mirror of
https://github.com/nlohmann/json.git
synced 2026-11-13 15:35:23 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Niels Lohmann
|
f2f64eb67c | ||
|
Niels Lohmann
|
3004829134 |
No files matched your search
@@ -25,7 +25,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -38,7 +38,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Check that Meson and pkg-config offer the CMake options
|
||||
run: make check_build_options
|
||||
- name: Install Meson
|
||||
@@ -92,7 +92,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -123,7 +123,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -142,7 +142,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -168,7 +168,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -244,7 +244,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: CXX=g++-${{ matrix.compiler }} cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -262,7 +262,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -279,7 +279,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Disable filesystem support (std::filesystem is unusable) for clang 7 / 8 / 9 / 10
|
||||
run: echo "JSON_FORCED_GLOBAL_COMPILE_OPTIONS=-DJSON_HAS_FILESYSTEM=0;-DJSON_HAS_EXPERIMENTAL_FILESYSTEM=0" >> "$GITHUB_ENV"
|
||||
if: ${{ matrix.compiler == '7' || matrix.compiler == '8' || matrix.compiler == '9' || matrix.compiler == '10' }}
|
||||
@@ -299,7 +299,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -319,7 +319,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build with libc++
|
||||
@@ -346,7 +346,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -362,13 +362,11 @@ jobs:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
# The module test uses `import std;`, which needs CMake's experimental
|
||||
# import-std support. Its opt-in token is CMake-version-specific, so pin
|
||||
# CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
|
||||
- name: Get pinned CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
# The module test uses `import std;`, which needs CMake 4.5 or newer.
|
||||
- name: Get CMake 4.5+ and ninja
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
with:
|
||||
cmakeVersion: 4.3.4
|
||||
cmakeVersion: '^4.5.0'
|
||||
# Clang: the std library module is provided by libc++ (the image's libstdc++
|
||||
# ships none), and the image's libc++ module manifest has a broken relative
|
||||
# path — repoint it at the real module sources.
|
||||
@@ -392,7 +390,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -409,7 +407,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -423,7 +421,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DJSON_CI=On
|
||||
- name: Build
|
||||
@@ -443,7 +441,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Run CMake
|
||||
run: cmake -S . -B build -DCMAKE_TOOLCHAIN_FILE=$EMSDK/upstream/emscripten/cmake/Modules/Platform/Emscripten.cmake -GNinja
|
||||
- name: Build
|
||||
@@ -484,7 +482,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Check that the job runs natively on arm64
|
||||
run: uname -m && test "$(uname -m)" = aarch64
|
||||
- name: Run CMake
|
||||
|
||||
@@ -90,7 +90,7 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
- name: Get latest CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
- name: Set extra CXX_FLAGS for latest std_version
|
||||
# /wd5285 silences C5285 emitted by the bundled third-party doctest.h, which
|
||||
# specializes std::tuple (newly diagnosed by the VS2026 v145 toolset)
|
||||
@@ -212,13 +212,11 @@ jobs:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
# The module test uses `import std;`, which needs CMake's experimental
|
||||
# import-std support. Its opt-in token is CMake-version-specific, so pin
|
||||
# CMake to the version whose token is set in tests/module_cpp20/CMakeLists.txt.
|
||||
- name: Get pinned CMake and ninja
|
||||
uses: lukka/get-cmake@f86dd60acae0d132056913e248bdabf0e0580b7a # v4.4.5
|
||||
# The module test uses `import std;`, which needs CMake 4.5 or newer.
|
||||
- name: Get CMake 4.5+ and ninja
|
||||
uses: lukka/get-cmake@16e8153a8b4918849d92aad131befe67a3705daa # v4.5.0
|
||||
with:
|
||||
cmakeVersion: 4.3.4
|
||||
cmakeVersion: '^4.5.0'
|
||||
# CMAKE_CXX_FLAGS replaces CMake's MSVC defaults (which include /EHsc), and
|
||||
# ci_module_cpp20 forwards it to the module build, so list /EHsc explicitly
|
||||
- name: Run CMake (Debug)
|
||||
|
||||
@@ -165,7 +165,8 @@ std::ifstream f("example.json");
|
||||
json data = json::parse(f);
|
||||
```
|
||||
|
||||
If using modules (enabled with `NLOHMANN_JSON_BUILD_MODULES`), this example becomes:
|
||||
If using modules (enabled with `NLOHMANN_JSON_BUILD_MODULES`; `import std;` needs CMake 4.5 or newer, see the
|
||||
[modules documentation](https://json.nlohmann.me/features/modules/)), this example becomes:
|
||||
```cpp
|
||||
import std;
|
||||
import nlohmann.json;
|
||||
|
||||
@@ -89,10 +89,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
- Throws [out_of_range.406](../../home/exceptions.md#jsonexceptionout_of_range406) if a high-precision number, or a
|
||||
float64 when `number_float_t` is `float`, does not fit into `number_float_t`
|
||||
- Throws [out_of_range.408](../../home/exceptions.md#jsonexceptionout_of_range408) if the count of an optimized
|
||||
container exceeds the capacity of the container (or of `std::size_t`; an array of type `N` is empty, so only the
|
||||
latter applies to it), if an optimized array of `Z`, `T`, or `F` has more than 1,048,576 elements, or if the
|
||||
optimized arrays of `Z`, `T`, and `F` in the input together have more than 1,048,576 elements plus 4 for every byte
|
||||
read so far
|
||||
container exceeds the capacity of the container (or of `std::size_t`), or if an optimized array of `Z`, `T`, or `F` has
|
||||
more than 1,048,576 elements
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -134,9 +132,6 @@ Linear in the size of the input.
|
||||
- Extended container support (1) to include types with lvalue-only ADL `begin`/`end` (matching `std::begin`/`std::end` semantics) in version 3.13.0.
|
||||
- Extended overload (2) to accept heterogeneous iterator+sentinel pairs (C++20 ranges support) in version 3.13.0.
|
||||
- Added `error_handler` parameter in version 3.13.0.
|
||||
- Report `start_array(0)` to a SAX handler for an optimized array of type `N` (`[$N#n`), whatever its count, in version
|
||||
3.13.0.
|
||||
- Limited the total number of elements of optimized arrays of `Z`, `T`, and `F` in one input in version 3.13.0.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -117,8 +117,5 @@ Linear in the size of the JSON value `j`.
|
||||
- Added `error_handler` parameter in version 3.13.0. Its default, `keep`, writes the bytes of a string or object key
|
||||
that is not valid UTF-8 unchanged, as before; `strict` (the default if
|
||||
[`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled) throws `type_error.316`.
|
||||
- Writes arrays of `Z`, `T`, or `F` without the `$` type annotation (`[#n Z Z ...`) once their elements in one call
|
||||
add up to more than 1,048,576, in version 3.13.0, so that `from_ubjson` can read the output back. Such output is
|
||||
larger: 270,000 rows of 100 `null` values take 26.8 MB instead of 1.35 MB.
|
||||
- Throws `type_error.321` for a discarded value since version 3.13.0; previously, a discarded value nested in an
|
||||
array or object was silently skipped, producing invalid UBJSON.
|
||||
@@ -122,18 +122,9 @@ The library uses the following mapping from JSON values types to UBJSON types ac
|
||||
already is the value. Its declared count is therefore the only thing that decides how much memory the receiving side
|
||||
allocates, and a handful of bytes can describe billions of elements. `from_ubjson` rejects such an array with
|
||||
[`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408) when the count exceeds 1,048,576
|
||||
(`1 << 20`), or when the counts of all such arrays in the input add up to more than 1,048,576 plus 4 for every byte
|
||||
read so far. `to_ubjson` therefore writes an array of these types in the counted but untyped form when it is longer
|
||||
than that, or when it would bring the total of the typed arrays written so far above 1,048,576: the `$` type marker
|
||||
is dropped, the `#` count is kept, and every element is written with its own marker (`[#l 1048577 Z Z ...`), so
|
||||
everything it produces can be read back. Only input from another encoder, or written by version 3.12.0 and earlier of
|
||||
this library, can exceed the limit: for example, 1,100 rows of 1,000 `null` values or 210,000 rows of 25, each with
|
||||
a `$Z` annotation. Version 3.12.0 writes such a row in 5 bytes (6 above 255 elements), so rows of 20 or fewer such
|
||||
values are never rejected. Objects and untyped counted arrays are not subject to this limit.
|
||||
|
||||
An optimized array of type `N` (no-op) is empty whatever its count is, because a no-op is not a value. Its count is
|
||||
not passed on: `sax_parse` reports `start_array(0)` (versions before 3.13.0 reported the declared count), and the DOM
|
||||
parser reserves nothing for it.
|
||||
(`1 << 20`), and `to_ubjson` writes longer arrays of these types in the counted but untyped form: the `$` type marker is
|
||||
dropped, the `#` count is kept, and every element is written with its own marker (`[#l 1048577 Z Z ...`), so any value
|
||||
it produces can be read back. Objects and untyped counted arrays are not subject to this limit.
|
||||
|
||||
!!! info "Binary values"
|
||||
|
||||
@@ -189,11 +180,10 @@ The library maps UBJSON types to JSON value types as follows:
|
||||
|
||||
Every well-formed UBJSON value can be converted to a JSON value, with these exceptions: a high-precision number
|
||||
outside the range of `number_float_t` ([`out_of_range.406`](../../home/exceptions.md#jsonexceptionout_of_range406)),
|
||||
optimized arrays of `Z`, `T`, or `F` with more elements than the limit allows (1,048,576 plus 4 per byte read),
|
||||
and a count that exceeds the capacity of the container
|
||||
([`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408)). High-precision numbers that do not
|
||||
fit an integer type are stored as floating-point numbers and may lose precision. Ill-formed input is rejected with a
|
||||
parse error.
|
||||
an optimized array of `Z`, `T`, or `F` with more than 1,048,576 elements, and a count that exceeds the capacity of the
|
||||
container ([`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408)). High-precision numbers that
|
||||
do not fit an integer type are stored as floating-point numbers and may lose precision. Ill-formed input is rejected
|
||||
with a parse error.
|
||||
|
||||
!!! info "Duplicate object keys"
|
||||
|
||||
|
||||
@@ -9,7 +9,19 @@ Importing the module instead of including the header reduces the compile time of
|
||||
## Requirements
|
||||
The `nlohmann.json` module requires that the build system is configured to build and resolve modules when imported. Obviously, as modules were introduced in C++20, this feature can only be used in C++20 and subsequent versions.
|
||||
|
||||
To enable building the `nlohmann.json` module (which is not done by default), the macro `NLOHMANN_JSON_BUILD_MODULES` must be passed to the build system.
|
||||
To enable building the `nlohmann.json` module (which is not done by default), set the CMake option
|
||||
[`NLOHMANN_JSON_BUILD_MODULES`](../integration/cmake.md#nlohmann_json_build_modules) and link the
|
||||
`nlohmann_json_modules` target.
|
||||
|
||||
With CMake, building the module needs:
|
||||
|
||||
- CMake 3.28 or newer, and
|
||||
- a generator that scans for modules: Ninja (1.11 or newer), Ninja Multi-Config, or Visual Studio 2022 or newer.
|
||||
|
||||
The example below also uses `import std;`. CMake supports it without experimental opt-in since version 4.5, and then
|
||||
only with the Ninja generators and these toolchains: Clang 18.1.2 or newer (with libc++ or libstdc++), MSVC toolset 14.36
|
||||
(Visual Studio 17.6) or newer, and GCC 15 or newer (GCC 16 on macOS). With older CMake versions, `import std;` needs
|
||||
CMake's version-specific experimental opt-in.
|
||||
|
||||
## Example
|
||||
When using modules rather than headers, the previous example for creating a `json` object through a JSON file, would instead be:
|
||||
@@ -67,7 +79,7 @@ and should not be used directly:
|
||||
|
||||
## Known issues
|
||||
|
||||
C++20 modules support is exercised in CI against current GCC and Clang on Ubuntu, and the default MSVC toolset on Windows Server 2022 — there is no documented minimum compiler version, unlike feature-test-macro-gated features such as [`JSON_HAS_RANGES`](../api/macros/json_has_ranges.md).
|
||||
C++20 modules support is exercised in CI with CMake 4.5 and `import std;` against current GCC and Clang on Ubuntu, and the default MSVC toolset on Windows Server 2022 — there is no documented minimum compiler version, unlike feature-test-macro-gated features such as [`JSON_HAS_RANGES`](../api/macros/json_has_ranges.md).
|
||||
|
||||
!!! info "Known compiler issues"
|
||||
|
||||
|
||||
@@ -94,22 +94,10 @@ For the binary formats, an announced size is never trusted outright:
|
||||
(reported as a parse error) instead of triggering an oversized allocation.
|
||||
- When an array announces its number of elements and the array container supports `reserve()` (as `#!cpp std::vector`,
|
||||
the default, does), the library reserves storage for at most 16384 of them upfront, regardless of how large the
|
||||
announced count is; further elements still grow the container normally as they are read. A truncated input whose
|
||||
count is larger than its remaining bytes therefore reserves at most that much before the parse error is reported.
|
||||
Every array element takes at least one byte of input, except in the [UBJSON](../binary_formats/ubjson.md) arrays of
|
||||
type `Z`, `T` or `F` described below.
|
||||
announced count is; further elements still grow the container normally as they are read.
|
||||
- An announced array or object size that exceeds what the target container could ever hold (its `max_size()`) is
|
||||
rejected immediately as [`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408), without
|
||||
attempting to allocate anything.
|
||||
- A UBJSON array of the no-op type (`[$N#<n>`) is empty whatever count it declares: a SAX handler is told
|
||||
`start_array(0)` and the DOM parser reserves nothing.
|
||||
- A UBJSON array of type `Z`, `T` or `F` has no payload, so its announced count is not bounded by the input. One array
|
||||
may announce at most 1,048,576 elements, and all such arrays of one input together may contain at most 1,048,576
|
||||
elements plus 4 for every byte read so far (checked when each array's header has been read); beyond that the input is
|
||||
rejected as [`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408). For a DOM that bounds the memory these
|
||||
arrays can need to about 80 bytes per byte of input plus about 33 MB for the first 1,048,576 elements; a SAX handler
|
||||
receives at most that many events. Every other optimized array element, and every UBJSON object member (it has a
|
||||
key), takes at least one byte of input.
|
||||
|
||||
## Strings
|
||||
|
||||
|
||||
@@ -1050,17 +1050,11 @@ The size of an array or object in a [binary format](../features/binary_formats/i
|
||||
the size following `#` for [UBJSON](../features/binary_formats/ubjson.md)/[BJData](../features/binary_formats/bjdata.md),
|
||||
or the encoded length for [CBOR](../features/binary_formats/cbor.md).
|
||||
|
||||
The exception is also thrown for [UBJSON](../features/binary_formats/ubjson.md) arrays of a type that is encoded by
|
||||
its marker alone (`Z`, `T` or `F`). Such an array has no payload, so its count alone decides how much memory is
|
||||
allocated, and a handful of bytes would otherwise describe billions of values. It is thrown if the declared count of one
|
||||
array exceeds 1,048,576 (`1 << 20`), and if the counts of all such arrays read so far in one input add up to more than
|
||||
1,048,576 plus 4 for every byte of the input read when the header of the last array has been read.
|
||||
[`to_ubjson`](../api/basic_json/to_ubjson.md) writes an array of these types without the `$` type annotation (the `#`
|
||||
count and one marker per element are kept) when it is longer, or when it would bring the total of the typed arrays
|
||||
written so far above 1,048,576, so everything it produces can be read back. Only input written by another encoder, or
|
||||
by version 3.12.0 and earlier of this library, can exceed the limit: for example, 1,100 rows of 1,000 `null` values or
|
||||
210,000 rows of 25, each with a `$Z` annotation. Version 3.12.0 writes such a row in 5 bytes (6 above 255 elements),
|
||||
so rows of 20 or fewer such values are never rejected.
|
||||
The exception is also thrown for a [UBJSON](../features/binary_formats/ubjson.md) array of a type that is encoded by its
|
||||
marker alone (`Z`, `T` or `F`) whose declared count exceeds 1,048,576 (`1 << 20`). Such an array has no payload, so its
|
||||
count alone decides how much memory is allocated, and a handful of bytes would otherwise describe billions of values.
|
||||
[`to_ubjson`](../api/basic_json/to_ubjson.md) writes longer arrays of these types without the `$` type annotation (the `#`
|
||||
count and one marker per element are kept), so any value it produces can still be read back.
|
||||
|
||||
!!! failure "Example messages"
|
||||
|
||||
@@ -1076,9 +1070,6 @@ so rows of 20 or fewer such values are never rejected.
|
||||
```
|
||||
[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size
|
||||
```
|
||||
```
|
||||
[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive number of elements without payload
|
||||
```
|
||||
|
||||
### json.exception.out_of_range.409
|
||||
|
||||
|
||||
@@ -269,6 +269,9 @@ target_link_libraries(myproject PRIVATE nlohmann_json_modules)
|
||||
target_compile_definitions(myproject PRIVATE NLOHMANN_JSON_BUILD_MODULES)
|
||||
```
|
||||
|
||||
If `main.cpp` also uses `import std;`, the project needs CMake 4.5 or newer and a Ninja generator; see
|
||||
[Modules](../features/modules.md#requirements) for the supported toolchains.
|
||||
|
||||
## See also
|
||||
|
||||
- [Macros](../api/macros/index.md) - reference of all macros
|
||||
|
||||
@@ -73,46 +73,13 @@ the input.
|
||||
|
||||
This is a sanity bound rather than a security boundary, and it is far above
|
||||
any container met in practice. @ref binary_writer falls back to the
|
||||
unoptimized encoding for longer containers, and for containers that together
|
||||
with the ones before them would exceed @ref valueless_elements_base, so that a
|
||||
value serialized by this library can always be read back.
|
||||
unoptimized encoding for longer containers, so that a value serialized by
|
||||
this library can always be read back.
|
||||
|
||||
@sa https://github.com/nlohmann/json/issues/2793
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 20;
|
||||
|
||||
/*!
|
||||
@brief number of elements of valueless UBJSON containers accepted on top of
|
||||
@ref valueless_elements_per_byte
|
||||
|
||||
The limit @ref max_valueless_container_size applies to each container on its
|
||||
own, so on its own it lets 9 bytes announce 1048576 values, and every further
|
||||
9 bytes another 1048576. The elements of all containers of a valueless type
|
||||
in one input are therefore added up, and the sum must stay below this base
|
||||
plus @ref valueless_elements_per_byte for every byte read so far. The base is
|
||||
the per-container limit, so a container that was accepted on its own before
|
||||
the sum was introduced is still accepted at the start of an input.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_base = max_valueless_container_size;
|
||||
|
||||
/*!
|
||||
@brief number of elements of valueless UBJSON containers accepted per byte of
|
||||
input, in addition to @ref valueless_elements_base
|
||||
|
||||
An element of a value that has a payload costs at least one byte of input.
|
||||
Valueless elements are accepted at a rate of 4 per byte. A value takes 16
|
||||
bytes of memory in a DOM, so these arrays add about 80 bytes of memory per
|
||||
byte of input (measured: 77; one `Z` per byte needs about 32), beyond what the
|
||||
same bytes cost anyway, plus the base. This bounds the arrays of valueless
|
||||
type, not the memory of a whole document. Containers written by
|
||||
@ref binary_writer never need more than the base, because it writes an array
|
||||
in the unoptimized form once the typed arrays written so far and this one add
|
||||
up to more than that. The rate matters for input written by other encoders and
|
||||
by versions before 3.13.0 only; in the data this was measured on, no input has
|
||||
more than 0.17 elements per byte.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_per_byte = 4;
|
||||
|
||||
///////////////////
|
||||
// binary reader //
|
||||
///////////////////
|
||||
@@ -3733,37 +3700,6 @@ class binary_reader
|
||||
return emit_unsigned(number);
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief add the elements of a container of a valueless type to the total of
|
||||
the input and check the total against the input read so far
|
||||
|
||||
A container of type 'Z', 'T' or 'F' has no payload, so its elements are the
|
||||
only ones for which the input does not bound the count. The check is made
|
||||
once per container, not per element.
|
||||
|
||||
@param[in] count number of elements the container declares; at most
|
||||
@ref max_valueless_container_size
|
||||
@return false if the total is more than @ref valueless_elements_base plus
|
||||
@ref valueless_elements_per_byte for every byte read so far; the
|
||||
total is not changed then
|
||||
*/
|
||||
bool charge_valueless_elements(const std::size_t count) noexcept
|
||||
{
|
||||
// the limit saturates instead of overflowing when size_t is 32 bits
|
||||
// wide and a very large input has been read; valueless_elements
|
||||
// never exceeds the limit, so the difference cannot underflow
|
||||
constexpr std::size_t max_size = (std::numeric_limits<std::size_t>::max)();
|
||||
const std::size_t limit = chars_read <= (max_size - valueless_elements_base) / valueless_elements_per_byte
|
||||
? valueless_elements_base + (valueless_elements_per_byte * chars_read)
|
||||
: max_size;
|
||||
if (JSON_HEDLEY_UNLIKELY(count > limit - valueless_elements))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
valueless_elements += count;
|
||||
return true;
|
||||
}
|
||||
|
||||
/*!
|
||||
@return whether array creation completed
|
||||
*/
|
||||
@@ -3849,27 +3785,24 @@ class binary_reader
|
||||
// declared count alone decides how much is allocated; the check is
|
||||
// made before the start event so that no container is opened that
|
||||
// is then abandoned. See @ref max_valueless_container_size.
|
||||
if (JSON_HEDLEY_UNLIKELY(size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F'))
|
||||
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
|
||||
&& size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
|
||||
}
|
||||
if (JSON_HEDLEY_UNLIKELY(!charge_valueless_elements(size_and_type.first)))
|
||||
{
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive number of elements without payload", "size");
|
||||
}
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
|
||||
}
|
||||
|
||||
// a no-op is not a value, so an array of them is empty whatever
|
||||
// count it declares: the SAX parser is told so, instead of being
|
||||
// made to reserve storage for a count that no input backs
|
||||
const std::size_t announced = size_and_type.second == 'N' ? 0 : size_and_type.first;
|
||||
if (JSON_HEDLEY_UNLIKELY(!enter_array(announced, size_and_type.second)))
|
||||
if (JSON_HEDLEY_UNLIKELY(!enter_array(size_and_type.first, size_and_type.second)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (size_and_type.second == 'N')
|
||||
{
|
||||
// a no-op is not a value, so a container of them holds none;
|
||||
// the declared size has already been passed to the SAX parser
|
||||
container_stack.back().remaining = 0;
|
||||
}
|
||||
|
||||
return size_and_type.second == 0
|
||||
|| parse_ubjson_typed_run(container_stack.back().remaining, size_and_type.second, std::integral_constant<bool, bulk_scan> {});
|
||||
}
|
||||
@@ -5181,10 +5114,6 @@ class binary_reader
|
||||
/// the number of characters read
|
||||
std::size_t chars_read = 0;
|
||||
|
||||
/// UBJSON: the sum of the element counts of the containers of a valueless
|
||||
/// type read so far; see @ref charge_valueless_elements
|
||||
std::size_t valueless_elements = 0;
|
||||
|
||||
/// whether we can assume little endianness
|
||||
const bool is_little_endian = little_endianness();
|
||||
|
||||
|
||||
@@ -1169,14 +1169,6 @@ class binary_writer
|
||||
write_container_iterative<msgpack_walk>(root);
|
||||
}
|
||||
|
||||
// a function, not an inline condition: for an object the type is never
|
||||
// valueless and MSVC would warn about a constant expression (C4127)
|
||||
static constexpr bool valueless_array_fits(const bool valueless_type, const std::size_t size,
|
||||
const std::size_t written) noexcept
|
||||
{
|
||||
return !valueless_type || size <= detail::valueless_elements_base - written;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief write the start of an array (@a IsArray) or object: its opening
|
||||
marker, the optimized type, and the count
|
||||
@@ -1212,27 +1204,20 @@ class binary_writer
|
||||
|
||||
// an optimized array of a valueless type carries no payload, so a
|
||||
// reader has nothing but the declared count to bound the allocation
|
||||
// by. It refuses one array of more than max_valueless_container_size
|
||||
// elements, and all such arrays of one input together when they add
|
||||
// up to more than valueless_elements_base plus a number per byte
|
||||
// read. Write the unoptimized form, at one byte per element, for
|
||||
// an array that would exceed the base with the arrays written so
|
||||
// far, so that the result can be read back: the limit of a reader
|
||||
// is never below the base. Objects are not affected: every element
|
||||
// is preceded by its key.
|
||||
if (same_prefix && !(use_bjdata && is_bjdata_excluded_type_marker(first_prefix)))
|
||||
// by and refuses an excessive one. Write the unoptimized form for
|
||||
// those, at one byte per element, so the result can be read back.
|
||||
// Objects are not affected: every element is preceded by its key.
|
||||
const bool valueless_type = (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
const bool excessive_valueless = IsArray
|
||||
&& valueless_type
|
||||
&& size > detail::max_valueless_container_size;
|
||||
|
||||
if (same_prefix && !excessive_valueless
|
||||
&& !(use_bjdata && is_bjdata_excluded_type_marker(first_prefix)))
|
||||
{
|
||||
const bool valueless_type = IsArray && (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
if (valueless_array_fits(valueless_type, size, valueless_elements_written))
|
||||
{
|
||||
prefix_required = false;
|
||||
oa.write_character(to_char_type('$'));
|
||||
oa.write_character(first_prefix);
|
||||
if (valueless_type)
|
||||
{
|
||||
valueless_elements_written += size;
|
||||
}
|
||||
}
|
||||
prefix_required = false;
|
||||
oa.write_character(to_char_type('$'));
|
||||
oa.write_character(first_prefix);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5456,10 +5441,6 @@ class binary_writer
|
||||
/// how to treat a string value or object key that is not valid UTF-8
|
||||
/// (CBOR, MessagePack, UBJSON, BJData, and BSON; not BON8)
|
||||
const error_handler_t error_handler = binary_writer_default_error_handler();
|
||||
|
||||
/// UBJSON: the number of elements written so far in optimized arrays of a
|
||||
/// valueless type, which a reader adds up and bounds
|
||||
std::size_t valueless_elements_written = 0;
|
||||
};
|
||||
|
||||
} // namespace detail
|
||||
|
||||
Generated
+26
-116
@@ -18464,46 +18464,13 @@ the input.
|
||||
|
||||
This is a sanity bound rather than a security boundary, and it is far above
|
||||
any container met in practice. @ref binary_writer falls back to the
|
||||
unoptimized encoding for longer containers, and for containers that together
|
||||
with the ones before them would exceed @ref valueless_elements_base, so that a
|
||||
value serialized by this library can always be read back.
|
||||
unoptimized encoding for longer containers, so that a value serialized by
|
||||
this library can always be read back.
|
||||
|
||||
@sa https://github.com/nlohmann/json/issues/2793
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t max_valueless_container_size = 1 << 20;
|
||||
|
||||
/*!
|
||||
@brief number of elements of valueless UBJSON containers accepted on top of
|
||||
@ref valueless_elements_per_byte
|
||||
|
||||
The limit @ref max_valueless_container_size applies to each container on its
|
||||
own, so on its own it lets 9 bytes announce 1048576 values, and every further
|
||||
9 bytes another 1048576. The elements of all containers of a valueless type
|
||||
in one input are therefore added up, and the sum must stay below this base
|
||||
plus @ref valueless_elements_per_byte for every byte read so far. The base is
|
||||
the per-container limit, so a container that was accepted on its own before
|
||||
the sum was introduced is still accepted at the start of an input.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_base = max_valueless_container_size;
|
||||
|
||||
/*!
|
||||
@brief number of elements of valueless UBJSON containers accepted per byte of
|
||||
input, in addition to @ref valueless_elements_base
|
||||
|
||||
An element of a value that has a payload costs at least one byte of input.
|
||||
Valueless elements are accepted at a rate of 4 per byte. A value takes 16
|
||||
bytes of memory in a DOM, so these arrays add about 80 bytes of memory per
|
||||
byte of input (measured: 77; one `Z` per byte needs about 32), beyond what the
|
||||
same bytes cost anyway, plus the base. This bounds the arrays of valueless
|
||||
type, not the memory of a whole document. Containers written by
|
||||
@ref binary_writer never need more than the base, because it writes an array
|
||||
in the unoptimized form once the typed arrays written so far and this one add
|
||||
up to more than that. The rate matters for input written by other encoders and
|
||||
by versions before 3.13.0 only; in the data this was measured on, no input has
|
||||
more than 0.17 elements per byte.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_per_byte = 4;
|
||||
|
||||
///////////////////
|
||||
// binary reader //
|
||||
///////////////////
|
||||
@@ -22124,37 +22091,6 @@ class binary_reader
|
||||
return emit_unsigned(number);
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief add the elements of a container of a valueless type to the total of
|
||||
the input and check the total against the input read so far
|
||||
|
||||
A container of type 'Z', 'T' or 'F' has no payload, so its elements are the
|
||||
only ones for which the input does not bound the count. The check is made
|
||||
once per container, not per element.
|
||||
|
||||
@param[in] count number of elements the container declares; at most
|
||||
@ref max_valueless_container_size
|
||||
@return false if the total is more than @ref valueless_elements_base plus
|
||||
@ref valueless_elements_per_byte for every byte read so far; the
|
||||
total is not changed then
|
||||
*/
|
||||
bool charge_valueless_elements(const std::size_t count) noexcept
|
||||
{
|
||||
// the limit saturates instead of overflowing when size_t is 32 bits
|
||||
// wide and a very large input has been read; valueless_elements
|
||||
// never exceeds the limit, so the difference cannot underflow
|
||||
constexpr std::size_t max_size = (std::numeric_limits<std::size_t>::max)();
|
||||
const std::size_t limit = chars_read <= (max_size - valueless_elements_base) / valueless_elements_per_byte
|
||||
? valueless_elements_base + (valueless_elements_per_byte * chars_read)
|
||||
: max_size;
|
||||
if (JSON_HEDLEY_UNLIKELY(count > limit - valueless_elements))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
valueless_elements += count;
|
||||
return true;
|
||||
}
|
||||
|
||||
/*!
|
||||
@return whether array creation completed
|
||||
*/
|
||||
@@ -22240,27 +22176,24 @@ class binary_reader
|
||||
// declared count alone decides how much is allocated; the check is
|
||||
// made before the start event so that no container is opened that
|
||||
// is then abandoned. See @ref max_valueless_container_size.
|
||||
if (JSON_HEDLEY_UNLIKELY(size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F'))
|
||||
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
|
||||
&& size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(size_and_type.first > max_valueless_container_size))
|
||||
{
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
|
||||
}
|
||||
if (JSON_HEDLEY_UNLIKELY(!charge_valueless_elements(size_and_type.first)))
|
||||
{
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive number of elements without payload", "size");
|
||||
}
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
|
||||
}
|
||||
|
||||
// a no-op is not a value, so an array of them is empty whatever
|
||||
// count it declares: the SAX parser is told so, instead of being
|
||||
// made to reserve storage for a count that no input backs
|
||||
const std::size_t announced = size_and_type.second == 'N' ? 0 : size_and_type.first;
|
||||
if (JSON_HEDLEY_UNLIKELY(!enter_array(announced, size_and_type.second)))
|
||||
if (JSON_HEDLEY_UNLIKELY(!enter_array(size_and_type.first, size_and_type.second)))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
if (size_and_type.second == 'N')
|
||||
{
|
||||
// a no-op is not a value, so a container of them holds none;
|
||||
// the declared size has already been passed to the SAX parser
|
||||
container_stack.back().remaining = 0;
|
||||
}
|
||||
|
||||
return size_and_type.second == 0
|
||||
|| parse_ubjson_typed_run(container_stack.back().remaining, size_and_type.second, std::integral_constant<bool, bulk_scan> {});
|
||||
}
|
||||
@@ -23572,10 +23505,6 @@ class binary_reader
|
||||
/// the number of characters read
|
||||
std::size_t chars_read = 0;
|
||||
|
||||
/// UBJSON: the sum of the element counts of the containers of a valueless
|
||||
/// type read so far; see @ref charge_valueless_elements
|
||||
std::size_t valueless_elements = 0;
|
||||
|
||||
/// whether we can assume little endianness
|
||||
const bool is_little_endian = little_endianness();
|
||||
|
||||
@@ -30727,14 +30656,6 @@ class binary_writer
|
||||
write_container_iterative<msgpack_walk>(root);
|
||||
}
|
||||
|
||||
// a function, not an inline condition: for an object the type is never
|
||||
// valueless and MSVC would warn about a constant expression (C4127)
|
||||
static constexpr bool valueless_array_fits(const bool valueless_type, const std::size_t size,
|
||||
const std::size_t written) noexcept
|
||||
{
|
||||
return !valueless_type || size <= detail::valueless_elements_base - written;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief write the start of an array (@a IsArray) or object: its opening
|
||||
marker, the optimized type, and the count
|
||||
@@ -30770,27 +30691,20 @@ class binary_writer
|
||||
|
||||
// an optimized array of a valueless type carries no payload, so a
|
||||
// reader has nothing but the declared count to bound the allocation
|
||||
// by. It refuses one array of more than max_valueless_container_size
|
||||
// elements, and all such arrays of one input together when they add
|
||||
// up to more than valueless_elements_base plus a number per byte
|
||||
// read. Write the unoptimized form, at one byte per element, for
|
||||
// an array that would exceed the base with the arrays written so
|
||||
// far, so that the result can be read back: the limit of a reader
|
||||
// is never below the base. Objects are not affected: every element
|
||||
// is preceded by its key.
|
||||
if (same_prefix && !(use_bjdata && is_bjdata_excluded_type_marker(first_prefix)))
|
||||
// by and refuses an excessive one. Write the unoptimized form for
|
||||
// those, at one byte per element, so the result can be read back.
|
||||
// Objects are not affected: every element is preceded by its key.
|
||||
const bool valueless_type = (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
const bool excessive_valueless = IsArray
|
||||
&& valueless_type
|
||||
&& size > detail::max_valueless_container_size;
|
||||
|
||||
if (same_prefix && !excessive_valueless
|
||||
&& !(use_bjdata && is_bjdata_excluded_type_marker(first_prefix)))
|
||||
{
|
||||
const bool valueless_type = IsArray && (first_prefix == 'Z' || first_prefix == 'T' || first_prefix == 'F');
|
||||
if (valueless_array_fits(valueless_type, size, valueless_elements_written))
|
||||
{
|
||||
prefix_required = false;
|
||||
oa.write_character(to_char_type('$'));
|
||||
oa.write_character(first_prefix);
|
||||
if (valueless_type)
|
||||
{
|
||||
valueless_elements_written += size;
|
||||
}
|
||||
}
|
||||
prefix_required = false;
|
||||
oa.write_character(to_char_type('$'));
|
||||
oa.write_character(first_prefix);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -35014,10 +34928,6 @@ class binary_writer
|
||||
/// how to treat a string value or object key that is not valid UTF-8
|
||||
/// (CBOR, MessagePack, UBJSON, BJData, and BSON; not BON8)
|
||||
const error_handler_t error_handler = binary_writer_default_error_handler();
|
||||
|
||||
/// UBJSON: the number of elements written so far in optimized arrays of a
|
||||
/// valueless type, which a reader adds up and bounds
|
||||
std::size_t valueless_elements_written = 0;
|
||||
};
|
||||
|
||||
} // namespace detail
|
||||
|
||||
@@ -1,11 +1,6 @@
|
||||
cmake_minimum_required(VERSION 3.30)
|
||||
|
||||
# `import std;` (used by main.cpp) needs CMake's experimental C++ import-std
|
||||
# support. The accepted token is CMake-version-specific; this value matches the
|
||||
# CMake version pinned in the ci_module_cpp20 CI jobs (4.3.x). If that pin is
|
||||
# bumped, this token must be updated to match (configuration fails loudly
|
||||
# otherwise).
|
||||
set(CMAKE_EXPERIMENTAL_CXX_IMPORT_STD "451f2fe2-a8a2-47c3-bc32-94786d8fc91b")
|
||||
# `import std;` (used by main.cpp) is supported without experimental opt-in
|
||||
# since CMake 4.5: it is available to every target that scans for C++ modules.
|
||||
cmake_minimum_required(VERSION 4.5)
|
||||
|
||||
project(json_test CXX)
|
||||
|
||||
@@ -13,7 +8,6 @@ project(json_test CXX)
|
||||
set(CMAKE_CXX_STANDARD 23)
|
||||
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
||||
set(CMAKE_CXX_EXTENSIONS OFF)
|
||||
set(CMAKE_CXX_MODULE_STD ON)
|
||||
|
||||
set(NLOHMANN_JSON_BUILD_MODULES ON CACHE BOOL "Enable nlohmann.json module support")
|
||||
|
||||
|
||||
@@ -17,8 +17,8 @@ using namespace nlohmann::literals;
|
||||
// Standard-library facilities are pulled in via `import std;` rather than
|
||||
// textual `#include`s: mixing `import` with textual standard headers does not
|
||||
// compile under GCC's C++20 modules implementation, whereas `import std;` works
|
||||
// across GCC, Clang, and MSVC. This requires C++23 and CMake's (experimental)
|
||||
// import-std support; see CMakeLists.txt.
|
||||
// across GCC, Clang, and MSVC. This requires C++23 and CMake 4.5 or newer;
|
||||
// see CMakeLists.txt.
|
||||
int main()
|
||||
{
|
||||
// basic_json / json: parsing and value access
|
||||
|
||||
@@ -19,12 +19,8 @@
|
||||
#include <nlohmann/json.hpp>
|
||||
using nlohmann::json;
|
||||
|
||||
#include <cstdio>
|
||||
#include <iostream>
|
||||
#include <sstream>
|
||||
#include <utility>
|
||||
#include <fstream>
|
||||
#include <limits>
|
||||
#include <list>
|
||||
#include <set>
|
||||
#include "make_test_data_available.hpp"
|
||||
@@ -2440,341 +2436,6 @@ TEST_CASE("UBJSON optimized arrays of a valueless type are bounded")
|
||||
}
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
/// SAX consumer that counts the values and keeps the id of a parse error
|
||||
struct ValuelessEventCounter : public nlohmann::json_sax<json>
|
||||
{
|
||||
bool null() override
|
||||
{
|
||||
return ++values < stop_after;
|
||||
}
|
||||
bool boolean(bool /*val*/) override
|
||||
{
|
||||
return ++values < stop_after;
|
||||
}
|
||||
bool number_integer(json::number_integer_t /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool number_unsigned(json::number_unsigned_t /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool number_float(json::number_float_t /*val*/, const std::string& /*s*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool string(std::string& /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool binary(json::binary_t& /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool start_object(std::size_t /*elements*/) override
|
||||
{
|
||||
return true;
|
||||
}
|
||||
bool key(std::string& /*val*/) override
|
||||
{
|
||||
return true;
|
||||
}
|
||||
bool end_object() override
|
||||
{
|
||||
return true;
|
||||
}
|
||||
bool start_array(std::size_t /*elements*/) override
|
||||
{
|
||||
return true;
|
||||
}
|
||||
bool end_array() override
|
||||
{
|
||||
return true;
|
||||
}
|
||||
bool parse_error(std::size_t /*position*/, const std::string& /*last_token*/, const json::exception& ex) override
|
||||
{
|
||||
error_id = ex.id;
|
||||
return false;
|
||||
}
|
||||
|
||||
/// the handler refuses the value that makes this many
|
||||
std::size_t stop_after = (std::numeric_limits<std::size_t>::max)();
|
||||
std::size_t values = 0;
|
||||
int error_id = 0;
|
||||
};
|
||||
|
||||
/// appends `[$<marker>#l<count>` (nine bytes) to @a v
|
||||
void append_valueless_array(std::vector<std::uint8_t>& v, const char marker, const std::uint32_t count)
|
||||
{
|
||||
v.push_back('[');
|
||||
v.push_back('$');
|
||||
v.push_back(static_cast<std::uint8_t>(marker));
|
||||
v.push_back('#');
|
||||
v.push_back('l');
|
||||
v.push_back(static_cast<std::uint8_t>(count >> 24));
|
||||
v.push_back(static_cast<std::uint8_t>(count >> 16));
|
||||
v.push_back(static_cast<std::uint8_t>(count >> 8));
|
||||
v.push_back(static_cast<std::uint8_t>(count));
|
||||
}
|
||||
|
||||
/// `[` followed by one `[$<marker>#l<count>` per entry of @a counts and `]`
|
||||
std::vector<std::uint8_t> valueless_arrays(const char marker, const std::vector<std::uint32_t>& counts)
|
||||
{
|
||||
std::vector<std::uint8_t> v = {'['};
|
||||
for (const auto count : counts)
|
||||
{
|
||||
append_valueless_array(v, marker, count);
|
||||
}
|
||||
v.push_back(']');
|
||||
return v;
|
||||
}
|
||||
} // namespace
|
||||
|
||||
TEST_CASE("UBJSON the valueless elements of a whole input are bounded")
|
||||
{
|
||||
// The per-container limit alone let nine bytes (`[$Z#l` and a count of
|
||||
// 1048576) announce a million values, and every further nine bytes another
|
||||
// million. The elements of all containers of type 'Z', 'T' or 'F' in one
|
||||
// input are now added up: they may not exceed 1048576 plus 4 for every
|
||||
// byte read when the container's header has been read.
|
||||
//
|
||||
// The tests count events with a SAX handler where they can: building and
|
||||
// comparing values of a million elements is what makes them slow under
|
||||
// Valgrind, so there is one rejection and one round trip with a DOM.
|
||||
json _;
|
||||
const char* const budget_message = "[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive number of elements without payload";
|
||||
|
||||
// two arrays that exceed the limit: the second one, with its header read
|
||||
// at byte 19, may hold 4 * 19 = 76 values on top of the base of 1048576
|
||||
const std::uint32_t over_first = 524288;
|
||||
const std::uint32_t over_second = 1048576 + 76 - over_first + 1;
|
||||
|
||||
SECTION("the input of the original report is rejected")
|
||||
{
|
||||
// 362 bytes (40 arrays of 1048576 values) used to allocate 661 MB; the
|
||||
// second array is the one that is refused
|
||||
const auto input = valueless_arrays('Z', {over_first, over_second});
|
||||
CHECK_THROWS_WITH_AS(_ = json::from_ubjson(input), budget_message, json::out_of_range&);
|
||||
}
|
||||
|
||||
SECTION("every input adapter applies the budget")
|
||||
{
|
||||
const auto input = valueless_arrays('Z', {over_first, over_second});
|
||||
|
||||
// stream; not strict, which does not matter
|
||||
std::stringstream stream;
|
||||
stream.write(reinterpret_cast<const char*>(input.data()), static_cast<std::streamsize>(input.size()));
|
||||
ValuelessEventCounter from_stream;
|
||||
CHECK(!json::sax_parse(stream, &from_stream, json::input_format_t::ubjson, false));
|
||||
CHECK(from_stream.error_id == 408);
|
||||
|
||||
// a container that is not contiguous; the counts of arrays of
|
||||
// different types are added up
|
||||
std::vector<std::uint8_t> mixed = {'['};
|
||||
append_valueless_array(mixed, 'T', over_first);
|
||||
append_valueless_array(mixed, 'F', over_second);
|
||||
mixed.push_back(']');
|
||||
const std::list<std::uint8_t> as_list(mixed.begin(), mixed.end());
|
||||
ValuelessEventCounter from_list;
|
||||
CHECK(!json::sax_parse(as_list.begin(), as_list.end(), &from_list, json::input_format_t::ubjson));
|
||||
CHECK(from_list.error_id == 408);
|
||||
CHECK(from_list.values == over_first);
|
||||
|
||||
// FILE*
|
||||
FILE* const file = std::tmpfile(); // NOLINT(cppcoreguidelines-owning-memory)
|
||||
REQUIRE(file != nullptr);
|
||||
CHECK(std::fwrite(input.data(), 1, input.size(), file) == input.size());
|
||||
CHECK(std::fseek(file, 0, SEEK_SET) == 0);
|
||||
ValuelessEventCounter from_file;
|
||||
CHECK(!json::sax_parse(file, &from_file, json::input_format_t::ubjson));
|
||||
CHECK(from_file.error_id == 408);
|
||||
std::fclose(file); // NOLINT(cert-err33-c,cppcoreguidelines-owning-memory)
|
||||
}
|
||||
|
||||
SECTION("the limit is exact and the bytes read raise it")
|
||||
{
|
||||
// [ [$Z#l 524288] [$U#l 4096 + 4096 bytes] [$Z#l count] ]: chars_read
|
||||
// is 1 + 9 + (9 + 4096) + 9 = 4124 when the last header has been read,
|
||||
// so the last array may hold 4 * 4124 = 16496 values on top of the
|
||||
// base of 1048576 less the 524288 of the first array
|
||||
const std::uint32_t last_allowed = 1048576 + 16496 - 524288;
|
||||
for (const std::uint32_t count :
|
||||
{
|
||||
last_allowed, last_allowed + 1
|
||||
})
|
||||
{
|
||||
CAPTURE(count)
|
||||
std::vector<std::uint8_t> input = {'['};
|
||||
append_valueless_array(input, 'Z', 524288);
|
||||
input.insert(input.end(), {'[', '$', 'U', '#', 'l', 0x00, 0x00, 0x10, 0x00});
|
||||
input.insert(input.end(), 4096, 0x01);
|
||||
append_valueless_array(input, 'Z', count);
|
||||
input.push_back(']');
|
||||
ValuelessEventCounter sax;
|
||||
const bool accepted = count == last_allowed;
|
||||
CHECK(json::sax_parse(input, &sax, json::input_format_t::ubjson) == accepted);
|
||||
CHECK(sax.error_id == (accepted ? 0 : 408));
|
||||
CHECK(sax.values == 524288u + 4096u + (accepted ? count : 0u));
|
||||
}
|
||||
|
||||
// an array of 1048576 values on its own is accepted as before
|
||||
const std::vector<std::uint8_t> single = {'[', '$', 'Z', '#', 'l', 0x00, 0x10, 0x00, 0x00};
|
||||
// (the handler ends the parse at the first value, so that the million
|
||||
// values are not read)
|
||||
ValuelessEventCounter sax;
|
||||
sax.stop_after = 1;
|
||||
CHECK(!json::sax_parse(single, &sax, json::input_format_t::ubjson));
|
||||
CHECK(sax.error_id == 0);
|
||||
CHECK(sax.values == 1);
|
||||
}
|
||||
|
||||
SECTION("to_ubjson writes the typed form up to the base only")
|
||||
{
|
||||
// 1048 rows of 1000 values fit under the base of 1048576, the 1049th
|
||||
// would not: its elements are written one by one. Written all typed,
|
||||
// 1100 rows of 6 bytes would be refused by a reader (1075 rows are the
|
||||
// most it accepts). The rows hold null, true or false, and the
|
||||
// fallback does not depend on which
|
||||
std::vector<std::uint8_t> encoded;
|
||||
{
|
||||
json table = json::array();
|
||||
for (int row = 0; row < 1100; ++row)
|
||||
{
|
||||
const json cell = row % 3 == 0 ? json(nullptr) : json(row % 3 == 1);
|
||||
table.push_back(json(1000, cell));
|
||||
}
|
||||
encoded = json::to_ubjson(table, true, true);
|
||||
}
|
||||
// outer array: `[$[#I` and the count (7 bytes), then 1048 typed rows of 6
|
||||
// bytes (`$Z#I` and two bytes) and 52 rows of `#I`, two bytes, and 1000 `Z`
|
||||
CHECK(encoded.size() == 7 + (1048 * 6) + (52 * (4 + 1000)));
|
||||
|
||||
// the output is read back
|
||||
ValuelessEventCounter sax;
|
||||
CHECK(json::sax_parse(encoded, &sax, json::input_format_t::ubjson));
|
||||
CHECK(sax.error_id == 0);
|
||||
CHECK(sax.values == 1100u * 1000u);
|
||||
}
|
||||
|
||||
SECTION("BJData is not affected")
|
||||
{
|
||||
// BJData has no optimized arrays of these types, and the writer does
|
||||
// not charge them
|
||||
json table = json::array();
|
||||
for (int row = 0; row < 3; ++row)
|
||||
{
|
||||
table.push_back(json(10, nullptr));
|
||||
}
|
||||
const auto encoded = json::to_bjdata(table, true, true);
|
||||
CHECK(json::from_bjdata(encoded) == table);
|
||||
|
||||
const std::vector<std::uint8_t> input = {'[', '$', 'Z', '#', 'l', 0x00, 0x10, 0x00, 0x00};
|
||||
CHECK_THROWS_AS(_ = json::from_bjdata(input), json::parse_error&);
|
||||
}
|
||||
|
||||
SECTION("an object of a valueless type needs a key for every value")
|
||||
{
|
||||
// an object member costs a key, so the count is bounded by the input
|
||||
// and is not charged to the budget
|
||||
const std::vector<std::uint8_t> input = {'{', '$', 'Z', '#', 'l', 0x00, 0x10, 0x00, 0x00};
|
||||
ValuelessEventCounter sax;
|
||||
CHECK(!json::sax_parse(input, &sax, json::input_format_t::ubjson));
|
||||
CHECK(sax.error_id == 110);
|
||||
CHECK(sax.values == 0);
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("UBJSON an optimized array of no-ops is empty whatever its count")
|
||||
{
|
||||
// A no-op ('N') is not a value, so `[$N#<n>` is an array without elements
|
||||
// for every n. The count used to be passed on to the SAX parser, which
|
||||
// told it to expect n elements, and the DOM parser reserved storage for
|
||||
// them: 16384 values (256 KB) for a count of 2^31 in 9 bytes of input.
|
||||
SECTION("the SAX parser is told that the array is empty")
|
||||
{
|
||||
for (const std::vector<std::uint8_t>& input :
|
||||
{
|
||||
std::vector<std::uint8_t> {'[', '$', 'N', '#', 'i', 2},
|
||||
std::vector<std::uint8_t> {'[', '$', 'N', '#', 'I', 0x7F, 0xFF},
|
||||
std::vector<std::uint8_t> {'[', '$', 'N', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF},
|
||||
std::vector<std::uint8_t> {'[', '$', 'N', '#', 'i', 0}
|
||||
})
|
||||
{
|
||||
SaxEventLogger logger;
|
||||
CHECK(json::sax_parse(input, &logger, json::input_format_t::ubjson));
|
||||
CHECK(logger.events == std::vector<std::string>({"start_array(0)", "end_array()"}));
|
||||
}
|
||||
|
||||
// between other values, the next value is read as usual
|
||||
const std::vector<std::uint8_t> nested = {'[', '[', '$', 'N', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF, 'T', '[', '$', 'N', '#', 'i', 3, ']'};
|
||||
SaxEventLogger logger;
|
||||
CHECK(json::sax_parse(nested, &logger, json::input_format_t::ubjson));
|
||||
CHECK(logger.events == std::vector<std::string>({"start_array()", "start_array(0)", "end_array()", "boolean(true)", "start_array(0)", "end_array()", "end_array()"}));
|
||||
}
|
||||
|
||||
SECTION("the DOM parser reserves nothing")
|
||||
{
|
||||
// 2000 arrays of 9 bytes that announce 2^31 elements each: with a
|
||||
// reservation of 16384 values per array this took about 500 MB
|
||||
std::vector<std::uint8_t> input = {'['};
|
||||
for (int i = 0; i < 2000; ++i)
|
||||
{
|
||||
input.insert(input.end(), {'[', '$', 'N', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF});
|
||||
}
|
||||
input.push_back(']');
|
||||
|
||||
const json j = json::from_ubjson(input);
|
||||
REQUIRE(j.size() == 2000);
|
||||
std::size_t capacity = 0;
|
||||
for (const auto& element : j)
|
||||
{
|
||||
CHECK(element.is_array());
|
||||
CHECK(element.empty());
|
||||
capacity += element.get_ref<const json::array_t&>().capacity();
|
||||
}
|
||||
CHECK(capacity == 0);
|
||||
|
||||
// the 7-byte form inside an optimized array of arrays
|
||||
std::vector<std::uint8_t> typed = {'[', '$', '[', '#', 'I', 0x07, 0xD0};
|
||||
for (int i = 0; i < 2000; ++i)
|
||||
{
|
||||
typed.insert(typed.end(), {'$', 'N', '#', 'I', 0x7F, 0xFF});
|
||||
}
|
||||
const json k = json::from_ubjson(typed);
|
||||
REQUIRE(k.size() == 2000);
|
||||
capacity = 0;
|
||||
for (const auto& element : k)
|
||||
{
|
||||
CHECK(element.empty());
|
||||
capacity += element.get_ref<const json::array_t&>().capacity();
|
||||
}
|
||||
CHECK(capacity == 0);
|
||||
}
|
||||
|
||||
SECTION("a count that no container could hold is no longer an error")
|
||||
{
|
||||
// the array is empty, so nothing has to fit: 0x7FFFFFFF used to be
|
||||
// reported as out_of_range.408 where it exceeds the maximum size of
|
||||
// an array, and is accepted now
|
||||
const std::vector<std::uint8_t> input = {'[', '$', 'N', '#', 'l', 0x7F, 0xFF, 0xFF, 0xFF};
|
||||
CHECK(json::from_ubjson(input) == json::array());
|
||||
|
||||
// a count that does not fit into std::size_t still is
|
||||
#if SIZE_MAX == 0xffffffff
|
||||
const std::vector<std::uint8_t> too_large = {'[', '$', 'N', '#', 'L', 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00};
|
||||
json _;
|
||||
CHECK_THROWS_AS(_ = json::from_ubjson(too_large), json::out_of_range&);
|
||||
#endif
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("issue #5405 - array reserve for definite-length UBJSON arrays")
|
||||
{
|
||||
#if !defined(JSON_NOEXCEPTION)
|
||||
|
||||
Reference in new issue
Block a user