(e));
+            break;
+        case simdjson::dom::element_type::DOUBLE:
+            st.num += double(e);
+            break;
+        default:
+            break;
+    }
+}
+
+#if JSON_VIEW_BENCH_BOOST
+static void walk(const boost::json::value& v, stats& st)
+{
+    ++st.nodes;
+    switch (v.kind())
+    {
+        case boost::json::kind::object:
+            for (const auto& kv : v.get_object())
+            {
+                st.str += kv.key().size();
+                walk(kv.value(), st);
+            }
+            break;
+        case boost::json::kind::array:
+            for (const auto& c : v.get_array())
+            {
+                walk(c, st);
+            }
+            break;
+        case boost::json::kind::string:
+            st.str += v.get_string().size();
+            break;
+        case boost::json::kind::int64:
+            st.num += static_cast<double>(v.get_int64());
+            break;
+        case boost::json::kind::uint64:
+            st.num += static_cast<double>(v.get_uint64());
+            break;
+        case boost::json::kind::double_:
+            st.num += v.get_double();
+            break;
+        default:
+            break;
+    }
+}
+#endif
+
+static std::string slurp(const std::string& p)
+{
+    std::ifstream f(p, std::ios::binary);
+    std::stringstream ss;
+    ss << f.rdbuf();
+    return ss.str();
+}
+
+static bool same(const stats& a, const stats& b)
+{
+    return a.nodes == b.nodes && a.str == b.str && (a.num == b.num || std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num));
+}
+
+int main(int argc, char** argv)
+{
+    int rounds = 0; // 0: by size
+    std::vector<std::string> files;
+    for (int i = 1; i < argc; ++i)
+    {
+        if (std::strcmp(argv[i], "--rounds") == 0 && i + 1 < argc)
+        {
+            rounds = std::atoi(argv[++i]);
+        }
+        else
+        {
+            files.push_back(argv[i]);
+        }
+    }
+    std::FILE* csv = std::fopen("bench_corpus.csv", "w");
+    std::fprintf(csv, "file,bytes,workload,engine,ns\n");
+    simdjson::dom::parser sj;
+    for (const auto& path : files)
+    {
+        const std::string s = slurp(path);
+        const std::string name = path.substr(path.rfind('/') + 1);
+        const simdjson::padded_string ps(s);
+
+        // all engines must agree before timing
+        stats a, b, c, d;
+        const json_document doc = json_document::parse(s);
+        walk(doc.root(), a);
+        yyjson_doc* y = yyjson_read(s.data(), s.size(), 0);
+        auto sjr = sj.parse(ps);
+#if JSON_VIEW_BENCH_BOOST
+        boost::json::parse_options opt;
+        opt.numbers = boost::json::number_precision::precise;
+        boost::json::monotonic_resource mr0;
+        const boost::json::value bv = boost::json::parse(s, &mr0, opt);
+#endif
+        if (y == nullptr || sjr.error())
+        {
+            std::printf("%-34s skipped (an engine rejects it)\n", name.c_str());
+            yyjson_doc_free(y);
+            continue;
+        }
+        walk(yyjson_doc_get_root(y), b);
+        walk(sjr.value_unsafe(), c);
+#if JSON_VIEW_BENCH_BOOST
+        walk(bv, d);
+#else
+        d = a;
+#endif
+        yyjson_doc_free(y);
+        const bool ok = same(a, b) && same(a, c) && same(a, d);
+
+        const int r = rounds > 0 ? rounds : static_cast<int>(std::max<std::size_t>(3, std::min<std::size_t>(60, 400000000 / (s.size() + 1))));
+        struct engine
+        {
+            std::string name;
+            std::function<void()> fn;
+        };
+        json_document vd = json_document::parse(s);
+        yyjson_doc* yd = yyjson_read(s.data(), s.size(), 0);
+        simdjson::dom::parser sjd;
+        const simdjson::dom::element se = sjd.parse(ps).value_unsafe();
+        const std::vector<std::pair<std::string, std::vector<engine>>> workloads =
+        {
+            {
+                "parse", {
+                    {"json_view", [&] { auto x = json_document::parse(s); g_sink = static_cast<double>(x.node_count()); }},
+                    {"yyjson", [&] { yyjson_doc* x = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(x)); yyjson_doc_free(x); }},
+                    {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+#if JSON_VIEW_BENCH_BOOST
+                    {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); g_sink = v.is_object(); }},
+#endif
+                }
+            },
+            {
+                "traverse", {
+                    {"json_view", [&] { auto x = json_document::parse(s); stats st; walk(x.root(), st); g_sink = st.num; }},
+                    {"yyjson", [&] { yyjson_doc* x = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(x), st); g_sink = st.num; yyjson_doc_free(x); }},
+                    {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
+#if JSON_VIEW_BENCH_BOOST
+                    {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); stats st; walk(v, st); g_sink = st.num; }},
+#endif
+                }
+            },
+            {
+                "dump", {
+                    {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                    {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
+                    {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
+                    {"json_view (source numbers)", [&] { std::string o = vd.root().dump(-1, ' ', false, json_view::number_format::source); g_sink = static_cast<double>(o.size()); }},
+                }
+            },
+        };
+        std::printf("%-34s %9zu B%s\n", name.c_str(), s.size(), ok ? "" : "  [ENGINES DISAGREE]");
+        for (const auto& wl : workloads)
+        {
+            std::vector<double> best(wl.second.size(), 1e300);
+            for (int i = 0; i < r; ++i)
+            {
+                for (std::size_t k = 0; k < wl.second.size(); ++k)
+                {
+                    const auto t0 = std::chrono::steady_clock::now();
+                    wl.second[k].fn();
+                    best[k] = std::min(best[k], std::chrono::duration<double, std::nano>(std::chrono::steady_clock::now() - t0).count());
+                }
+            }
+            std::printf("  %-9s", wl.first.c_str());
+            for (std::size_t k = 0; k < wl.second.size(); ++k)
+            {
+                std::printf("  %s %.2f GB/s (%.2fx)", wl.second[k].name.c_str(), static_cast<double>(s.size()) / best[k], best[k] / best[0]);
+                std::fprintf(csv, "%s,%zu,%s,%s,%.1f\n", name.c_str(), s.size(), wl.first.c_str(), wl.second[k].name.c_str(), best[k]);
+            }
+            std::printf("\n");
+            std::fflush(stdout);
+        }
+        yyjson_doc_free(yd);
+    }
+    std::fclose(csv);
+}

tests/benchmarks/json_view/bench_view.cpp

@@ -0,0 +1,735 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+// Same-feature-set benchmark: read-only JSON documents with random access.
+//
+//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused)
+//   yyjson         yyjson_read(): immutable document, random access
+//   simdjson DOM   dom::parser (reused, as recommended): immutable, random access
+// references (different feature sets):
+//   simdjson OD    On-Demand: forward-only, lazy
+//   Boost.JSON     owning, mutable DOM (monotonic resource)
+//   json::parse    owning, mutable DOM (nlohmann today)
+//
+// Workloads: parse (build + free), traverse (visit everything, convert every
+// number, touch every string and key), select (a few fields per document),
+// dump (compact serialization of the parsed document).
+// All engines run interleaved in every round; the best round is reported.
+#include <nlohmann/json_view.hpp>
+
+#if JSON_VIEW_BENCH_BOOST
+    #include <boost/json.hpp>
+    #include <boost/json/src.hpp>
+#endif
+#include <simdjson.h>
+#include <yyjson.h>
+
+#include <algorithm>
+#include <chrono>
+#include <cmath>
+#include <cstdio>
+#include <fstream>
+#include <functional>
+#include <map>
+#include <sstream>
+
+using nlohmann::json;
+using nlohmann::json_document;
+using nlohmann::json_view;
+
+static volatile double g_sink;
+
+struct stats
+{
+    double num = 0;
+    std::size_t str = 0, nodes = 0;
+};
+
+// ---------------- traversal ----------------
+
+static void walk(json_view v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case json::value_t::object:
+            for (auto it = v.begin(); it != v.end(); ++it)
+            {
+                st.str += it.key().size();
+                walk(*it, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const json_view e : v)
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += v.get_string().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(v.get<std::int64_t>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(v.get<std::uint64_t>());
+            break;
+        case json::value_t::number_float:
+            st.num += v.get<double>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(const json& j, stats& st)
+{
+    ++st.nodes;
+    switch (j.type())
+    {
+        case json::value_t::object:
+            for (const auto& kv : j.get_ref<const json::object_t&>())
+            {
+                st.str += kv.first.size();
+                walk(kv.second, st);
+            }
+            break;
+        case json::value_t::array:
+            for (const auto& e : j.get_ref<const json::array_t&>())
+            {
+                walk(e, st);
+            }
+            break;
+        case json::value_t::string:
+            st.str += j.get_ref<const std::string&>().size();
+            break;
+        case json::value_t::number_integer:
+            st.num += static_cast<double>(*j.get_ptr<const json::number_integer_t*>());
+            break;
+        case json::value_t::number_unsigned:
+            st.num += static_cast<double>(*j.get_ptr<const json::number_unsigned_t*>());
+            break;
+        case json::value_t::number_float:
+            st.num += *j.get_ptr<const json::number_float_t*>();
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(yyjson_val* v, stats& st)
+{
+    ++st.nodes;
+    switch (yyjson_get_type(v))
+    {
+        case YYJSON_TYPE_OBJ:
+        {
+            std::size_t idx, max;
+            yyjson_val* k, * val;
+            yyjson_obj_foreach(v, idx, max, k, val)
+            {
+                st.str += yyjson_get_len(k);
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_ARR:
+        {
+            std::size_t idx, max;
+            yyjson_val* val;
+            yyjson_arr_foreach(v, idx, max, val)
+            {
+                walk(val, st);
+            }
+            break;
+        }
+        case YYJSON_TYPE_STR:
+            st.str += yyjson_get_len(v);
+            break;
+        case YYJSON_TYPE_NUM:
+            if (yyjson_is_sint(v))
+            {
+                st.num += static_cast<double>(yyjson_get_sint(v));
+            }
+            else if (yyjson_is_uint(v))
+            {
+                st.num += static_cast<double>(yyjson_get_uint(v));
+            }
+            else
+            {
+                st.num += yyjson_get_real(v);
+            }
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk(simdjson::dom::element e, stats& st)
+{
+    ++st.nodes;
+    switch (e.type())
+    {
+        case simdjson::dom::element_type::OBJECT:
+            for (auto f : simdjson::dom::object(e))
+            {
+                st.str += f.key.size();
+                walk(f.value, st);
+            }
+            break;
+        case simdjson::dom::element_type::ARRAY:
+            for (auto c : simdjson::dom::array(e))
+            {
+                walk(c, st);
+            }
+            break;
+        case simdjson::dom::element_type::STRING:
+            st.str += std::string_view(e).size();
+            break;
+        case simdjson::dom::element_type::INT64:
+            st.num += static_cast<double>(int64_t(e));
+            break;
+        case simdjson::dom::element_type::UINT64:
+            st.num += static_cast<double>(uint64_t(e));
+            break;
+        case simdjson::dom::element_type::DOUBLE:
+            st.num += double(e);
+            break;
+        default:
+            break;
+    }
+}
+
+static void walk_od(simdjson::ondemand::value v, stats& st)
+{
+    ++st.nodes;
+    switch (v.type())
+    {
+        case simdjson::ondemand::json_type::object:
+            for (auto f : v.get_object())
+            {
+                st.str += std::string_view(f.unescaped_key()).size();
+                walk_od(f.value(), st);
+            }
+            break;
+        case simdjson::ondemand::json_type::array:
+            for (auto c : v.get_array())
+            {
+                walk_od(c.value(), st);
+            }
+            break;
+        case simdjson::ondemand::json_type::string:
+            st.str += std::string_view(v.get_string()).size();
+            break;
+        case simdjson::ondemand::json_type::number:
+        {
+            simdjson::ondemand::number n = v.get_number();
+            switch (n.get_number_type())
+            {
+                case simdjson::ondemand::number_type::signed_integer:
+                    st.num += static_cast<double>(n.get_int64());
+                    break;
+                case simdjson::ondemand::number_type::unsigned_integer:
+                    st.num += static_cast<double>(n.get_uint64());
+                    break;
+                default:
+                    st.num += n.get_double();
+                    break;
+            }
+            break;
+        }
+        case simdjson::ondemand::json_type::boolean:
+            (void)bool(v.get_bool());
+            break;
+        default:
+            (void)v.is_null();
+            break;
+    }
+}
+
+#if JSON_VIEW_BENCH_BOOST
+static void walk(const boost::json::value& v, stats& st)
+{
+    ++st.nodes;
+    switch (v.kind())
+    {
+        case boost::json::kind::object:
+            for (const auto& kv : v.get_object())
+            {
+                st.str += kv.key().size();
+                walk(kv.value(), st);
+            }
+            break;
+        case boost::json::kind::array:
+            for (const auto& c : v.get_array())
+            {
+                walk(c, st);
+            }
+            break;
+        case boost::json::kind::string:
+            st.str += v.get_string().size();
+            break;
+        case boost::json::kind::int64:
+            st.num += static_cast<double>(v.get_int64());
+            break;
+        case boost::json::kind::uint64:
+            st.num += static_cast<double>(v.get_uint64());
+            break;
+        case boost::json::kind::double_:
+            st.num += v.get_double();
+            break;
+        default:
+            break;
+    }
+}
+#endif
+
+// ---------------- selective access ----------------
+// twitter: per status id, user.screen_name, retweet_count
+// citm: per performance id, eventId, #seatCategories; #events
+// canada: type, features[0].geometry.type, #coordinates
+// jeopardy: per question: round == "Final Jeopardy!", len(category)
+// status (one tweet): id, user.screen_name, retweet_count
+// rpc: method, params.minuend, id
+
+static double pick(const std::string& name, json_view r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](json_view s)
+        {
+            acc += static_cast<double>(s["id"].get<std::uint64_t>());
+            acc += static_cast<double>(s["user"]["screen_name"].get_string().size());
+            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
+        };
+        if (name == "twitter")
+        {
+            for (const json_view s : r["statuses"])
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (const json_view p : r["performances"])
+        {
+            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
+        }
+        acc += static_cast<double>(r["events"].size());
+    }
+    else if (name == "canada")
+    {
+        const json_view g = r["features"][0]["geometry"];
+        acc += static_cast<double>(r["type"].get_string().size() + g["type"].get_string().size() + g["coordinates"].size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (const json_view q : r)
+        {
+            acc += q["round"].get_string() == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(q["category"].get_string().size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(r["method"].get_string().size());
+        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, const json& r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](const json & s)
+        {
+            acc += static_cast<double>(s["id"].get<std::uint64_t>());
+            acc += static_cast<double>(s["user"]["screen_name"].get_ref<const std::string&>().size());
+            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
+        };
+        if (name == "twitter")
+        {
+            for (const auto& s : r["statuses"])
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (const auto& p : r["performances"])
+        {
+            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
+        }
+        acc += static_cast<double>(r["events"].size());
+    }
+    else if (name == "canada")
+    {
+        const json& g = r["features"][0]["geometry"];
+        acc += static_cast<double>(r["type"].get_ref<const std::string&>().size() + g["type"].get_ref<const std::string&>().size() + g["coordinates"].size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (const auto& q : r)
+        {
+            acc += q["round"].get_ref<const std::string&>() == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(q["category"].get_ref<const std::string&>().size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(r["method"].get_ref<const std::string&>().size());
+        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, yyjson_val* r)
+{
+    double acc = 0;
+    auto get = [](yyjson_val * o, const char* k)
+    {
+        return yyjson_obj_get(o, k);
+    };
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](yyjson_val * s)
+        {
+            acc += static_cast<double>(yyjson_get_uint(get(s, "id")));
+            acc += static_cast<double>(yyjson_get_len(get(get(s, "user"), "screen_name")));
+            acc += static_cast<double>(yyjson_get_sint(get(s, "retweet_count")));
+        };
+        if (name == "twitter")
+        {
+            std::size_t idx, max;
+            yyjson_val* s;
+            yyjson_arr_foreach(get(r, "statuses"), idx, max, s)
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        std::size_t idx, max;
+        yyjson_val* p;
+        yyjson_arr_foreach(get(r, "performances"), idx, max, p)
+        {
+            acc += static_cast<double>(yyjson_get_uint(get(p, "id")) + yyjson_get_uint(get(p, "eventId")) + yyjson_arr_size(get(p, "seatCategories")));
+        }
+        acc += static_cast<double>(yyjson_obj_size(get(r, "events")));
+    }
+    else if (name == "canada")
+    {
+        yyjson_val* g = get(yyjson_arr_get(get(r, "features"), 0), "geometry");
+        acc += static_cast<double>(yyjson_get_len(get(r, "type")) + yyjson_get_len(get(g, "type")) + yyjson_arr_size(get(g, "coordinates")));
+    }
+    else if (name == "jeopardy")
+    {
+        std::size_t idx, max;
+        yyjson_val* q;
+        yyjson_arr_foreach(r, idx, max, q)
+        {
+            acc += yyjson_equals_str(get(q, "round"), "Final Jeopardy!") ? 1 : 0;
+            acc += static_cast<double>(yyjson_get_len(get(q, "category")));
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(yyjson_get_len(get(r, "method")));
+        acc += static_cast<double>(yyjson_get_sint(get(get(r, "params"), "minuend")) + yyjson_get_sint(get(r, "id")));
+    }
+    return acc;
+}
+
+static double pick(const std::string& name, simdjson::dom::element r)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](simdjson::dom::element s)
+        {
+            acc += static_cast<double>(uint64_t(s["id"]));
+            acc += static_cast<double>(std::string_view(s["user"]["screen_name"]).size());
+            acc += static_cast<double>(int64_t(s["retweet_count"]));
+        };
+        if (name == "twitter")
+        {
+            for (auto s : simdjson::dom::array(r["statuses"]))
+            {
+                one(s);
+            }
+        }
+        else
+        {
+            one(r);
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        for (auto p : simdjson::dom::array(r["performances"]))
+        {
+            acc += static_cast<double>(uint64_t(p["id"]) + uint64_t(p["eventId"]) + simdjson::dom::array(p["seatCategories"]).size());
+        }
+        acc += static_cast<double>(simdjson::dom::object(r["events"]).size());
+    }
+    else if (name == "canada")
+    {
+        auto g = r["features"].at(0)["geometry"];
+        acc += static_cast<double>(std::string_view(r["type"]).size() + std::string_view(g["type"]).size() + simdjson::dom::array(g["coordinates"]).size());
+    }
+    else if (name == "jeopardy")
+    {
+        for (auto q : simdjson::dom::array(r))
+        {
+            acc += std::string_view(q["round"]) == "Final Jeopardy!" ? 1 : 0;
+            acc += static_cast<double>(std::string_view(q["category"]).size());
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(std::string_view(r["method"]).size());
+        acc += static_cast<double>(int64_t(r["params"]["minuend"]) + int64_t(r["id"]));
+    }
+    return acc;
+}
+
+static double pick_od(const std::string& name, simdjson::ondemand::document& d)
+{
+    double acc = 0;
+    if (name == "twitter" || name == "status")
+    {
+        auto one = [&](simdjson::ondemand::object s)
+        {
+            acc += static_cast<double>(uint64_t(s["id"]));
+            acc += static_cast<double>(std::string_view(s["user"]["screen_name"]).size());
+            acc += static_cast<double>(int64_t(s["retweet_count"]));
+        };
+        if (name == "twitter")
+        {
+            for (auto s : d["statuses"])
+            {
+                one(s.get_object());
+            }
+        }
+        else
+        {
+            one(d.get_object());
+        }
+    }
+    else if (name == "citm_catalog")
+    {
+        simdjson::ondemand::object ev = d["events"].get_object();
+        acc += static_cast<double>(ev.count_fields());
+        for (auto p : d["performances"])
+        {
+            simdjson::ondemand::object o = p.get_object();
+            const auto a = uint64_t(o["eventId"]) + uint64_t(o["id"]);
+            simdjson::ondemand::array sc = o["seatCategories"].get_array();
+            acc += static_cast<double>(a + sc.count_elements());
+        }
+    }
+    else if (name == "canada")
+    {
+        acc += static_cast<double>(std::string_view(d["type"]).size());
+        auto g = d["features"].at(0)["geometry"];
+        acc += static_cast<double>(std::string_view(g["type"]).size());
+        simdjson::ondemand::array co = g["coordinates"].get_array();
+        acc += static_cast<double>(co.count_elements());
+    }
+    else if (name == "jeopardy")
+    {
+        for (auto q : d)
+        {
+            simdjson::ondemand::object o = q.get_object();
+            acc += static_cast<double>(std::string_view(o["category"]).size());
+            acc += std::string_view(o["round"]) == "Final Jeopardy!" ? 1 : 0;
+        }
+    }
+    else if (name == "rpc")
+    {
+        acc += static_cast<double>(std::string_view(d["method"]).size());
+        acc += static_cast<double>(int64_t(d["params"]["minuend"]));
+        acc += static_cast<double>(int64_t(d["id"]));
+    }
+    return acc;
+}
+
+// ---------------- harness ----------------
+
+static std::string slurp(const std::string& p)
+{
+    std::ifstream f(p, std::ios::binary);
+    std::stringstream ss;
+    ss << f.rdbuf();
+    return ss.str();
+}
+
+struct engine
+{
+    std::string name;
+    std::function<void()> fn;
+};
+
+int main(int argc, char** argv)
+{
+    if (argc < 2)
+    {
+        std::fprintf(stderr, "usage: %s <json_test_data directory> [rounds] [document]\n", argv[0]);
+        return 1;
+    }
+    const std::string T = std::string(argv[1]) + "/";
+    const int rounds = argc > 2 ? std::atoi(argv[2]) : 30;
+    const std::string only = argc > 3 ? argv[3] : "";
+    struct doc
+    {
+        std::string name, text;
+        int batch;
+    };
+    std::vector<doc> docs;
+    for (const char* f :
+            {"nativejson-benchmark/twitter.json", "nativejson-benchmark/citm_catalog.json", "nativejson-benchmark/canada.json", "jeopardy/jeopardy.json"
+            })
+    {
+        std::string n = std::string(f).substr(std::string(f).find('/') + 1);
+        docs.push_back({n.substr(0, n.size() - 5), slurp(T + f), 1});
+    }
+    docs.push_back({"status", json::parse(docs[0].text)["statuses"][0].dump(), 200});
+    docs.push_back({"rpc", R"({"jsonrpc": "2.0", "method": "subtract", "params": {"minuend": 42, "subtrahend": 23}, "id": 3})", 5000});
+
+    // correctness cross-check of the workloads
+    for (const auto& dc : docs)
+    {
+        stats a, b, c, dd;
+        walk(json::parse(dc.text), a);
+        auto d = json_document::parse(dc.text);
+        walk(d.root(), b);
+        yyjson_doc* y = yyjson_read(dc.text.data(), dc.text.size(), 0);
+        walk(yyjson_doc_get_root(y), c);
+        simdjson::dom::parser p;
+        walk(p.parse(dc.text).value(), dd);
+        const bool ok = a.nodes == b.nodes && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
+                        && std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num) && std::fabs(a.num - c.num) <= 1e-9 * std::fabs(a.num);
+        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
+        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pc && pa == pd) ? "OK" : "MISMATCH");
+        yyjson_doc_free(y);
+    }
+
+    std::FILE* csv = std::fopen("bench_view.csv", "w");
+    std::fprintf(csv, "doc,bytes,workload,engine,ns\n");
+    json_document reused;
+    simdjson::dom::parser sj;
+    simdjson::ondemand::parser od;
+    for (const auto& dc : docs)
+    {
+        if (!only.empty() && dc.name != only)
+        {
+            continue;
+        }
+        const std::string& s = dc.text;
+        const simdjson::padded_string ps(s);
+        const std::string name = dc.name;
+        std::vector<std::pair<std::string, std::vector<engine>>> workloads;
+
+        workloads.push_back({"parse", {
+                {"json_view", [&] { auto d = json_document::parse(s); g_sink = static_cast<double>(d.node_count()); }},
+                {"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(d)); yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
+#if JSON_VIEW_BENCH_BOOST
+                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); g_sink = v.is_object(); }},
+#endif
+                {"json::parse", [&] { json j = json::parse(s); g_sink = static_cast<double>(j.size()); }},
+            }});
+        workloads.push_back({"traverse", {
+                {"json_view", [&] { auto d = json_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(d), st); g_sink = st.num; yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
+                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); stats st; walk_od(d.get_value().value_unsafe(), st); g_sink = st.num; }},
+#if JSON_VIEW_BENCH_BOOST
+                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); stats st; walk(v, st); g_sink = st.num; }},
+#endif
+                {"json::parse", [&] { json j = json::parse(s); stats st; walk(j, st); g_sink = st.num; }},
+            }});
+        workloads.push_back({"select", {
+                {"json_view", [&] { auto d = json_document::parse(s); g_sink = pick(name, d.root()); }},
+                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = pick(name, yyjson_doc_get_root(d)); yyjson_doc_free(d); }},
+                {"simdjson DOM", [&] { g_sink = pick(name, sj.parse(ps).value_unsafe()); }},
+                {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); g_sink = pick_od(name, d); }},
+                {"json::parse", [&] { json j = json::parse(s); g_sink = pick(name, j); }},
+            }});
+        {
+            // serialization of an already parsed document
+            static json_document vd;
+            vd.read(s);
+            static yyjson_doc* yd = nullptr;
+            if (yd)
+            {
+                yyjson_doc_free(yd);
+            }
+            yd = yyjson_read(s.data(), s.size(), 0);
+            static simdjson::dom::parser sjd;
+            static simdjson::dom::element se;
+            se = sjd.parse(ps).value_unsafe();
+            static json jd;
+            jd = json::parse(s);
+            workloads.push_back({"dump", {
+                    {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
+                    {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
+                    {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
+                    {"json::parse", [&] { std::string o = jd.dump(); g_sink = static_cast<double>(o.size()); }},
+                }});
+        }
+
+        for (auto& wl : workloads)
+        {
+            std::vector<double> best(wl.second.size(), 1e300);
+            const int r = s.size() > 10000000 ? std::max(3, rounds / 5) : rounds;
+            for (int i = 0; i < r; ++i)
+            {
+                for (std::size_t k = 0; k < wl.second.size(); ++k)
+                {
+                    const auto t0 = std::chrono::steady_clock::now();
+                    for (int b = 0; b < dc.batch; ++b)
+                    {
+                        wl.second[k].fn();
+                    }
+                    const double ns = std::chrono::duration<double, std::nano>(std::chrono::steady_clock::now() - t0).count() / dc.batch;
+                    best[k] = std::min(best[k], ns);
+                }
+            }
+            const double ref = best[0];
+            std::printf("%-13s %-9s", dc.name.c_str(), wl.first.c_str());
+            for (std::size_t k = 0; k < wl.second.size(); ++k)
+            {
+                const double us = best[k] / 1e3;
+                std::printf("  %s %s%s (%.2fx)", wl.second[k].name.c_str(), us >= 100 ? "" : "", (us >= 1000 ? std::to_string(static_cast<long>(us)) + "us" : (std::to_string(us).substr(0, 5) + "us")).c_str(), best[k] / ref);
+                std::fprintf(csv, "%s,%zu,%s,%s,%.1f\n", dc.name.c_str(), s.size(), wl.first.c_str(), wl.second[k].name.c_str(), best[k]);
+            }
+            std::printf("\n");
+            std::fflush(stdout);
+        }
+    }
+    std::fclose(csv);
+}

tests/benchmarks/json_view/compare.py

@@ -0,0 +1,300 @@
+#!/usr/bin/env python3
+#     __ _____ _____ _____
+#  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+# |  |  |__   |  |  | | | |  version 3.12.0
+# |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+#
+# SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+# SPDX-License-Identifier: MIT
+
+"""Compare json_view with yyjson, simdjson, Boost.JSON, and json::parse.
+
+Builds bench_view.cpp and bench_corpus.cpp against the include/ directory of
+this checkout, runs them, and writes the results with everything needed to
+reproduce them (date, commit, CPU, OS, compiler, library versions, flags) to
+results/<date>-<host>.md and .csv next to this script.
+
+The other libraries come from the system (--system, the default: pkg-config
+or Homebrew) or are downloaded as pinned releases and checked against their
+SHA-256 (--download). Boost.JSON is optional: without Boost headers, its
+columns are skipped, and the results say so.
+
+Only the Python 3 standard library is used; a C++17 compiler is needed.
+"""
+
+import argparse
+import datetime
+import hashlib
+import os
+import platform
+import re
+import shlex
+import shutil
+import subprocess
+import sys
+import tarfile
+import urllib.request
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+REPO = os.path.abspath(os.path.join(HERE, '..', '..', '..'))
+
+# pinned releases for --download; the hashes are those of the archives
+PINNED = {
+    'yyjson': {
+        'version': '0.13.0',
+        'url': 'https://github.com/ibireme/yyjson/archive/refs/tags/0.13.0.tar.gz',
+        'sha256': '34e0f62a2bc11ab20d601e8ca1cc2b2079503aa45119a19133d89d19b94a0fae',
+        'dir': 'yyjson-0.13.0',
+    },
+    'simdjson': {
+        'version': '4.6.11',
+        'url': 'https://github.com/simdjson/simdjson/archive/refs/tags/v4.6.11.tar.gz',
+        'sha256': '61d948fc24f0d793829ad658058e7597d064988a89b4607ea02e401a82df98ff',
+        'dir': 'simdjson-4.6.11',
+    },
+    'boost': {
+        'version': '1.92.0',
+        'url': 'https://archives.boost.io/release/1.92.0/source/boost_1_92_0.tar.gz',
+        'sha256': 'c4a3b310ddd2472416e091067166b0713be97c63f38c212c484ada022fd296ce',
+        'dir': 'boost_1_92_0',
+    },
+}
+
+# the documents of bench_view.cpp, relative to the json_test_data directory
+DEFAULT_CORPUS = [
+    'nativejson-benchmark/twitter.json',
+    'nativejson-benchmark/citm_catalog.json',
+    'nativejson-benchmark/canada.json',
+    'jeopardy/jeopardy.json',
+]
+
+
+def run(cmd, **kwargs):
+    print('+ ' + ' '.join(shlex.quote(c) for c in cmd), flush=True)
+    return subprocess.run(cmd, check=True, **kwargs)
+
+
+def output(cmd):
+    try:
+        return subprocess.run(cmd, check=True, capture_output=True, text=True).stdout.strip()
+    except (OSError, subprocess.CalledProcessError):
+        return ''
+
+
+# ---------------------------------------------------------------------------
+# libraries
+# ---------------------------------------------------------------------------
+
+class Library:
+    """include directories, sources to compile, and linker flags of a library"""
+
+    def __init__(self, name, include=None, sources=None, link=None, version=''):
+        self.name = name
+        self.include = include or []
+        self.sources = sources or []
+        self.link = link or []
+        self.version = version
+
+
+def header_version(path, pattern):
+    try:
+        with open(path, encoding='utf-8', errors='replace') as f:
+            m = re.search(pattern, f.read())
+        return m.group(1) if m else ''
+    except OSError:
+        return ''
+
+
+def library_version(name, include_dirs):
+    patterns = {
+        'yyjson': ('yyjson.h', r'#define\s+YYJSON_VERSION_STRING\s+"([^"]+)"'),
+        'simdjson': ('simdjson.h', r'#define\s+SIMDJSON_VERSION\s+"?([0-9.]+)"?'),
+        'boost': (os.path.join('boost', 'version.hpp'), r'#define\s+BOOST_LIB_VERSION\s+"([^"]+)"'),
+    }
+    header, pattern = patterns[name]
+    for d in include_dirs:
+        v = header_version(os.path.join(d, header), pattern)
+        if v:
+            return v.replace('_', '.')
+    return ''
+
+
+def system_library(name):
+    """a library found with pkg-config or Homebrew, or None"""
+    flags = output(['pkg-config', '--cflags', '--libs', name]).split()
+    if flags:
+        include = [f[2:] for f in flags if f.startswith('-I')]
+        link = [f for f in flags if f.startswith('-L') or f.startswith('-l')]
+        libdirs = [f[2:] for f in link if f.startswith('-L')]
+        link += ['-Wl,-rpath,' + d for d in libdirs]
+        return Library(name, include, [], link, library_version(name, include))
+    prefix = output(['brew', '--prefix', name]) if shutil.which('brew') else ''
+    if prefix and os.path.isdir(os.path.join(prefix, 'include')):
+        include = [os.path.join(prefix, 'include')]
+        link = []
+        if name != 'boost':
+            lib = os.path.join(prefix, 'lib')
+            link = ['-L' + lib, '-l' + name, '-Wl,-rpath,' + lib]
+        return Library(name, include, [], link, library_version(name, include))
+    if name == 'boost':
+        for d in ['/usr/include', '/usr/local/include']:
+            if os.path.isfile(os.path.join(d, 'boost', 'json.hpp')):
+                return Library(name, [d], [], [], library_version(name, [d]))
+    return None
+
+
+def download_library(name, work):
+    """a pinned release, downloaded and checked, or an error"""
+    pin = PINNED[name]
+    archive = os.path.join(work, 'download', os.path.basename(pin['url']))
+    os.makedirs(os.path.dirname(archive), exist_ok=True)
+    if not os.path.isfile(archive):
+        print(f'downloading {pin["url"]}', flush=True)
+        urllib.request.urlretrieve(pin['url'], archive)
+    with open(archive, 'rb') as f:
+        digest = hashlib.sha256(f.read()).hexdigest()
+    if digest != pin['sha256']:
+        sys.exit(f'error: SHA-256 of {archive} is {digest}, expected {pin["sha256"]}')
+    src = os.path.join(work, 'download', pin['dir'])
+    if not os.path.isdir(src):
+        with tarfile.open(archive) as t:
+            # (the 'data' filter rejects links and paths outside the target where Python has it)
+            kwargs = {'filter': 'data'} if hasattr(tarfile, 'data_filter') else {}
+            t.extractall(os.path.join(work, 'download'), **kwargs)  # noqa: S202 (checked archive)
+    if name == 'yyjson':
+        return Library(name, [os.path.join(src, 'src')], [os.path.join(src, 'src', 'yyjson.c')], [], pin['version'])
+    if name == 'simdjson':
+        single = os.path.join(src, 'singleheader')
+        return Library(name, [single], [os.path.join(single, 'simdjson.cpp')], [], pin['version'])
+    return Library(name, [src], [], [], pin['version'])
+
+
+# ---------------------------------------------------------------------------
+# machine description
+# ---------------------------------------------------------------------------
+
+def cpu_model():
+    if sys.platform == 'darwin':
+        return output(['sysctl', '-n', 'machdep.cpu.brand_string'])
+    try:
+        with open('/proc/cpuinfo', encoding='utf-8') as f:
+            for line in f:
+                if line.startswith('model name') or line.startswith('Model'):
+                    return line.split(':', 1)[1].strip()
+    except OSError:
+        pass
+    # (AArch64 Linux: /proc/cpuinfo has no model name, lscpu knows it)
+    for line in output(['lscpu']).splitlines():
+        if line.startswith('Model name:'):
+            return line.split(':', 1)[1].strip()
+    return platform.processor() or platform.machine()
+
+
+def git_commit():
+    commit = output(['git', '-C', REPO, 'rev-parse', '--short=12', 'HEAD'])
+    dirty = output(['git', '-C', REPO, 'status', '--porcelain', '--untracked-files=no'])
+    return commit + (' (with local changes)' if dirty else '')
+
+
+# ---------------------------------------------------------------------------
+# main
+# ---------------------------------------------------------------------------
+
+def main():
+    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument('--data', required=True, help='json_test_data directory (with nativejson-benchmark/ and jeopardy/)')
+    ap.add_argument('--download', action='store_true', help='use pinned downloads instead of system libraries')
+    ap.add_argument('--no-boost', action='store_true', help='skip Boost.JSON')
+    ap.add_argument('--native', action='store_true', help='compile for this CPU (-march=native / -mcpu=native)')
+    ap.add_argument('--rounds', type=int, default=30, help='rounds of bench_view (default: 30)')
+    ap.add_argument('--corpus', nargs='*', default=[], help='more files for bench_corpus')
+    ap.add_argument('--build-dir', default=os.path.join(HERE, 'build'), help='where to build (default: build/ next to this script)')
+    args = ap.parse_args()
+
+    cxx = os.environ.get('CXX', 'c++')
+    cc = os.environ.get('CC', 'cc')
+    os.makedirs(args.build_dir, exist_ok=True)
+
+    libs = {}
+    for name in ['yyjson', 'simdjson', 'boost']:
+        if name == 'boost' and args.no_boost:
+            continue
+        lib = download_library(name, args.build_dir) if args.download else system_library(name)
+        if lib is None and name != 'boost':
+            sys.exit(f'error: {name} not found; install it, or use --download')
+        if lib is not None:
+            libs[name] = lib
+    with_boost = 'boost' in libs
+    if not with_boost:
+        print('Boost.JSON not found: its columns are skipped', flush=True)
+
+    flags = ['-std=c++17', '-O3', '-DNDEBUG', f'-DJSON_VIEW_BENCH_BOOST={1 if with_boost else 0}']
+    if args.native:
+        flags.append('-mcpu=native' if platform.machine().lower() in ('arm64', 'aarch64') else '-march=native')
+    include = ['-I' + os.path.join(REPO, 'include')] + ['-I' + d for lib in libs.values() for d in lib.include]
+    link = [f for lib in libs.values() for f in lib.link]
+
+    # C sources of downloaded libraries are compiled once
+    objects = []
+    for lib in libs.values():
+        for src in lib.sources:
+            obj = os.path.join(args.build_dir, os.path.basename(src) + '.o')
+            compiler = cc if src.endswith('.c') else cxx
+            run([compiler] + (['-std=c++17'] if compiler == cxx else []) + ['-O3', '-DNDEBUG', '-c', src, '-o', obj]
+                + ['-I' + d for d in lib.include])
+            objects.append(obj)
+
+    binaries = {}
+    for bench in ['bench_view', 'bench_corpus']:
+        exe = os.path.join(args.build_dir, bench)
+        run([cxx] + flags + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
+        binaries[bench] = exe
+
+    # run: bench_view on its documents, bench_corpus on those and the given files
+    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
+    outputs = {}
+    outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=args.build_dir,
+                                capture_output=True, text=True).stdout
+    outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=args.build_dir,
+                                  capture_output=True, text=True).stdout
+    for name, text in outputs.items():
+        print(text)
+
+    # results with their metadata
+    now = datetime.datetime.now()
+    host = re.sub(r'[^A-Za-z0-9-]+', '-', platform.node().split('.')[0]) or 'host'
+    stem = os.path.join(HERE, 'results', f'{now:%Y-%m-%d}-{host}')
+    os.makedirs(os.path.dirname(stem), exist_ok=True)
+    meta = [
+        ('date', f'{now:%Y-%m-%d %H:%M}'),
+        ('commit', git_commit()),
+        ('CPU', cpu_model()),
+        ('OS', f'{platform.system()} {platform.release()} ({platform.machine()})'),
+        ('compiler', output([cxx, '--version']).splitlines()[0] if output([cxx, '--version']) else cxx),
+        ('flags', ' '.join(flags)),
+        ('yyjson', libs['yyjson'].version),
+        ('simdjson', libs['simdjson'].version),
+        ('Boost.JSON', libs['boost'].version if with_boost else 'skipped (not found)'),
+        ('libraries from', 'pinned downloads' if args.download else 'the system'),
+        ('rounds', str(args.rounds)),
+    ]
+    with open(stem + '.md', 'w', encoding='utf-8') as f:
+        f.write(f'# json_view comparison, {now:%Y-%m-%d}\n\n')
+        f.write('Generated by `tests/benchmarks/json_view/compare.py`; best of the interleaved rounds.\n\n')
+        f.write('| | |\n|---|---|\n')
+        for key, value in meta:
+            f.write(f'| {key} | {value} |\n')
+        for name, text in outputs.items():
+            f.write(f'\n## {name}\n\n```\n{text.rstrip()}\n```\n')
+    with open(stem + '.csv', 'w', encoding='utf-8') as out:
+        out.write(''.join(f'# {key}: {value}\n' for key, value in meta))
+        for name in ['bench_view', 'bench_corpus']:
+            path = os.path.join(args.build_dir, name + '.csv')
+            if os.path.isfile(path):
+                with open(path, encoding='utf-8') as f:
+                    out.write(f'# {name}\n' + f.read())
+    print(f'results: {stem}.md, {stem}.csv')
+
+
+if __name__ == '__main__':
+    main()

tests/benchmarks/src/benchmarks_view.cpp

@@ -144,3 +144,37 @@ static void ViewMaterialize(benchmark::State& state, const char* filename)
     state.SetBytesProcessed(state.iterations() * str.size());
 }
 JSON_VIEW_BENCHMARK_FILES(ViewMaterialize);
+
+//////////////////////////////////////////////////////////////////////////////
+// serialize a parsed document (compare with Dump)
+//////////////////////////////////////////////////////////////////////////////
+
+static void ViewDump(benchmark::State& state, const char* filename, int indent)
+{
+    const std::string str = read_file(filename);
+    const json_document d = json_document::parse(str);
+
+    while (state.KeepRunning())
+    {
+        std::string output = d.root().dump(indent);
+        benchmark::DoNotOptimize(output);
+    }
+
+    state.SetBytesProcessed(state.iterations() * d.root().dump(indent).size());
+}
+BENCHMARK_CAPTURE(ViewDump, jeopardy / -,          TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json",                 -1);
+BENCHMARK_CAPTURE(ViewDump, jeopardy / 4,          TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json",                 4);
+BENCHMARK_CAPTURE(ViewDump, canada / -,            TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json",       -1);
+BENCHMARK_CAPTURE(ViewDump, canada / 4,            TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json",       4);
+BENCHMARK_CAPTURE(ViewDump, citm_catalog / -,      TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", -1);
+BENCHMARK_CAPTURE(ViewDump, citm_catalog / 4,      TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", 4);
+BENCHMARK_CAPTURE(ViewDump, twitter / -,           TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json",      -1);
+BENCHMARK_CAPTURE(ViewDump, twitter / 4,           TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json",      4);
+BENCHMARK_CAPTURE(ViewDump, floats / -,            TEST_DATA_DIRECTORY "/regression/floats.json",                 -1);
+BENCHMARK_CAPTURE(ViewDump, floats / 4,            TEST_DATA_DIRECTORY "/regression/floats.json",                 4);
+BENCHMARK_CAPTURE(ViewDump, signed_ints / -,       TEST_DATA_DIRECTORY "/regression/signed_ints.json",            -1);
+BENCHMARK_CAPTURE(ViewDump, signed_ints / 4,       TEST_DATA_DIRECTORY "/regression/signed_ints.json",            4);
+BENCHMARK_CAPTURE(ViewDump, unsigned_ints / -,     TEST_DATA_DIRECTORY "/regression/unsigned_ints.json",          -1);
+BENCHMARK_CAPTURE(ViewDump, unsigned_ints / 4,     TEST_DATA_DIRECTORY "/regression/unsigned_ints.json",          4);
+BENCHMARK_CAPTURE(ViewDump, small_signed_ints / -, TEST_DATA_DIRECTORY "/regression/small_signed_ints.json",      -1);
+BENCHMARK_CAPTURE(ViewDump, small_signed_ints / 4, TEST_DATA_DIRECTORY "/regression/small_signed_ints.json",      4);

tests/src/unit-json_view.cpp

@@ -22,6 +22,7 @@ using nlohmann::ordered_json_view;
 #include <cstdint>
 #include <cstdio>
 #include <cstring>
+#include <iomanip>
 #include <iterator>
 #include <list>
 #include <map>
@@ -872,7 +873,15 @@ TEST_CASE("json_view values")
         std::mt19937_64 rng(5295); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
         std::vector<std::string> tokens = {"0.1", "-0.0", "1e308", "1.7976931348623157e308", "2.2250738585072011e-308", "4.9e-324", "5e-324",
                                            "0.1000000000000000055511151231257827021181583404541015625", "123456789012345678901234567890",
-                                           "9007199254740993", "1.00000000000000011102230246251565404236316680908203125", "7.2057594037927933e16"
+                                           "9007199254740993", "1.00000000000000011102230246251565404236316680908203125", "7.2057594037927933e16",
+                                           // around the limits of the conversion from the digit layout: 19 and 20
+                                           // digits, and those of Clinger's fast path (2^53, 10^22)
+                                           "1234567890.123456789", "1234567890.1234567891", "0.0000000000000000001", "123456789012345678.9",
+                                           "9007199254740992.0", "9007199254740993.0", "9007199254740994.0", "1.5e22", "1.5e23", "15e-22", "15e-23",
+                                           "1e-400", "0.0e0", "-0.0e-5", "12E+3", "12e-0",
+                                           // and of float: 2^24 + 1 and 2^24 + 3 (ties), the subnormal and normal limits
+                                           "16777217", "16777219", "1.4e-45", "7.006492321624085e-46", "7.006492321624086e-46",
+                                           "1.17549435e-38", "0.30000001192092896", "3.4028234e37"
                                           };
         for (int i = 0; i < 20000; ++i)
         {
@@ -1081,3 +1090,247 @@ TEST_CASE("json_view JSON pointers")
     }
 #endif
 }
+
+TEST_CASE("json_view dump")
+{
+    SECTION("the output of ordered_json::dump()")
+    {
+        generator g;
+        for (int i = 0; i < 2000; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            const ordered_json_document d = ordered_json_document::parse(text);
+            if (has_duplicate_keys(d.root()))
+            {
+                continue;
+            }
+            CAPTURE(text);
+            const ordered_json j = ordered_json::parse(text);
+            for (const int indent :
+                    {
+                        -1, 0, 2
+                    })
+            {
+                for (const bool ensure_ascii :
+                        {
+                            false, true
+                        })
+                {
+                    CHECK(d.root().dump(indent, i % 2 == 0 ? ' ' : '\t', ensure_ascii) == j.dump(indent, i % 2 == 0 ? ' ' : '\t', ensure_ascii));
+                }
+            }
+            // also of each element
+            for (const ordered_json_view e : d.root())
+            {
+                CHECK(e.dump() == e.materialize().dump());
+            }
+        }
+    }
+
+    SECTION("strings")
+    {
+        const std::string text = R"(["plain", "\u0000\u0001\u001f\u007f\u0080é€￿😀", "\"\\\/\b\f\n\r\t", "aéあ😀b", "long text beyond the eight bytes of a word \n with an escape in the middle"])";
+        const ordered_json_document d = ordered_json_document::parse(text);
+        const ordered_json j = ordered_json::parse(text);
+        CHECK(d.root().dump() == j.dump());
+        CHECK(d.root().dump(-1, ' ', true) == j.dump(-1, ' ', true));
+        CHECK(d.root().dump(4, ' ', true) == j.dump(4, ' ', true));
+        const ordered_json_document keys = ordered_json_document::parse(R"({"é\n": {"\"": [], "": {}}})");
+        CHECK(keys.root().dump(2, ' ', true) == ordered_json::parse(R"({"é\n": {"\"": [], "": {}}})").dump(2, ' ', true));
+    }
+
+    SECTION("numbers")
+    {
+        const std::string text = "[1.50, 1E2, -0, -0.0, 123456789012345678901234567890, 18446744073709551615, -9223372036854775808, 0.1, 1e-7, 5e-324]";
+        const json_document d = json_document::parse(text);
+        CHECK(d.root().dump() == json::parse(text).dump());
+        CHECK(d.root().dump() == "[1.5,100.0,0,-0.0,1.2345678901234568e+29,18446744073709551615,-9223372036854775808,0.1,1e-07,5e-324]");
+        CHECK(d.root().dump(-1, ' ', false, json_view::number_format::source) == "[1.50,1E2,-0,-0.0,123456789012345678901234567890,18446744073709551615,-9223372036854775808,0.1,1e-7,5e-324]");
+
+        // random doubles, written as parse() and dump() would
+        std::mt19937_64 rng(1170); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed)
+        std::string many = "[";
+        for (int i = 0; i < 5000; ++i)
+        {
+            const std::uint64_t bits = rng();
+            double x = 0;
+            std::memcpy(&x, &bits, sizeof(x));
+            if (std::isfinite(x))
+            {
+                many += (many.size() > 1 ? "," : "") + json(x).dump();
+            }
+        }
+        many += ']';
+        CHECK(json_document::parse(many).root().dump() == json::parse(many).dump());
+
+        using json_float = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, float>;
+        CHECK(nlohmann::basic_json_document<json_float>::parse("[0.1, 1.5e10, 3.4028235e38]").root().dump() == json_float::parse("[0.1, 1.5e10, 3.4028235e38]").dump());
+    }
+
+    SECTION("members in document order, all of them")
+    {
+        const json_document d = json_document::parse(R"({"b": 1, "a": 2, "b": 3})");
+        CHECK(d.root().dump() == R"({"b":1,"a":2,"b":3})");
+        CHECK(d.root().dump(1) == "{\n \"b\": 1,\n \"a\": 2,\n \"b\": 3\n}");
+    }
+
+    SECTION("deep nesting")
+    {
+        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
+        CHECK(json_document::parse(deep).root().dump() == deep);
+    }
+
+    SECTION("streams and discarded views")
+    {
+        const json_document d = json_document::parse(R"({"a": [1, 2]})");
+        std::ostringstream compact;
+        compact << d.root();
+        CHECK(compact.str() == R"({"a":[1,2]})");
+        std::ostringstream pretty;
+        pretty << std::setw(2) << std::setfill('.') << d.root() << d.root()["a"];
+        CHECK(pretty.str() == "{\n..\"a\": [\n....1,\n....2\n..]\n}[1,2]");
+        CHECK(json_view().dump() == json(json::value_t::discarded).dump());
+    }
+}
+
+TEST_CASE("json_view comparison")
+{
+    SECTION("equality of the values parse() produces")
+    {
+        generator g;
+        std::vector<std::string> texts;
+        for (int i = 0; i < 600; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            texts.push_back(text);
+            // the same value written differently: sorted keys, canonical numbers
+            texts.push_back(json::parse(text).dump(1));
+        }
+        for (std::size_t i = 0; i + 2 < texts.size(); ++i)
+        {
+            for (std::size_t k = i; k < i + 3; ++k)
+            {
+                CAPTURE(texts[i]);
+                CAPTURE(texts[k]);
+                const json_document a = json_document::parse(texts[i]);
+                const json_document b = json_document::parse(texts[k]);
+                const json ja = json::parse(texts[i]);
+                const json jb = json::parse(texts[k]);
+                CHECK((a.root() == b.root()) == (ja == jb));
+                CHECK((a.root() != b.root()) == (ja != jb));
+                CHECK((a.root() == jb) == (ja == jb));
+                CHECK((jb == a.root()) == (ja == jb));
+                CHECK((a.root() != jb) == (ja != jb));
+                CHECK((jb != a.root()) == (ja != jb));
+
+                // ordered_json compares members in order
+                const ordered_json_document oa = ordered_json_document::parse(texts[i]);
+                const ordered_json_document ob = ordered_json_document::parse(texts[k]);
+                const ordered_json oja = ordered_json::parse(texts[i]);
+                const ordered_json ojb = ordered_json::parse(texts[k]);
+                CHECK((oa.root() == ob.root()) == (oja == ojb));
+                CHECK((oa.root() == ojb) == (oja == ojb));
+            }
+        }
+    }
+
+    SECTION("numbers, duplicate keys, member order")
+    {
+        const auto same = [](const char* x, const char* y)
+        {
+            return json_document::parse(x).root() == json_document::parse(y).root();
+        };
+        CHECK(same("1", "1.0"));
+        CHECK(same("[1, -1, 2.5]", "[1.0, -1.0, 25e-1]"));
+        CHECK(!same("1", "1.5"));
+        CHECK(same("18446744073709551615", "18446744073709551615"));
+        CHECK(same(R"({"a": 1, "a": 2})", R"({"a": 2})"));
+        CHECK(!same(R"({"a": 1, "a": 2})", R"({"a": 1})"));
+        CHECK(same(R"({"a": 1, "b": 2})", R"({"b": 2, "a": 1})"));
+        CHECK(!same(R"({"a": 1})", R"({"a": 1, "b": 2})"));
+        CHECK(!same("[1, 2]", "[2, 1]"));
+        CHECK(!same("\"a\"", "\"b\""));
+        CHECK(same("\"\\u00e9\"", "\"\xc3\xa9\""));
+        CHECK(!same("null", "false"));
+        CHECK(!same("[]", "{}"));
+        CHECK(ordered_json_document::parse(R"({"a": 1, "b": 2, "a": 3})").root() == ordered_json_document::parse(R"({"a": 3, "b": 2})").root());
+        CHECK(ordered_json_document::parse(R"({"a": 1, "b": 2})").root() != ordered_json_document::parse(R"({"b": 2, "a": 1})").root());
+
+        // discarded values compare as basic_json's do
+        const json discarded(json::value_t::discarded);
+        CHECK((json_view() == json_view()) == (discarded == discarded)); // NOLINT(readability-container-size-empty): operator== is tested
+        CHECK((json_view() == discarded) == (discarded == discarded));
+        CHECK(!(json_view() == json_document::parse("null").root())); // NOLINT(readability-container-size-empty)
+        CHECK(!(json_document::parse("null").root() == discarded));
+    }
+
+    SECTION("deep nesting")
+    {
+        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
+        const json_document a = json_document::parse(deep);
+        const json_document b = json_document::parse(deep);
+        CHECK(a.root() == b.root());
+        CHECK(a.root() == json::parse(deep));
+        const std::string other = std::string(100000, '[') + "1" + std::string(100000, ']');
+        CHECK(a.root() != json_document::parse(other).root());
+    }
+}
+
+TEST_CASE("json_view large objects")
+{
+    // objects with 128 members or more are looked up with a hash index
+    for (const std::size_t members :
+            {
+                127u, 128u, 129u, 10000u
+            })
+    {
+        CAPTURE(members);
+        std::string text = "{";
+        for (std::size_t i = 0; i < members; ++i)
+        {
+            text += (i != 0 ? ",\"" : "\"") + std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\\n" : "") + "\":" + std::to_string(i);
+        }
+        text += R"(,"":"empty key","k1":"a duplicate of an earlier key"})";
+        const json_document d = json_document::parse(text);
+        const json_view v = d.root();
+        const json j = json::parse(text);
+        for (std::size_t i = 0; i < members; ++i)
+        {
+            const std::string key = std::string(i % 23, 'k') + std::to_string(i) + (i % 7 == 0 ? "\n" : "");
+            CHECK(v[key].get<std::size_t>() == i);
+            CHECK(v.contains(key));
+            CHECK(v.find(key).key() == key);
+            CHECK(v.at(key).get<std::size_t>() == i);
+            CHECK(!v.contains(key + "x"));
+        }
+        CHECK(v[""].get_string() == "empty key");
+        CHECK(v["k1"].get<int>() == 1); // the first of duplicate keys, as for small objects
+        CHECK(!v.contains("missing"));
+        CHECK_THROWS_WITH_AS(v.at("missing"), "[json.exception.out_of_range.403] key 'missing' not found", json::out_of_range&);
+        CHECK(v == j);
+        CHECK(v.materialize() == j);
+    }
+
+    SECTION("nested, reused, and in arrays")
+    {
+        std::string inner = "{";
+        for (int i = 0; i < 300; ++i)
+        {
+            inner += (i != 0 ? ",\"m" : "\"m") + std::to_string(i) + "\":" + std::to_string(i);
+        }
+        inner += '}';
+        const std::string text = "[" + inner + ",{\"x\":" + inner + "}," + inner + "]";
+        json_document d = json_document::parse(text);
+        CHECK(d.root()[0]["m299"].get<int>() == 299);
+        CHECK(d.root()[1]["x"]["m150"].get<int>() == 150);
+        CHECK(d.root()[2]["m0"].get<int>() == 0);
+        const std::size_t with_index = d.memory_usage();
+        d.read(std::string("{\"small\": 1}"));
+        CHECK(d.root()["small"].get<int>() == 1);
+        d.read(text);
+        CHECK(d.root()[2]["m7"].get<int>() == 7);
+        CHECK(d.memory_usage() >= with_index / 2);
+    }
+}

tests/src/unit-json_view_builder.cpp

@@ -17,6 +17,7 @@
 #endif
 using nlohmann::json;
 
+#include <array>
 #include <cstdint>
 #include <fstream>
 #include <map>
@@ -142,6 +143,32 @@ void check_same(const std::string& text)
     }
 }
 
+// a string value and a key must be accepted or rejected as json::parse does,
+// and give its value (cheaper than check_same: the options do not matter)
+void check_string(const std::string& content)
+{
+    for (const std::string& text :
+            {
+                "[\"" + content + "\"]", "{\"" + content + "\":1}"
+            })
+    {
+        const bool accepted = json::accept(text);
+        for (const bool sentinel :
+                {
+                    true, false
+                })
+        {
+            const built b = build(text, false, false, sentinel);
+            if (b.ok != accepted || (accepted && value_of(b) != json::parse(text)))
+            {
+                CAPTURE(text);
+                CHECK(b.ok == accepted);
+                CHECK((b.ok && accepted ? value_of(b) == json::parse(text) : true));
+            }
+        }
+    }
+}
+
 // a small deterministic generator of documents
 struct generator
 {
@@ -401,3 +428,81 @@ TEST_CASE("json_view builder")
         }
     }
 }
+
+TEST_CASE("json_view builder: strings across vector blocks")
+{
+    // Strings are scanned 8 or 16 bytes at a time (NEON, SSE2, or SWAR) and
+    // non-ASCII text with the vector UTF-8 check (NEON, SSSE3) or one sequence
+    // at a time. Sequences are placed so that they start at every offset
+    // around the block boundaries of keys (16, 32) and values (8, 24), with
+    // text of several lengths after them.
+    const std::array<std::size_t, 16> prefixes = {{0, 6, 7, 8, 13, 14, 15, 16, 21, 22, 23, 24, 29, 30, 31, 32}};
+    const std::array<std::size_t, 3> suffixes = {{0, 3, 17}};
+    const auto around = [&](const std::string & seq, std::size_t prefix, std::size_t suffix)
+    {
+        return std::string(prefix, 'a') + seq + std::string(suffix, 'b');
+    };
+
+    SECTION("every two-byte sequence")
+    {
+        for (unsigned lead = 0x80; lead <= 0xFF; ++lead)
+        {
+            for (unsigned second = 0; second <= 0xFF; ++second)
+            {
+                if (second == '"' || second == '\\')
+                {
+                    continue;
+                }
+                const std::string seq = {static_cast<char>(lead), static_cast<char>(second)};
+                check_string(around(seq, prefixes[(lead + second) % 16], suffixes[second % 3]));
+            }
+        }
+    }
+
+    SECTION("three- and four-byte sequences")
+    {
+        const std::array<unsigned, 8> conts = {{0x7F, 0x80, 0x8F, 0x90, 0x9F, 0xA0, 0xBF, 0xC0}};
+        for (unsigned lead = 0xE0; lead <= 0xF7; ++lead)
+        {
+            for (const unsigned b2 : conts)
+            {
+                for (const unsigned b3 : conts)
+                {
+                    for (const std::size_t prefix : prefixes)
+                    {
+                        std::string seq = {static_cast<char>(lead), static_cast<char>(b2), static_cast<char>(b3)};
+                        if (lead >= 0xF0)
+                        {
+                            seq += static_cast<char>(prefix % 2 == 0 ? 0x80 : 0xBF);
+                        }
+                        check_string(around(seq, prefix, suffixes[prefix % 3]));
+                        // cut short before the end of the string
+                        check_string(around(seq.substr(0, seq.size() - 1), prefix, suffixes[prefix % 3]));
+                    }
+                }
+            }
+        }
+    }
+
+    SECTION("long runs of text with one damaged byte")
+    {
+        const std::array<const char*, 7> chars = {{"a", "\xc3\xa9", "\xe3\x81\x82", "\xf0\x9f\x98\x80", "\xed\x9f\xbf", "\xef\xbf\xbf", "\xf4\x8f\xbf\xbf"}};
+        const std::array<char, 11> damage = {{'\x80', '\xbf', '\xc0', '\xc1', '\xe0', '\xed', '\xf5', '\xff', '\x1f', '"', '\\'}};
+        std::mt19937 rng(5295); // NOLINT(cert-msc32-c,cert-msc51-cpp,bugprone-random-generator-seed): reproducible
+        for (int i = 0; i < 4000; ++i)
+        {
+            std::string text;
+            const auto n = rng() % 60;
+            for (unsigned k = 0; k < n; ++k)
+            {
+                text += chars[rng() % chars.size()];
+            }
+            check_string(text);
+            if (!text.empty())
+            {
+                text[rng() % text.size()] = damage[rng() % damage.size()];
+                check_string(text);
+            }
+        }
+    }
+}