Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b7b14445f1 | ||
|
|
098eebd412 | ||
|
|
555ef48fb6 | ||
|
|
d732d616ba | ||
|
|
b927100ca1 | ||
|
|
ccb253baf1 | ||
|
|
8c3335d41f | ||
|
|
0ac14610d6 | ||
|
|
2951790d40 | ||
|
|
77611d412f | ||
|
|
f6eb5e4fb1 | ||
|
|
ac0d25f51c | ||
|
|
f91e900875 | ||
|
|
6ac411e14c | ||
|
|
1f7250f77f | ||
|
|
03ce377876 | ||
|
|
a1284028b2 | ||
|
|
abbc29963a | ||
|
|
7127a82fa1 | ||
|
|
99adff001d | ||
|
|
253e4c3926 | ||
|
|
73ec296320 | ||
|
|
79f6513cec | ||
|
|
81888ff9f0 | ||
|
|
38cb5d0573 | ||
|
|
72966ae73d |
No files matched your search
+1
-1
@@ -66,7 +66,7 @@ labels:
|
||||
- "tests/src/fuzzer-(parse_json_view|json_view_image)\\.cpp"
|
||||
- "tests/benchmarks/json_view/.*"
|
||||
- "tools/amalgamate/config_json_view\\.json"
|
||||
- "docs/mkdocs/docs/features/json_view\\.md"
|
||||
- "docs/mkdocs/docs/features/json_view/.*"
|
||||
- "docs/mkdocs/docs/api/basic_json_(document|view)/.*"
|
||||
- "docs/mkdocs/docs/api/(ordered_)?json_(editable_)?(document|view)\\.md"
|
||||
- "docs/mkdocs/docs/examples/(basic_json_(document|view)__|(ordered_)?json_(editable_)?(document|view)).*"
|
||||
|
||||
@@ -28,7 +28,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -46,7 +46,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -115,9 +115,7 @@ jobs:
|
||||
|
||||
python3 $TOOL_DIR/amalgamate.py -c $TOOL_DIR/config_json.json -s .
|
||||
python3 $TOOL_DIR/amalgamate.py -c $TOOL_DIR/config_json_fwd.json -s .
|
||||
# the configuration of json_view.hpp comes with the pull request until
|
||||
# it is on develop; the tool itself is still develop's
|
||||
python3 $TOOL_DIR/amalgamate.py -c $MAIN_DIR/tools/amalgamate/config_json_view.json -s .
|
||||
python3 $TOOL_DIR/amalgamate.py -c $TOOL_DIR/config_json_view.json -s .
|
||||
|
||||
# the header list of the Bazel "json" target must match the files in include/
|
||||
cmake -P cmake/scripts/gen_bazel_build_file.cmake
|
||||
|
||||
@@ -20,7 +20,7 @@ jobs:
|
||||
timeout-minutes: 30
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ jobs:
|
||||
runs-on: ubuntu-22.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -27,7 +27,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ jobs:
|
||||
pull-requests: write
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ jobs:
|
||||
security-events: write
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -54,7 +54,7 @@ jobs:
|
||||
timeout-minutes: 60
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -37,7 +37,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
|
||||
@@ -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
|
||||
@@ -80,7 +80,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -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
|
||||
@@ -112,7 +112,7 @@ jobs:
|
||||
target: [ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -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
|
||||
@@ -178,7 +178,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -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 +362,16 @@ 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
|
||||
# get-cmake extracts the Ninja zip with the system unzip, which the Clang
|
||||
# image lacks; other Clang jobs get away with it by hitting the cache.
|
||||
- name: Install unzip (Clang)
|
||||
if: matrix.container == 'silkeh/clang:latest'
|
||||
run: apt-get update ; apt-get install -y unzip
|
||||
# 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 +395,7 @@ 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 +412,7 @@ 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 +426,7 @@ 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
|
||||
@@ -433,7 +436,7 @@ jobs:
|
||||
runs-on: ubuntu-26.04
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -443,7 +446,7 @@ 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
|
||||
@@ -456,7 +459,7 @@ jobs:
|
||||
target: [ci_test_examples, ci_test_build_documentation, ci_test_documentation_mermaid]
|
||||
steps:
|
||||
- name: Harden Runner
|
||||
uses: step-security/harden-runner@46b06cea07f9e64621fdf066ba77ac6915163d43 # v2.22.3
|
||||
uses: step-security/harden-runner@1d88384fd173af6ecb012dfd0264a306b711241a # v2.22.4
|
||||
with:
|
||||
egress-policy: audit
|
||||
|
||||
@@ -484,7 +487,7 @@ 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)
|
||||
|
||||
+2
-3
@@ -20,7 +20,7 @@
|
||||
|
||||
# fuzzers
|
||||
/tests/corpus_*
|
||||
/tests/parse_*_fuzzer
|
||||
/tests/*_fuzzer
|
||||
|
||||
# documentation
|
||||
/docs/docset/JSON_for_Modern_C++.docset/
|
||||
@@ -47,11 +47,10 @@ nlohmann_json.spdx
|
||||
# Bazel-related
|
||||
MODULE.bazel.lock
|
||||
|
||||
# backups left by `make check-amalgamation` or the ci_test_amalgamation target if they are interrupted
|
||||
# backups left by `make check-amalgamation` if it is interrupted
|
||||
/BUILD.bazel~
|
||||
/nlohmann_json.natvis~
|
||||
/single_include/nlohmann/*.hpp~
|
||||
/venv_astyle/
|
||||
|
||||
# release outputs of `make release`
|
||||
/include.zip
|
||||
|
||||
@@ -28,6 +28,7 @@ The [GitHub Actions](https://docs.github.com/en/actions) workflows that build, t
|
||||
- `publish_documentation.yml` — build and publish the documentation on pushes to the `develop` branch that touch the documentation sources (or the files it embeds).
|
||||
- `check_docs_links.yml` — check the links of the documentation weekly, as external links can break without any change in this repository.
|
||||
- `cancel_closed_pr_runs.yml` — cancel unfinished workflow runs of a pull request once it is closed or merged.
|
||||
- `json_view_benchmarks.yml` — compare the performance of `json_view` with other JSON libraries on GitHub-hosted x86-64 and AArch64 Linux runners, on demand or when a pull request gets the label "benchmark".
|
||||
|
||||
Further documentation:
|
||||
|
||||
|
||||
@@ -215,7 +215,7 @@ release: include.zip json.tar.xz
|
||||
|
||||
# clean up
|
||||
clean:
|
||||
rm -fr *.dSYM tests/*.dSYM tests/parse_*_fuzzer
|
||||
rm -fr *.dSYM tests/*.dSYM tests/*_fuzzer
|
||||
rm -fr cmake-build-benchmarks cmake-build-pvs-studio release_files
|
||||
$(MAKE) clean -Cdocs
|
||||
|
||||
|
||||
@@ -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;
|
||||
@@ -1382,6 +1383,7 @@ Use your favorite [**package manager**](https://json.nlohmann.me/integration/pac
|
||||
- [**build2**](https://json.nlohmann.me/integration/package_managers/#build2) `nlohmann-json`
|
||||
- <img src="https://raw.githubusercontent.com/nlohmann/json/refs/heads/develop/docs/mkdocs/docs/images/package_managers/CPM.png" height="20"> [**cpm.cmake**](https://json.nlohmann.me/integration/package_managers/#cpmcmake) `gh:nlohmann/json`
|
||||
- <img src="https://raw.githubusercontent.com/nlohmann/json/refs/heads/develop/docs/mkdocs/docs/images/package_managers/xmake.svg" height="20"> [**xmake**](https://json.nlohmann.me/integration/package_managers/#xmake) `nlohmann_json`
|
||||
- <img src="https://raw.githubusercontent.com/nlohmann/json/refs/heads/develop/docs/mkdocs/docs/images/package_managers/nix.svg" height="20"> [**Nix**](https://json.nlohmann.me/integration/package_managers/#nix) `nlohmann_json`
|
||||
|
||||
The library is part of many package managers. See the [**documentation**](https://json.nlohmann.me/integration/package_managers/) for detailed descriptions and examples.
|
||||
|
||||
|
||||
@@ -406,61 +406,6 @@ add_custom_target(ci_test_clang_sanitizer
|
||||
COMMENT "Compile and test with sanitizers"
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
# Check if header is amalgamated and sources are properly indented.
|
||||
###############################################################################
|
||||
|
||||
# Same file set as .github/workflows/check_amalgamation.yml, so this CMake target (which can be run locally) is held
|
||||
# to the same standard as the workflow (which runs for pull requests and for pushes to develop/master/release/*).
|
||||
file(GLOB_RECURSE INDENT_FILES
|
||||
${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.hpp
|
||||
${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.cpp
|
||||
${PROJECT_SOURCE_DIR}/docs/mkdocs/docs/examples/*.cu
|
||||
${PROJECT_SOURCE_DIR}/include/*.hpp
|
||||
${PROJECT_SOURCE_DIR}/include/*.cpp
|
||||
${PROJECT_SOURCE_DIR}/include/*.cu
|
||||
${PROJECT_SOURCE_DIR}/tests/*.hpp
|
||||
${PROJECT_SOURCE_DIR}/tests/*.cpp
|
||||
${PROJECT_SOURCE_DIR}/tests/*.cu
|
||||
)
|
||||
list(FILTER INDENT_FILES EXCLUDE REGEX "/tests/thirdparty/|/tests/abi/include/nlohmann/")
|
||||
|
||||
set(include_dir ${PROJECT_SOURCE_DIR}/single_include/nlohmann)
|
||||
set(tool_dir ${PROJECT_SOURCE_DIR}/tools/amalgamate)
|
||||
add_custom_target(ci_test_amalgamation
|
||||
COMMAND rm -fr ${include_dir}/json.hpp~ ${include_dir}/json_fwd.hpp~ ${include_dir}/json_literals.hpp~ ${include_dir}/json_view.hpp~
|
||||
COMMAND cp ${include_dir}/json.hpp ${include_dir}/json.hpp~
|
||||
COMMAND cp ${include_dir}/json_fwd.hpp ${include_dir}/json_fwd.hpp~
|
||||
COMMAND cp ${include_dir}/json_literals.hpp ${include_dir}/json_literals.hpp~
|
||||
COMMAND cp ${include_dir}/json_view.hpp ${include_dir}/json_view.hpp~
|
||||
COMMAND cp ${PROJECT_SOURCE_DIR}/BUILD.bazel ${PROJECT_SOURCE_DIR}/BUILD.bazel~
|
||||
|
||||
COMMAND ${Python3_EXECUTABLE} -mvenv venv_astyle
|
||||
COMMAND venv_astyle/bin/pip3 --quiet install -r ${CMAKE_SOURCE_DIR}/tools/astyle/requirements.txt
|
||||
COMMAND venv_astyle/bin/astyle --version
|
||||
|
||||
COMMAND ${Python3_EXECUTABLE} ${tool_dir}/amalgamate.py -c ${tool_dir}/config_json.json -s .
|
||||
COMMAND ${Python3_EXECUTABLE} ${tool_dir}/amalgamate.py -c ${tool_dir}/config_json_fwd.json -s .
|
||||
COMMAND cp ${PROJECT_SOURCE_DIR}/include/nlohmann/json_literals.hpp ${include_dir}/json_literals.hpp
|
||||
COMMAND ${Python3_EXECUTABLE} ${tool_dir}/amalgamate.py -c ${tool_dir}/config_json_view.json -s .
|
||||
COMMAND venv_astyle/bin/astyle --project=tools/astyle/.astylerc --suffix=none ${include_dir}/json.hpp ${include_dir}/json_fwd.hpp ${include_dir}/json_literals.hpp ${include_dir}/json_view.hpp
|
||||
COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/scripts/gen_bazel_build_file.cmake
|
||||
|
||||
COMMAND diff ${include_dir}/json.hpp~ ${include_dir}/json.hpp
|
||||
COMMAND diff ${include_dir}/json_fwd.hpp~ ${include_dir}/json_fwd.hpp
|
||||
COMMAND diff ${include_dir}/json_literals.hpp~ ${include_dir}/json_literals.hpp
|
||||
COMMAND diff ${include_dir}/json_view.hpp~ ${include_dir}/json_view.hpp
|
||||
COMMAND diff ${PROJECT_SOURCE_DIR}/BUILD.bazel~ ${PROJECT_SOURCE_DIR}/BUILD.bazel
|
||||
|
||||
COMMAND venv_astyle/bin/astyle --project=tools/astyle/.astylerc --suffix=orig ${INDENT_FILES}
|
||||
COMMAND for FILE in `find . -name '*.orig'`\; do false \; done
|
||||
|
||||
COMMAND rm -f ${include_dir}/json.hpp~ ${include_dir}/json_fwd.hpp~ ${include_dir}/json_literals.hpp~ ${include_dir}/json_view.hpp~ ${PROJECT_SOURCE_DIR}/BUILD.bazel~
|
||||
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
|
||||
COMMENT "Check amalgamation, formatting, and BUILD.bazel"
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
# Build and test using the amalgamated header
|
||||
###############################################################################
|
||||
@@ -692,19 +637,6 @@ else()
|
||||
)
|
||||
endif()
|
||||
|
||||
###############################################################################
|
||||
# Benchmarks
|
||||
###############################################################################
|
||||
|
||||
add_custom_target(ci_benchmarks
|
||||
COMMAND ${CMAKE_COMMAND}
|
||||
-DCMAKE_BUILD_TYPE=Release -GNinja
|
||||
-S${PROJECT_SOURCE_DIR}/tests/benchmarks -B${PROJECT_BINARY_DIR}/build_benchmarks
|
||||
COMMAND ${CMAKE_COMMAND} --build ${PROJECT_BINARY_DIR}/build_benchmarks --target json_benchmarks
|
||||
COMMAND cd ${PROJECT_BINARY_DIR}/build_benchmarks && ./json_benchmarks
|
||||
COMMENT "Run benchmarks"
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
# CMake flags
|
||||
###############################################################################
|
||||
@@ -965,12 +897,3 @@ add_custom_target(ci_test_documentation_mermaid
|
||||
WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}/docs/mkdocs
|
||||
COMMENT "Check the Mermaid diagrams of the documentation"
|
||||
)
|
||||
|
||||
###############################################################################
|
||||
# Clean up all generated files.
|
||||
###############################################################################
|
||||
|
||||
add_custom_target(ci_clean
|
||||
COMMAND rm -fr ${PROJECT_BINARY_DIR}/build_* ${PROJECT_BINARY_DIR}/cmake-3.5.0 ${PROJECT_BINARY_DIR}/cmake-3.31.6 ${PROJECT_BINARY_DIR}/cmake-4.0.0 ${JSON_CMAKE_FLAG_BUILD_DIRS} ${single_binaries}
|
||||
COMMENT "Clean generated directories"
|
||||
)
|
||||
@@ -1 +1 @@
|
||||
semgrep==1.184.0
|
||||
semgrep==1.185.0
|
||||
@@ -265,7 +265,9 @@ basic_json(basic_json&& other) noexcept;
|
||||
4. Depends on the called constructor. For types directly supported by the library (i.e., all types for which no
|
||||
`to_json()` function was provided), a strong guarantee holds: if an exception is thrown, there are no changes to any
|
||||
JSON value.
|
||||
5. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
5. Strong guarantee: if an exception is thrown, there are no changes to any JSON value. Values that are moved into
|
||||
`init` (e.g., `a` in `#!cpp json::object({std::move(a), 5})`) are moved when the initializer list is created,
|
||||
before the constructor runs, and stay moved-from if it throws.
|
||||
6. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
7. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
8. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
|
||||
@@ -58,7 +58,9 @@ is not UTF-8 encoded and `error_handler` is set to `strict`
|
||||
|
||||
## Complexity
|
||||
|
||||
Linear.
|
||||
Linear in the size of the result. With an `indent`, every line starts with up to `indent` characters per nesting level,
|
||||
so the result can be larger than the value by a factor of its nesting depth (see
|
||||
[Parsing untrusted input](../../features/parsing/untrusted_input.md#nesting-depth)).
|
||||
|
||||
## Notes
|
||||
|
||||
|
||||
@@ -26,10 +26,12 @@ void erase(const size_type idx);
|
||||
|
||||
If called on a primitive type other than `#!json null`, the resulting JSON value will be `#!json null`.
|
||||
|
||||
2. Remove an element range specified by `[first; last)` from a JSON value. The iterator `first` does not need to be
|
||||
dereferenceable if `first == last`: erasing an empty range is a no-op.
|
||||
2. Remove an element range specified by `[first; last)` from a JSON value. For arrays and objects, the iterator `first`
|
||||
does not need to be dereferenceable if `first == last`: erasing an empty range is a no-op.
|
||||
|
||||
If called on a primitive type other than `#!json null`, the resulting JSON value will be `#!json null`.
|
||||
If called on a primitive type other than `#!json null`, the range must be `[begin(); end())`, and the resulting JSON
|
||||
value will be `#!json null`. Any other range, including the empty ranges `[begin(); begin())` and
|
||||
`[end(); end())`, throws [`invalid_iterator.204`](../../home/exceptions.md#jsonexceptioninvalid_iterator204).
|
||||
|
||||
3. Removes an element from a JSON object by key.
|
||||
|
||||
@@ -93,8 +95,8 @@ Strong exception safety: if an exception occurs, the original value stays intact
|
||||
- Throws [`invalid_iterator.203`](../../home/exceptions.md#jsonexceptioninvalid_iterator203) if called on iterators
|
||||
which does not belong to the current JSON value; example: `"iterators do not fit current value"`
|
||||
- Throws [`invalid_iterator.204`](../../home/exceptions.md#jsonexceptioninvalid_iterator204) if called on a
|
||||
primitive type with invalid iterators (i.e., if `first != begin()` and `last != end()`); example: `"iterators out
|
||||
of range"`
|
||||
primitive type with invalid iterators (i.e., if `first != begin()` or `last != end()`, which includes the empty
|
||||
ranges `[begin(); begin())` and `[end(); end())`); example: `"iterators out of range"`
|
||||
3. The function can throw the following exceptions:
|
||||
- Throws [`type_error.307`](../../home/exceptions.md#jsonexceptiontype_error307) when called on a type other than
|
||||
JSON object; example: `"cannot use erase() with null"`
|
||||
|
||||
@@ -18,7 +18,8 @@ Strong exception safety: if an exception occurs, the original value stays intact
|
||||
|
||||
## Complexity
|
||||
|
||||
Linear in the size of the JSON value.
|
||||
Linear in the size of the result. Every key repeats the path of its value, so the keys can be larger than the value by a
|
||||
factor of its nesting depth (see [Parsing untrusted input](../../features/parsing/untrusted_input.md#nesting-depth)).
|
||||
|
||||
## Notes
|
||||
|
||||
|
||||
@@ -69,8 +69,10 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
|
||||
## Exceptions
|
||||
|
||||
- Throws [parse_error.110](../../home/exceptions.md#jsonexceptionparse_error110) if the given input ends prematurely or
|
||||
the end of the file was not reached when `strict` was set to true
|
||||
- Throws [parse_error.110](../../home/exceptions.md#jsonexceptionparse_error110) if the given input ends prematurely,
|
||||
if the end of the file was not reached when `strict` was set to true, or if a string at the end of the value is not
|
||||
terminated by 0xFF although a byte follows it (also when `strict` is false: the byte that ends the string is
|
||||
taken from the input, so the next value would be lost)
|
||||
- Throws [parse_error.112](../../home/exceptions.md#jsonexceptionparse_error112) if a parse error occurs, for instance
|
||||
an invalid byte, a string that is not valid UTF-8, or an object key that is not a string
|
||||
|
||||
|
||||
@@ -89,8 +89,11 @@ 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`), or if an optimized array of `Z`, `T`, or `F` has
|
||||
more than 1,048,576 elements
|
||||
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
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../macros/json_ubjson_valueless_elements_per_byte.md) (4 by default) for
|
||||
every byte read so far
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -119,6 +122,8 @@ Linear in the size of the input.
|
||||
- [Parsing untrusted input](../../features/parsing/untrusted_input.md) - limits and safe handling of hostile data
|
||||
- [Binary values](../../features/binary_values.md) - how binary values and subtypes are handled
|
||||
- [`to_ubjson`](to_ubjson.md) - create a UBJSON serialization of a JSON value
|
||||
- [`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../macros/json_ubjson_valueless_elements_per_byte.md) -
|
||||
set how many elements of arrays of `null`, `true`, or `false` the input may announce per byte
|
||||
- [`from_cbor`](from_cbor.md) - create a JSON value from an input in CBOR format
|
||||
- [`from_msgpack`](from_msgpack.md) - create a JSON value from an input in MessagePack format
|
||||
- [`from_bson`](from_bson.md) - create a JSON value from an input in BSON format
|
||||
@@ -132,6 +137,12 @@ 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; the
|
||||
number of elements per byte can be set with
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../macros/json_ubjson_valueless_elements_per_byte.md), for example to read
|
||||
files written by version 3.12.0 and earlier that exceed the default.
|
||||
|
||||
!!! warning "Deprecation"
|
||||
|
||||
|
||||
@@ -18,7 +18,9 @@ JSON object value
|
||||
|
||||
## Exception safety
|
||||
|
||||
Strong guarantee: if an exception is thrown, there are no changes in the JSON value.
|
||||
Strong guarantee: if an exception is thrown, there are no changes in the JSON value. Values that are moved into `init`
|
||||
(e.g., `a` in `#!cpp json::object({std::move(a), 5})`) are moved when the initializer list is created, before this
|
||||
function runs, and stay moved-from if it throws.
|
||||
|
||||
## Exceptions
|
||||
|
||||
|
||||
@@ -2,12 +2,21 @@
|
||||
|
||||
```cpp
|
||||
namespace std {
|
||||
void swap(nlohmann::basic_json& j1, nlohmann::basic_json& j2);
|
||||
void swap(nlohmann::basic_json& j1, nlohmann::basic_json& j2) noexcept(
|
||||
is_nothrow_move_constructible<nlohmann::basic_json>::value &&
|
||||
is_nothrow_move_assignable<nlohmann::basic_json>::value
|
||||
);
|
||||
}
|
||||
```
|
||||
|
||||
Exchanges the values of two JSON objects.
|
||||
|
||||
This specialization is only provided before C++20, which no longer allows specializing function templates in
|
||||
namespace `std`. With C++20 (and in generic code with any standard), use the idiom `#!cpp using std::swap; swap(j1, j2);`: it finds
|
||||
the [`swap`](swap.md) friend function (overload 2) by argument-dependent lookup. A qualified `#!cpp std::swap(j1, j2)`
|
||||
still compiles with C++20, but uses the generic `std::swap`, which swaps by three moves instead of exchanging the
|
||||
contents.
|
||||
|
||||
## Parameters
|
||||
|
||||
`j1` (in, out)
|
||||
@@ -18,7 +27,9 @@ Exchanges the values of two JSON objects.
|
||||
|
||||
## Exception safety
|
||||
|
||||
No-throw guarantee: this function never throws exceptions.
|
||||
No-throw guarantee if the `noexcept` condition above holds: it holds unless moving the
|
||||
[`json_base_class_t`](json_base_class_t.md) can throw. With the default base class, this function never throws
|
||||
exceptions.
|
||||
|
||||
## Complexity
|
||||
|
||||
@@ -57,3 +68,4 @@ void swap(nlohmann::basic_json& j1, nlohmann::basic_json& j2)
|
||||
|
||||
- Added in version 1.0.0.
|
||||
- Extended for arbitrary basic_json types in version 3.10.5.
|
||||
- Not provided with C++20 since version 3.9.0.
|
||||
@@ -75,8 +75,12 @@ void swap(typename binary_t::container_type& other);
|
||||
|
||||
## Exception safety
|
||||
|
||||
1. No-throw guarantee: this function never throws exceptions.
|
||||
2. No-throw guarantee: this function never throws exceptions.
|
||||
1. No-throw guarantee if the `noexcept` condition above holds: it holds unless moving the
|
||||
[`json_base_class_t`](json_base_class_t.md) can throw (moving the type tag and the stored value never throws).
|
||||
With the default base class, this function never throws exceptions.
|
||||
2. No-throw guarantee if the `noexcept` condition above holds: it holds unless moving the
|
||||
[`json_base_class_t`](json_base_class_t.md) can throw (moving the type tag and the stored value never throws).
|
||||
With the default base class, this function never throws exceptions.
|
||||
3. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
4. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
5. Strong guarantee: if an exception is thrown, there are no changes to any JSON value.
|
||||
@@ -85,8 +89,8 @@ void swap(typename binary_t::container_type& other);
|
||||
|
||||
## Exceptions
|
||||
|
||||
1. No-throw guarantee: this function never throws exceptions.
|
||||
2. No-throw guarantee: this function never throws exceptions.
|
||||
1. Throws only what moving the [`json_base_class_t`](json_base_class_t.md) throws; nothing with the default base class.
|
||||
2. Throws only what moving the [`json_base_class_t`](json_base_class_t.md) throws; nothing with the default base class.
|
||||
3. Throws [`type_error.310`](../../home/exceptions.md#jsonexceptiontype_error310) if called on JSON values other than
|
||||
arrays; example: `"cannot use swap(array_t&) with boolean"`
|
||||
4. Throws [`type_error.310`](../../home/exceptions.md#jsonexceptiontype_error310) if called on JSON values other than
|
||||
|
||||
@@ -57,7 +57,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
|
||||
## Exceptions
|
||||
|
||||
- Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
|
||||
is false, and `j` contains a non-empty array, object, or binary value.
|
||||
is false, and `j` contains a non-empty array, object, or binary value. Scalars and empty arrays, objects, or binary
|
||||
values do not throw.
|
||||
- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
|
||||
not valid UTF-8 and `error_handler` is `strict` (the default only if
|
||||
[`JSON_STRICT_BINARY_UTF8`](../macros/json_strict_binary_utf8.md) is enabled)
|
||||
@@ -105,6 +106,8 @@ Linear in the size of the JSON value `j`.
|
||||
- [Binary formats](../../features/binary_formats/index.md) - overview and comparison of the supported binary formats
|
||||
- [Binary values](../../features/binary_values.md) - how binary values and subtypes are handled
|
||||
- [`from_ubjson`](from_ubjson.md) - create a JSON value from an input in UBJSON format
|
||||
- [`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../macros/json_ubjson_valueless_elements_per_byte.md) -
|
||||
set how many elements of arrays of `null`, `true`, or `false` a reader accepts per byte of input
|
||||
- [`to_cbor`](to_cbor.md) - create a CBOR serialization of a JSON value
|
||||
- [`to_msgpack`](to_msgpack.md) - create a MessagePack serialization of a JSON value
|
||||
- [`to_bson`](to_bson.md) - create a BSON serialization of a JSON value
|
||||
@@ -117,5 +120,10 @@ 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. The limit does not depend on
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../macros/json_ubjson_valueless_elements_per_byte.md): a reader accepts at
|
||||
least 1,048,576 elements whatever it is set to, so the writer follows that base only.
|
||||
- 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.
|
||||
@@ -26,7 +26,8 @@ The function can throw the following exceptions:
|
||||
- Throws [`type_error.314`](../../home/exceptions.md#jsonexceptiontype_error314) if value is not an object
|
||||
- Throws [`type_error.315`](../../home/exceptions.md#jsonexceptiontype_error315) if object values are not primitive
|
||||
- Throws [`type_error.313`](../../home/exceptions.md#jsonexceptiontype_error313) if a key (JSON pointer) leads to a
|
||||
conflicting nesting; example: `"invalid value to unflatten"`
|
||||
conflicting nesting, for example if a key with a value other than `#!json null` is a prefix of another key (as `/a`
|
||||
and `/a/b`), in whichever order the keys come; example: `"invalid value to unflatten"`
|
||||
- Throws [`parse_error.106`](../../home/exceptions.md#jsonexceptionparse_error106) if an array index in a key begins
|
||||
with '0'; example: `"array index '01' must not begin with '0'"`
|
||||
- Throws [`parse_error.107`](../../home/exceptions.md#jsonexceptionparse_error107) if a key is not empty and does not
|
||||
@@ -90,3 +91,6 @@ Apart from these three cases, for a JSON value `j`, the following is always true
|
||||
- Throws [`parse_error.109`](../../home/exceptions.md#jsonexceptionparse_error109) instead of
|
||||
[`out_of_range.404`](../../home/exceptions.md#jsonexceptionout_of_range404) for a one-character array index that is
|
||||
not a digit (e.g., `/x`) in version 3.13.0, as it already did for longer ones.
|
||||
- Throws [`type_error.313`](../../home/exceptions.md#jsonexceptiontype_error313) for a key that is a prefix of an
|
||||
earlier key in version 3.13.0; before, an object type that keeps the insertion order (such as
|
||||
[`ordered_json`](../ordered_json.md)) silently replaced the nested value.
|
||||
@@ -66,7 +66,8 @@ has `erase`; calling it on a read-only `basic_json_document` fails to compile (`
|
||||
[`parse_error.106`](../../home/exceptions.md#jsonexceptionparse_error106) (a leading `#!cpp '0'`),
|
||||
[`parse_error.109`](../../home/exceptions.md#jsonexceptionparse_error109) (not a number),
|
||||
[`out_of_range.410`](../../home/exceptions.md#jsonexceptionout_of_range410) (too large for `size_type`), or
|
||||
[`out_of_range.404`](../../home/exceptions.md#jsonexceptionout_of_range404) (an empty token); otherwise (an
|
||||
[`out_of_range.404`](../../home/exceptions.md#jsonexceptionout_of_range404) (an empty token, or the token
|
||||
`#!cpp "-"`, which never names an existing element); otherwise (an
|
||||
object, or a primitive value the pointer's parent resolves to) throws what 1. throws.
|
||||
|
||||
Overloads 1. and 2. also throw [`invalid_iterator.202`](../../home/exceptions.md#jsonexceptioninvalid_iterator202)
|
||||
|
||||
@@ -100,7 +100,8 @@ points apply to every edit:
|
||||
[`root()`](root.md). New values (and the element sequences of an edited array/object) go to storage owned by the
|
||||
document, allocated on demand.
|
||||
- **A view keeps referring to the same value.** After [`set`](set.md) replaces the value a view refers to, that view
|
||||
sees the new value; a view of a value that a later edit replaces or drops keeps showing what it last held. An edit
|
||||
sees the new value; a view of a value that a later edit replaces or drops keeps showing what it last held. Such a
|
||||
view can still be edited: the edit changes only that detached value, never anything reachable from `root()`. An edit
|
||||
of an array or object, however, **invalidates the iterators taken over it** (its members may now live in a
|
||||
different sequence), and a string obtained with [`get_string()`](../basic_json_view/get_string.md) stays valid even
|
||||
as further edits happen (earlier buffers of edited text are kept alive, not overwritten).
|
||||
|
||||
@@ -164,7 +164,9 @@ general.
|
||||
The same switch happens, for the same reason, when overload 1. replaces a multi-node array/object value with a
|
||||
scalar: the *parent's* element sequence is what has to switch to links, not `target` itself, because the parent
|
||||
originally stepped over `target`'s whole subtree by its node count, which no longer applies once `target` is a
|
||||
one-node scalar.
|
||||
one-node scalar. This also holds when `target` is no longer part of the document (an edit erased or replaced it, or
|
||||
a value that contains it): if the container that `target` was in still uses its parsed layout, it switches to links
|
||||
(otherwise nothing steps over `target` any more), and only the dropped values change.
|
||||
|
||||
## Examples
|
||||
|
||||
|
||||
@@ -62,10 +62,9 @@ view.
|
||||
|
||||
!!! info "Overload 2 never throws"
|
||||
|
||||
Unlike [`BasicJsonType::contains(const json_pointer&)`](../basic_json/contains.md), which can throw for certain
|
||||
malformed pointers (for instance an empty array-index reference token), overload 2 never throws: a missing key,
|
||||
an out-of-range or malformed array index, a `#!cpp "-"` index, or a reference token used on a primitive all
|
||||
simply make it return `#!cpp false`.
|
||||
Like [`BasicJsonType::contains(const json_pointer&)`](../basic_json/contains.md), overload 2 never throws: a
|
||||
missing key, an out-of-range or malformed array index, a `#!cpp "-"` index, or a reference token used on a
|
||||
primitive all simply make it return `#!cpp false`.
|
||||
|
||||
## Examples
|
||||
|
||||
|
||||
@@ -27,9 +27,10 @@ for (const auto [key, value] : v.items())
|
||||
}
|
||||
```
|
||||
|
||||
Note the `#!cpp const auto` (by value), not `#!cpp const auto&`: unlike `BasicJsonType::items()`, whose elements are
|
||||
references into an existing object, a view's `item` is produced on the fly for each step of the iteration, so there
|
||||
is nothing for a reference to bind to.
|
||||
Taking `item` by value (`#!cpp const auto`) is recommended: unlike `BasicJsonType::items()`, whose elements are
|
||||
references into an existing object, a view's `item` is produced on the fly for each step of the iteration and is
|
||||
cheap to copy. A `#!cpp const auto&` (as in the first snippet) also works, as it binds to that temporary, but a
|
||||
non-const `#!cpp auto&` does not compile.
|
||||
|
||||
## Return value
|
||||
|
||||
|
||||
@@ -7,6 +7,10 @@ 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);
|
||||
|
||||
// (3)
|
||||
template<view_mode M>
|
||||
bool operator==(const basic_json_view& lhs, const basic_json_view<BasicJsonType, M>& rhs);
|
||||
```
|
||||
|
||||
1. Compares two views for equality: whether the values [`BasicJsonType::parse()`](../basic_json/parse.md) would
|
||||
@@ -14,8 +18,12 @@ bool operator==(const BasicJsonType& lhs, const basic_json_view& rhs);
|
||||
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).
|
||||
3. Like overload 1, for two views of the same `BasicJsonType` but of different [view modes](../view_mode.md), in
|
||||
either order: a view of a read-only document (such as a [`json_view`](../json_view.md)) and a view of an editable
|
||||
document (such as a [`json_editable_view`](../json_editable_view.md)). This overload only takes part in overload
|
||||
resolution if `M` is not the mode of `lhs`.
|
||||
|
||||
Neither overload builds a `BasicJsonType` value for a view to do the comparison (see [Notes](#notes) below). Numbers
|
||||
No 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.
|
||||
This is not what [`operator[]`](operator[].md) and the other lookups return for a duplicate key: they find the *first*
|
||||
|
||||
@@ -7,11 +7,17 @@ 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);
|
||||
|
||||
// (3)
|
||||
template<view_mode M>
|
||||
bool operator!=(const basic_json_view& lhs, const basic_json_view<BasicJsonType, M>& 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).
|
||||
3. Compares a read-only and an editable view of the same `BasicJsonType` for inequality, in either order. Returns
|
||||
`#!cpp !(lhs == rhs)`, 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
|
||||
|
||||
@@ -15,6 +15,10 @@ materializing anything.
|
||||
- `#!cpp static_cast<std::size_t>(-1)` for a [discarded](is_discarded.md) view, and for a string that contains
|
||||
escapes — such a string was decoded once into the document's own buffer, so there is no single byte range in
|
||||
`source()` left to point at.
|
||||
- `#!cpp static_cast<std::size_t>(-1)` in an [editable document](../json_editable_document.md) for a value written
|
||||
by an edit ([`set`](../basic_json_document/set.md), [`push_back`](../basic_json_document/push_back.md),
|
||||
[`insert`](../basic_json_document/insert.md)), and for an array or object whose elements an edit added or removed.
|
||||
The values an edit did not touch keep their offsets.
|
||||
|
||||
## Exception safety
|
||||
|
||||
|
||||
@@ -8,8 +8,9 @@ using json_editable_document = basic_json_document<json, view_mode::editable>;
|
||||
|
||||
This type is an **editable** [`basic_json_document`](basic_json_document/index.md) of the default
|
||||
[`json`](json.md) specialization: in addition to everything [`json_document`](json_document.md) offers,
|
||||
[`set`](basic_json_document/set.md) and [`push_back`](basic_json_document/push_back.md) change values after
|
||||
parsing, without ever rewriting the source text — see [Edits](basic_json_document/index.md#edits) and
|
||||
[`set`](basic_json_document/set.md), [`push_back`](basic_json_document/push_back.md),
|
||||
[`insert`](basic_json_document/insert.md), and [`erase`](basic_json_document/erase.md) change values after parsing,
|
||||
without ever rewriting the source text — see [Edits](basic_json_document/index.md#edits) and
|
||||
[Editing a document](../features/json_view/editing.md).
|
||||
|
||||
## Examples
|
||||
|
||||
@@ -9,7 +9,8 @@ using json_editable_view = basic_json_view<json, view_mode::editable>;
|
||||
This type is a [`basic_json_view`](basic_json_view/index.md) of a value of a
|
||||
[`json_editable_document`](json_editable_document.md). It offers the same read-only interface as
|
||||
[`json_view`](json_view.md); what is different is what it can be a view *of* — a value that
|
||||
[`set`](basic_json_document/set.md) and [`push_back`](basic_json_document/push_back.md) can change, with every view
|
||||
[`set`](basic_json_document/set.md), [`push_back`](basic_json_document/push_back.md),
|
||||
[`insert`](basic_json_document/insert.md), and [`erase`](basic_json_document/erase.md) can change, with every view
|
||||
still referring to it seeing the change, see [Edits](basic_json_document/index.md#edits).
|
||||
|
||||
## Examples
|
||||
|
||||
@@ -26,6 +26,8 @@ header. See also the [macro overview page](../../features/macros.md).
|
||||
UBJSON, BJData, and BSON writers
|
||||
- [**JSON_STRICT_NUL_HANDLING**](json_strict_nul_handling.md) - opt in to rejecting a NUL byte in the input instead of
|
||||
treating it as end of input
|
||||
- [**JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE**](json_ubjson_valueless_elements_per_byte.md) - set how many elements of
|
||||
UBJSON arrays of `null`, `true`, or `false` an input may announce per byte it has
|
||||
|
||||
## Language support
|
||||
|
||||
|
||||
@@ -47,11 +47,9 @@ Therefore, assertions can be switched off by defining `NDEBUG`.
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
Assertion failed: (m_value.object->find(key) != m_value.object->end()), function operator[], file json.hpp, line 2144.
|
||||
```
|
||||
The assertion `#!cpp it != m_data.m_value.object->end()` fails in `#!cpp operator[]`.
|
||||
The exact diagnostic format, source filename, and line number depend on the platform,
|
||||
library version, and whether the single-header or multi-header version is used.
|
||||
|
||||
??? example "Example: user-defined behavior"
|
||||
|
||||
|
||||
@@ -27,7 +27,7 @@ comparison of two [`json_view`](../basic_json_view/index.md) documents has a fix
|
||||
and does not depend on it either.
|
||||
|
||||
The call stack that these operations need grows with the limit: roughly *a few kilobytes plus a cost per level times the
|
||||
limit*, where the cost per level is up to about 2.3 KiB in an unoptimized and up to about 0.5 KiB in an optimized build
|
||||
limit*, where the cost per level is up to about 1.8 KiB in an unoptimized and up to about 0.5 KiB in an optimized build
|
||||
(see [Stack needed](#stack-needed)). The default of `128` levels is tuned for threads with ordinary stacks of a few
|
||||
hundred kilobytes or more. Set a lower limit if your threads have small stacks (RTOS tasks, fibers, threads of the musl
|
||||
C
|
||||
@@ -67,7 +67,7 @@ When the macro is not defined, the library defines it to its default value.
|
||||
the levels that are descended into are counted, so the count never exceeds the limit, not even when user code (a
|
||||
copy constructor of a custom base class, say) copies a value while a copy is going on. A byte holds `255` at
|
||||
most, and the limit stays below that, so that the count cannot wrap around. (More levels would hardly be
|
||||
useful: `254` levels need up to 576 KiB of stack in an unoptimized build already, twice as much as the
|
||||
useful: `254` levels need up to 448 KiB of stack in an unoptimized build already, twice as much as the
|
||||
default.)
|
||||
|
||||
### Stack needed
|
||||
@@ -83,7 +83,7 @@ Unoptimized (`-O0`):
|
||||
|
||||
| Operation | limit 16 | limit 32 | limit 64 | limit 128 | limit 254 |
|
||||
|---|---:|---:|---:|---:|---:|
|
||||
| `dump()` and `dump(indent)`, `operator<<` | 48 / 32 | 80 / 64 | 144 / 128 | 288 / 256 | 576 / 512 |
|
||||
| `dump()` and `dump(indent)`, `operator<<` | 16 / 16 | 16 / 16 | 32 / 32 | 48 / 48 | 96 / 96 |
|
||||
| copy construction and assignment | 32 / 16 | 48 / 32 | 112 / 80 | 224 / 144 | 432 / 304 |
|
||||
| `==` | 16 / 16 | 16 / 16 | 16 / 16 | 48 / 32 | 96 / 48 |
|
||||
| `<=>` (C++20) | 16 / 16 | 16 / 16 | 32 / 32 | 64 / 64 | 144 / 128 |
|
||||
@@ -123,23 +123,24 @@ The rule of thumb is
|
||||
|
||||
> stack needed ≈ a few KiB + cost per level × limit
|
||||
|
||||
with a cost per level of up to 2.3 KiB (`dump` at `-O0` with Clang; 2.1 KiB with GCC), 1.7 KiB for copying and merging
|
||||
(1.3 KiB with GCC), and 0.1 to 0.5 KiB for most other operations at `-O0`; and 0.5 KiB or less at `-O2`. The numbers
|
||||
come from the difference between the limits `128` and `254` in the tables, so they are rough: other compilers,
|
||||
other targets (the frames of x86-64 code are about as large), other standard libraries, `JSON_DIAGNOSTICS`, and
|
||||
sanitizers change them. Measure with your own tool chain (see the example below) rather than relying on the tables.
|
||||
The stack that your own code and the operating system need comes on top of these numbers.
|
||||
with a cost per level of up to 1.8 KiB (conversion to another `basic_json` type at `-O0` with Clang; 1.3 KiB with
|
||||
GCC), 1.7 KiB for copying and merging (1.3 KiB with GCC), 0.4 KiB for `dump`, and 0.1 to 0.5 KiB for most other
|
||||
operations at `-O0`; and 0.5 KiB or less at `-O2`. The numbers come from the difference between the limits `128` and
|
||||
`254` in the tables, so they are rough: other compilers, other targets (the frames of x86-64 code are about as large),
|
||||
other standard libraries, `JSON_DIAGNOSTICS`, and sanitizers change them. Measure with your own tool chain (see the
|
||||
example below) rather than relying on the tables. The stack that your own code and the operating system need comes on
|
||||
top of these numbers.
|
||||
|
||||
Which limit to choose, for the stack that you can spare for the library (the largest limit of those measured
|
||||
for which the slowest operation needs at most that much):
|
||||
|
||||
| Stack for the library | optimized (`-O2`) | unoptimized (`-O0`) |
|
||||
|---|---:|---:|
|
||||
| 32 KiB | 64 | 0 |
|
||||
| 64 KiB | 128 | 16 |
|
||||
| 128 KiB (the default stack of threads on musl) | 254 | 32 |
|
||||
| 256 KiB | 254 | 64 |
|
||||
| 512 KiB | 254 | 128 |
|
||||
| 32 KiB | 64 | 16 |
|
||||
| 64 KiB | 128 | 32 |
|
||||
| 128 KiB (the default stack of threads on musl) | 254 | 64 |
|
||||
| 256 KiB | 254 | 128 |
|
||||
| 512 KiB | 254 | 254 |
|
||||
| 1 MiB or more | 254 | 254 |
|
||||
|
||||
### Speed
|
||||
|
||||
@@ -0,0 +1,175 @@
|
||||
# JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE
|
||||
|
||||
```cpp
|
||||
#define JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE /* value */
|
||||
```
|
||||
|
||||
[`from_ubjson`](../basic_json/from_ubjson.md) and [`sax_parse`](../basic_json/sax_parse.md) refuse an input in which the
|
||||
optimized arrays of type `Z` (null), `T` (true), and `F` (false) together have more than 1,048,576 elements plus
|
||||
`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE` for every byte read so far, with
|
||||
[`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408). The macro sets that number. It is the
|
||||
elements per byte that the input is allowed to announce without paying for them: an element of such an array is a
|
||||
single marker that is implied by the array's `$Z#n` header, so a few bytes can announce a million values (see
|
||||
[Parsing Untrusted Input](../../features/parsing/untrusted_input.md)).
|
||||
|
||||
The macro only matters for input that was not written by this library 3.13.0 or later:
|
||||
[`to_ubjson`](../basic_json/to_ubjson.md) never writes more than the base of 1,048,576 elements in typed arrays of
|
||||
these types, and a reader accepts at least that many whatever the macro is. Its main use is reading files written by
|
||||
version 3.12.0 and earlier, which did not limit them (see
|
||||
[below](#reading-files-written-by-version-3120-and-earlier)).
|
||||
|
||||
## Default definition
|
||||
|
||||
The default value is `4`.
|
||||
|
||||
```cpp
|
||||
#define JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE 4
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
!!! info "Allowed values"
|
||||
|
||||
The value must be a **positive integer** (a value of `0` would not allow any element beyond the base, and a negative
|
||||
or fractional rate has no meaning). Any other value is a compile-time error with a message that names the macro:
|
||||
|
||||
```
|
||||
error: static assertion failed: JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must be a positive integer
|
||||
error: static assertion failed: JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must be an integer (not bool or a character type)
|
||||
error: static assertion failed: JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must not be wider than std::uintmax_t
|
||||
```
|
||||
|
||||
The first is reported for `0` and negative values, the second for values such as `4.5`, `1e3`, `true`, or a
|
||||
character of any character type (`'a'`, `L'a'`, `u8'a'`, ...), and the third for an integer type that is wider
|
||||
than `#!cpp std::uintmax_t` (for example `unsigned __int128`). A value that is larger than the largest `#!cpp
|
||||
std::size_t` is treated as that largest value, so that a project can use one spelling, for example
|
||||
`0xFFFFFFFFFFFFFFFFu`, for 32-bit and 64-bit targets.
|
||||
|
||||
!!! info "Large values: the limit is switched off"
|
||||
|
||||
The limit is the base plus the rate times the bytes read. It saturates at the largest `#!cpp std::size_t` instead of
|
||||
overflowing, for any rate and any input size (also with a 32-bit `#!cpp std::size_t`), so a large value never makes
|
||||
the limit smaller. A rate of **at least 131,072** (`1048576 / 8`) effectively switches the limit for the whole
|
||||
input off: the shortest header of an array of more than 32,767 elements takes 8 bytes (`$Z#l` and four bytes of the
|
||||
count, inside an optimized array of arrays; 9 bytes, `[$Z#l`, at the top level), and a shorter header (`$Z#I` and
|
||||
two bytes) can announce at most 32,767. No array can then announce more than the rate times the bytes of its own
|
||||
header. With a rate of 131,071 that is not so: rows of 1,048,576 elements in 8 bytes each gain 8 elements per row,
|
||||
and a table of 278,527 such rows (2.2 MB) is the shortest input that is refused.
|
||||
|
||||
!!! info "What the macro does not change"
|
||||
|
||||
- The limit of **one array** stays at 1,048,576 elements
|
||||
([`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408), "excessive array size"), whatever
|
||||
the macro is. A value that switches the whole-input limit off does not allow a single array of 1,048,577
|
||||
elements.
|
||||
- The **base** of 1,048,576 elements is a fixed constant, the same as the limit of one array. An array that was
|
||||
accepted on its own before the whole-input limit existed is therefore still accepted at the start of an input.
|
||||
- The **writer** is not affected. [`to_ubjson`](../basic_json/to_ubjson.md) follows the base only: it writes a typed
|
||||
array of `Z`, `T`, or `F` only while the arrays written so far and this one stay within 1,048,576 elements, and
|
||||
writes the elements one by one otherwise. That is within the limit of every reader, because the limit is never
|
||||
below the base.
|
||||
- **Objects** and arrays of other types are not counted: every member of an object has a key, and every element of
|
||||
another type takes at least a byte of input.
|
||||
- [`from_bjdata`](../basic_json/from_bjdata.md) is not affected: BJData has no optimized arrays of these types.
|
||||
|
||||
!!! info "Memory"
|
||||
|
||||
A value takes 16 bytes in a DOM, so every element that the limit lets pass costs memory. Beyond the first 1,048,576
|
||||
elements (about 33 MB: 16 bytes per element, and a vector that grows by reallocation needs the old and the new
|
||||
storage at once), a malicious input of `n` bytes can take **about `20 * K * n` bytes** of memory in a DOM, where `K`
|
||||
is the value of the macro. The measurements below read inputs that are at the limit, with containers of `9 * K`
|
||||
elements (`[$Z#l` and a count, 9 bytes each), with `from_ubjson` on macOS, arm64, compiled with `-O2`. The numbers
|
||||
on other systems differ by the allocator; the 16 bytes per element are the lower bound.
|
||||
|
||||
| `K` | bytes of memory per byte of input | memory for 1 MB of input |
|
||||
|------:|----------------------------------:|-------------------------:|
|
||||
| 1 | 25 | 25 MB |
|
||||
| 4 | 81 | 81 MB |
|
||||
| 16 | 312 | 312 MB |
|
||||
| 64 | 1,226 | 1.2 GB |
|
||||
| 256 | 5,493 | 5.5 GB |
|
||||
|
||||
A SAX handler receives the same number of events, and no memory beyond what it keeps. Choose the smallest value that
|
||||
accepts your files, not a large one, if the input comes from an untrusted source: a value of 131,072 or more
|
||||
switches the limit of the whole input off, so that every 8 bytes of input can announce another 1,048,576 values,
|
||||
the limit of one array.
|
||||
|
||||
!!! warning "Define it before the include, in every translation unit"
|
||||
|
||||
This macro must be defined **before** including `<nlohmann/json.hpp>`. Defining it after the include has no effect.
|
||||
|
||||
The value is compiled into the member functions of the binary reader, which are inline, but it is **not**
|
||||
encoded in the [namespace](../../features/namespace.md) of the library (there is no ABI tag for it). It must
|
||||
have the same value in every translation unit of a program (for example by defining it on the command line or in
|
||||
a common header); translation units with different values violate the One Definition Rule, which is undefined
|
||||
behavior (no diagnostic is required). In practice, which value a read uses depends on which functions the compiler
|
||||
inlined and which out-of-line copy of each remaining function the linker kept, so a function compiled with one
|
||||
value can call a function compiled with the other, and a single parse can mix both values.
|
||||
|
||||
### Reading files written by version 3.12.0 and earlier
|
||||
|
||||
Version 3.12.0 wrote an array of `Z`, `T`, or `F` of any length in the optimized form, and a table of equal rows as an
|
||||
optimized array of optimized arrays: a header of `[$[#` and the number of rows (`i` or `U` and 1 byte, `I` and 2 bytes, or
|
||||
`l` and 4 bytes: `h` = 6, 7, or 9 bytes in all for up to 255, 32,767, or more rows), then for every row `$Z#` and its count:
|
||||
5 bytes for up to 255 elements (`U`), 6 bytes for up to 32,767 (`I`), and 8 bytes above (`l`). Every row announces `N`
|
||||
elements for the `b` bytes of its header, so the limit grows by `K * b` and the number of elements by `N` per row.
|
||||
|
||||
- A table is never refused if its rows have at most `K * b` elements each: at most 5 `K` for rows of up to 255
|
||||
elements (20 at the default of `K = 4`), at most 6 `K` for rows of 256 to 32,767 (rows of 1,000 need `K >= 167`),
|
||||
and at most 8 `K` above.
|
||||
- Otherwise the first `(1,048,576 + h * K) / (N - K * b)` rows are accepted, rounded down (`h` as above; 7 for the
|
||||
numbers here). For the default, a table of rows of 1,000 `null` values is read up to row 1,074 (the input of the first
|
||||
example below has 1,100); for `K = 1`, up to row 1,054; for `K = 16`, up to row 1,160.
|
||||
- In general, the smallest value that accepts an input is the largest of
|
||||
`(the elements of the arrays so far - 1,048,576) / (the bytes read when the header of the last of them has been
|
||||
read)` over all arrays, rounded up. For 1,100 rows of 1,000 elements that is
|
||||
`(1,100,000 - 1,048,576) / 6,607 = 7.8`, so `K = 8`.
|
||||
|
||||
To read such a file, define the macro, before the include (or with `-DJSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE=8`), to
|
||||
the smallest value that accepts the file, and see the table above for what that value allows an untrusted input to
|
||||
cost. A file can be converted once: read it with the larger value and write it again with `to_ubjson`, which writes no
|
||||
typed array that a reader with the default value would refuse, so that the result does not need the macro.
|
||||
|
||||
## Examples
|
||||
|
||||
??? example "Example: default limit"
|
||||
|
||||
The table of 1,100 rows of 1,000 `null` values (6,607 bytes) that version 3.12.0 wrote announces 1,100,000 values,
|
||||
which is more than 1,048,576 plus 4 for every byte read.
|
||||
|
||||
```cpp
|
||||
--8<-- "examples/ubjson_valueless_elements_per_byte.cpp"
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
--8<-- "examples/ubjson_valueless_elements_per_byte.output"
|
||||
```
|
||||
|
||||
??? example "Example: raised limit"
|
||||
|
||||
With 16 elements per byte the same table is read. The limit of one array still applies.
|
||||
|
||||
```cpp
|
||||
--8<-- "examples/ubjson_valueless_elements_per_byte_raised.cpp"
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
--8<-- "examples/ubjson_valueless_elements_per_byte_raised.output"
|
||||
```
|
||||
|
||||
## See also
|
||||
|
||||
- [`from_ubjson`](../basic_json/from_ubjson.md) - create a JSON value from a UBJSON serialization
|
||||
- [`to_ubjson`](../basic_json/to_ubjson.md) - create a UBJSON serialization of a JSON value
|
||||
- [`sax_parse`](../basic_json/sax_parse.md) - generate SAX events
|
||||
- [UBJSON](../../features/binary_formats/ubjson.md) - the format and its limits in the library
|
||||
- [Parsing Untrusted Input](../../features/parsing/untrusted_input.md) - limits and checks for input you do not control
|
||||
- [`out_of_range.408`](../../home/exceptions.md#jsonexceptionout_of_range408) - the exception that reports the limit
|
||||
|
||||
## Version history
|
||||
|
||||
- Added in version 3.13.0.
|
||||
@@ -171,7 +171,7 @@ See the examples below for the concrete generated code.
|
||||
|
||||
The macro is equivalent to:
|
||||
|
||||
```cpp hl_lines="22 22 23 24 25 26 27 28"
|
||||
```cpp hl_lines="22 23 24 25 26 27 28"
|
||||
--8<-- "examples/nlohmann_define_type_intrusive_only_serialize_explicit.cpp"
|
||||
```
|
||||
|
||||
|
||||
@@ -69,7 +69,7 @@ For further information please refer to the corresponding macros without `WITH_N
|
||||
|
||||
The macro is equivalent to:
|
||||
|
||||
```cpp hl_lines="16 17 18 19 20 21 22 23 24 25 26 27 28"
|
||||
```cpp hl_lines="16 17 18 19 20 21 22 23 24 25 26 27 28 29 30"
|
||||
--8<-- "examples/nlohmann_define_type_non_intrusive_with_names_explicit.cpp"
|
||||
```
|
||||
|
||||
|
||||
@@ -89,19 +89,21 @@ This differs from `#!cpp std::map`, where the same operations are O(log n).
|
||||
!!! warning "Quadratic cost of building large objects"
|
||||
|
||||
Because every insertion scans all elements inserted so far, building an object of `n` distinct keys costs
|
||||
**O(n²)** in total. This applies to filling an [`ordered_json`](ordered_json.md) object key by key as well as to
|
||||
parsing one, since the parser inserts each key as it is read.
|
||||
**O(n²)** in total. This applies to filling an [`ordered_json`](ordered_json.md) object key by key (with
|
||||
`operator[]`, `emplace`, or `insert`) and, for now, to reading one with a binary reader such as
|
||||
[`from_cbor`](basic_json/from_cbor.md) ([#6104](https://github.com/nlohmann/json/issues/6104)). Parsing JSON text
|
||||
is not affected: the parser finds the keys of an object with many members in a hash table and takes linear time.
|
||||
|
||||
The cost is negligible for the object sizes typically found in configuration files or API payloads, but it grows
|
||||
steeply for machine-generated objects with many thousands of keys. Measured with `-O2 -DNDEBUG` for parsing a flat
|
||||
object of `n` keys, relative to `#!cpp nlohmann::json` (which uses `#!cpp std::map`):
|
||||
steeply for machine-generated objects with many thousands of keys. Measured with Apple clang 21, `-O2 -DNDEBUG`,
|
||||
arm64, for a flat object of `n` keys (best of seven runs):
|
||||
|
||||
| `n` | `json` | `ordered_json` | factor |
|
||||
|--------|--------|----------------|--------|
|
||||
| 2000 | 0.7 ms | 3.6 ms | 5× |
|
||||
| 4000 | 0.8 ms | 14.0 ms | 19× |
|
||||
| 8000 | 1.6 ms | 67.8 ms | 43× |
|
||||
| 16 000 | 3.3 ms | 181.6 ms | 54× |
|
||||
| `n` | `json::parse` | `ordered_json::parse` | `ordered_json`, key by key | `ordered_json::from_cbor` |
|
||||
|--------|---------------|-----------------------|----------------------------|---------------------------|
|
||||
| 2000 | 0.3 ms | 0.1 ms | 4.5 ms | 4.4 ms |
|
||||
| 4000 | 0.5 ms | 0.2 ms | 17.1 ms | 16.8 ms |
|
||||
| 8000 | 0.9 ms | 0.3 ms | 67.0 ms | 66.8 ms |
|
||||
| 16 000 | 2.0 ms | 0.7 ms | 282.4 ms | 282.4 ms |
|
||||
|
||||
If key order matters for objects of that size, consider a container with a lookup index, such as
|
||||
[`nlohmann::fifo_map`](https://github.com/nlohmann/fifo_map)
|
||||
|
||||
@@ -50,8 +50,8 @@ flowchart LR
|
||||
enabled explicitly. Invalid UTF-8 is rejected.
|
||||
- **Errors are reported, not ignored.** Malformed input results in a [`parse_error`](../home/exceptions.md#parse-errors)
|
||||
with the byte position of the error. Binary readers do not trust announced sizes: strings and binary values grow
|
||||
only as bytes are actually read, arrays reserve at most a fixed number of elements up front, and sizes that no
|
||||
container can hold are rejected.
|
||||
only as bytes are actually read, arrays reserve at most a fixed number of elements up front (and all of them
|
||||
together no more than the input read so far can back), and sizes that no container can hold are rejected.
|
||||
- **Memory is owned by values.** Each `basic_json` value owns its content, and there is no manual memory management in
|
||||
user code. The destructor recurses only over a bounded number of nesting levels and then continues without the call
|
||||
stack, so destroying a deeply nested value does not exhaust the stack.
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
#include <cstdint>
|
||||
#include <iostream>
|
||||
#include <vector>
|
||||
#include <nlohmann/json.hpp>
|
||||
|
||||
using json = nlohmann::json;
|
||||
|
||||
// the bytes version 3.12.0 wrote for a table of 1100 rows of 1000 null values
|
||||
// with to_ubjson(table, true, true): `[$[#I` and the number of rows, then
|
||||
// `$Z#I` and the number of elements for every row
|
||||
std::vector<std::uint8_t> table_written_by_3_12_0()
|
||||
{
|
||||
std::vector<std::uint8_t> bytes = {'[', '$', '[', '#', 'I', 1100 >> 8, 1100 & 0xFF};
|
||||
for (int row = 0; row < 1100; ++row)
|
||||
{
|
||||
bytes.insert(bytes.end(), {'$', 'Z', '#', 'I', 1000 >> 8, 1000 & 0xFF});
|
||||
}
|
||||
return bytes;
|
||||
}
|
||||
|
||||
int main()
|
||||
{
|
||||
try
|
||||
{
|
||||
// 6607 bytes announce 1,100,000 values, more than 1,048,576 plus 4 for
|
||||
// every byte read (the limit is exceeded in row 1075)
|
||||
json table = json::from_ubjson(table_written_by_3_12_0());
|
||||
std::cout << table.size() << " rows\n";
|
||||
}
|
||||
catch (const json::out_of_range& e)
|
||||
{
|
||||
std::cout << e.what() << '\n';
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1 @@
|
||||
[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive number of elements without payload
|
||||
@@ -0,0 +1,42 @@
|
||||
#include <cstdint>
|
||||
#include <iostream>
|
||||
#include <vector>
|
||||
|
||||
// accept 16 values per byte of input instead of 4; define the macro before the
|
||||
// first inclusion of the header, and to the same value in every translation unit
|
||||
#define JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE 16
|
||||
#include <nlohmann/json.hpp>
|
||||
|
||||
using json = nlohmann::json;
|
||||
|
||||
// the bytes version 3.12.0 wrote for a table of 1100 rows of 1000 null values
|
||||
// with to_ubjson(table, true, true): `[$[#I` and the number of rows, then
|
||||
// `$Z#I` and the number of elements for every row
|
||||
std::vector<std::uint8_t> table_written_by_3_12_0()
|
||||
{
|
||||
std::vector<std::uint8_t> bytes = {'[', '$', '[', '#', 'I', 1100 >> 8, 1100 & 0xFF};
|
||||
for (int row = 0; row < 1100; ++row)
|
||||
{
|
||||
bytes.insert(bytes.end(), {'$', 'Z', '#', 'I', 1000 >> 8, 1000 & 0xFF});
|
||||
}
|
||||
return bytes;
|
||||
}
|
||||
|
||||
int main()
|
||||
{
|
||||
// 6607 bytes announce 1,100,000 values, which is below 1,048,576 plus 16
|
||||
// for every byte read
|
||||
json table = json::from_ubjson(table_written_by_3_12_0());
|
||||
std::cout << table.size() << " rows of " << table[0].size() << " values\n";
|
||||
|
||||
// a single container is still limited to 1,048,576 elements
|
||||
const std::vector<std::uint8_t> too_long = {'[', '$', 'Z', '#', 'l', 0x00, 0x10, 0x00, 0x01};
|
||||
try
|
||||
{
|
||||
json j = json::from_ubjson(too_long);
|
||||
}
|
||||
catch (const json::out_of_range& e)
|
||||
{
|
||||
std::cout << e.what() << '\n';
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,2 @@
|
||||
1100 rows of 1000 values
|
||||
[json.exception.out_of_range.408] syntax error while parsing UBJSON size: excessive array size
|
||||
@@ -18,6 +18,10 @@ before including the `json.hpp` header.
|
||||
|
||||
## Function with runtime assertions
|
||||
|
||||
The examples below identify the failing assertion and the function containing it.
|
||||
The exact diagnostic format, source filename, and line number depend on the platform,
|
||||
library version, and whether the single-header or multi-header version is used.
|
||||
|
||||
### Unchecked access to a const value
|
||||
|
||||
Function [`operator[]`](../api/basic_json/operator%5B%5D.md) implements unchecked access for arrays and objects. Whereas
|
||||
@@ -46,11 +50,7 @@ See also the documentation on [element access](element_access/index.md).
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
Assertion failed: (it != m_data.m_value.object->end()), function operator[], file json.hpp, line 28795.
|
||||
```
|
||||
The assertion `#!cpp it != m_data.m_value.object->end()` fails in `#!cpp operator[]`.
|
||||
|
||||
??? example "Example 2: Invalid array index in a JSON pointer"
|
||||
|
||||
@@ -69,11 +69,7 @@ See also the documentation on [element access](element_access/index.md).
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
Assertion failed: (idx < m_data.m_value.array->size()), function operator[], file json.hpp, line 28758.
|
||||
```
|
||||
The assertion `#!cpp idx < ptr->m_data.m_value.array->size()` fails in `#!cpp get_unchecked`.
|
||||
|
||||
### Constructing from an uninitialized iterator range
|
||||
|
||||
@@ -96,11 +92,7 @@ uninitialized iterator is undefined behavior and yields a runtime assertion.
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
Assertion failed: (m_object != nullptr), function operator++, file iter_impl.hpp, line 368.
|
||||
```
|
||||
The assertion `#!cpp first.m_object != nullptr` fails in `#!cpp basic_json`.
|
||||
|
||||
### Operations on uninitialized iterators
|
||||
|
||||
@@ -123,11 +115,7 @@ behavior and yields a runtime assertion.
|
||||
}
|
||||
```
|
||||
|
||||
Output:
|
||||
|
||||
```
|
||||
Assertion failed: (m_object != nullptr), function operator++, file iter_impl.hpp, line 368.
|
||||
```
|
||||
The assertion `#!cpp m_object != nullptr` fails in `#!cpp operator++`.
|
||||
|
||||
## Changes
|
||||
|
||||
|
||||
@@ -181,7 +181,10 @@ of the message are reported as [parse_error.110](../../home/exceptions.md#jsonex
|
||||
arrays and objects with up to four elements that are terminated by 0xFE, unsorted object keys, or a 0xFF after a
|
||||
string that would also end without it, are accepted. A second 0xFF is not a terminator but an empty string.
|
||||
|
||||
Strings must be valid UTF-8, and a string at the very end of a message must be terminated by 0xFF.
|
||||
Strings must be valid UTF-8, and a string at the very end of a message must be terminated by 0xFF. This also
|
||||
holds when `strict` is false and more data follows the value: the byte that would end the string belongs to the
|
||||
next value, and reading it would remove it from the input, so the missing 0xFF is reported as
|
||||
[parse_error.110](../../home/exceptions.md#jsonexceptionparse_error110).
|
||||
|
||||
Duplicate object keys are accepted; the last value wins (`ordered_json` keeps the position of the first occurrence).
|
||||
The specification does not say how to treat them; the HikoGUI reference decoder keeps the first value.
|
||||
|
||||
@@ -119,12 +119,31 @@ The library uses the following mapping from JSON values types to UBJSON types ac
|
||||
receiving side is immediately informed on the number of elements of the container.
|
||||
|
||||
An array whose type marker is `Z` (null), `T` (true) or `F` (false) stores no payload at all, because the marker
|
||||
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
|
||||
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`), 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.
|
||||
(`1 << 20`), or when the counts of all such arrays in the input add up to more than 1,048,576 plus _K_ for every byte
|
||||
read so far, where _K_ is the value of the macro
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../../api/macros/json_ubjson_valueless_elements_per_byte.md) (4 by
|
||||
default). `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 a row in 5 bytes (6 above 255 elements, 8 above 32,767),
|
||||
which raises the limit by 5 _K_ (6 _K_, 8 _K_), so rows of up to 5 _K_ values (20 at the default) are never
|
||||
rejected. To read such a file, define the macro to a larger value (`8` is enough for the 1,100 rows of 1,000
|
||||
`null` values; memory for the arrays then rises to about 20 _K_ bytes per byte of input in a DOM); the macro's
|
||||
page explains how to choose a value and what it costs. The limit of one array of 1,048,576 elements does not
|
||||
depend on the macro. 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.
|
||||
|
||||
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.
|
||||
|
||||
!!! info "Binary values"
|
||||
|
||||
@@ -180,10 +199,13 @@ 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)),
|
||||
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.
|
||||
optimized arrays of `Z`, `T`, or `F` with more elements than the limit allows (1,048,576 plus
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../../api/macros/json_ubjson_valueless_elements_per_byte.md), 4 by default,
|
||||
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.
|
||||
|
||||
!!! info "Duplicate object keys"
|
||||
|
||||
|
||||
@@ -261,6 +261,16 @@ This macro overrides `#!cpp try` calls inside the library.
|
||||
|
||||
See [full documentation of `JSON_TRY_USER`](../api/macros/json_throw_user.md).
|
||||
|
||||
## `JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`
|
||||
|
||||
Sets how many elements of optimized UBJSON arrays of `Z` (null), `T` (true), and `F` (false) a reader accepts for
|
||||
every byte of input it has read, on top of a base of 1,048,576 elements. These arrays have no payload, so a few bytes
|
||||
can announce a million values. The value must be a positive integer; the default is `4`, and a value of 131,072 or
|
||||
more switches the limit of the whole input off. The limit of 1,048,576 elements for a single array always applies. The
|
||||
macro is not part of the [ABI tag](namespace.md): use the same value in every translation unit.
|
||||
|
||||
See [full documentation of `JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../api/macros/json_ubjson_valueless_elements_per_byte.md).
|
||||
|
||||
## `JSON_USE_IMPLICIT_CONVERSIONS`
|
||||
|
||||
When defined to `0`, implicit conversions are switched off. By default, implicit conversions are switched on.
|
||||
|
||||
@@ -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"
|
||||
|
||||
|
||||
@@ -64,13 +64,13 @@ stack for the nesting.)
|
||||
|
||||
The call stack still needs room for the levels that are recursed into, and the default limit assumes a stack of ordinary
|
||||
size. The stack that an operation needs is roughly proportional to the limit; with the default of 128 levels, the most
|
||||
demanding operation (`dump` in an unoptimized build) needed up to 288 KiB, and an optimized build needed 48 KiB or less,
|
||||
in measurements on macOS with arm64. The most demanding operation needed this much stack at the limits `0`, `32`,
|
||||
`128`, and `254`:
|
||||
demanding operations (copying a value and converting it to another `basic_json` type, in an unoptimized build) needed
|
||||
up to 224 KiB, and an optimized build needed 48 KiB or less, in measurements on macOS with arm64. The most demanding
|
||||
operation needed this much stack at the limits `0`, `32`, `128`, and `254`:
|
||||
|
||||
| Stack needed, in KiB | limit 0 | limit 32 | limit 128 (default) | limit 254 |
|
||||
|---|---:|---:|---:|---:|
|
||||
| unoptimized build (`-O0`) | 16 or less | 80 | 288 | 576 |
|
||||
| unoptimized build (`-O0`) | 16 or less | 64 | 224 | 448 |
|
||||
| optimized build (`-O2`) | 16 or less | 16 or less | 48 | 112 |
|
||||
|
||||
A thread with a smaller stack (a task of a real-time operating system, a fiber, or a thread of the musl C library, whose
|
||||
@@ -81,6 +81,20 @@ result. See the [documentation of the macro](../../api/macros/json_recursion_dep
|
||||
the speed, and the rules for choosing a value. Destroying a value (its destructor) recurses over the same number of
|
||||
levels and then continues without the call stack, and needs 32 KiB or less at every limit.
|
||||
|
||||
!!! warning "Indented output and flattened keys grow with the depth"
|
||||
|
||||
Some results are larger than the value by a factor of its nesting depth.
|
||||
[`dump`](../../api/basic_json/dump.md) with an `indent` of `n` (and likewise `operator<<` with `std::setw(n)` and
|
||||
[`basic_json_view::dump`](../../api/basic_json_view/dump.md)) writes up to `n` characters per nesting level in
|
||||
front of every line, and [`flatten`](../../api/basic_json/flatten.md) repeats the path of every value in its key.
|
||||
For the 80,001-byte array `[1,[1,...[1,1]...]]` with 20,000 levels, `dump(1)` returns 600 MB, `dump(4)` 2.4 GB,
|
||||
and the keys of `flatten()` hold 400 MB. A compact `dump()` without indentation stays the size of the value. If you
|
||||
pretty-print, log, or flatten untrusted input, limit its nesting depth while parsing, for example with a
|
||||
[parser callback](parser_callbacks.md#recipe-max-nesting-depth-via-a-callback): with a limit of `d`, every line has
|
||||
at most `n * d` indentation characters, and every flattened key has at most `d` reference tokens.
|
||||
[`JSON_RECURSION_DEPTH_LIMIT`](../../api/macros/json_recursion_depth_limit.md) does not help here: it changes only
|
||||
how much of the call stack a walk uses, never its result, and it does not limit the depth that `parse()` accepts.
|
||||
|
||||
## Input size
|
||||
|
||||
The library does not limit the overall size of a JSON text; a value nested or wide enough will use memory
|
||||
@@ -93,11 +107,39 @@ For the binary formats, an announced size is never trusted outright:
|
||||
actually consumed, rather than allocating the announced length up front — a truncated input runs out of bytes
|
||||
(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.
|
||||
the default, does), the DOM parser reserves storage for them before the elements are read, but for at most 16384
|
||||
elements per array, regardless of how large the announced count is; further elements still grow the container
|
||||
normally as they are read. The arrays that are open at the same time hold their storage at the same time, and an
|
||||
announcement is not backed by input when it is read, so the elements reserved for all arrays of one input together
|
||||
may not exceed 65,536 plus 2 for every byte of input read so far; an array that announces more gets what is left
|
||||
of that and grows as its elements arrive. An 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), so the elements of the
|
||||
arrays that were read use up what was reserved for them, and only arrays that are nested deeply, with an array as
|
||||
their first element, can announce more than is left. For a truncated or hostile input, the storage that
|
||||
announcements can hold is therefore at most (65,536 + 2 per byte of input) values, that is about 1 MiB plus 32 bytes
|
||||
per byte of input with 16-byte values (a value is larger with `JSON_DIAGNOSTICS` or `JSON_DIAGNOSTIC_POSITIONS`, 24 to
|
||||
40 bytes, and so is the bound). For example, 100,000 nested CBOR array headers `99 40 00` (300,000 bytes) that
|
||||
announce 16384 elements each peaked at 23 MiB, against 1.65 GiB if every array reserved what it announced and 12 MiB
|
||||
with version 3.12.0, which reserved nothing.
|
||||
A [SAX](../../api/json_sax/index.md) handler is not affected: it is told the announced number of elements.
|
||||
- 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 _K_ for every byte read so far (checked when each array's header has been read), where _K_ is the
|
||||
value of the macro
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../../api/macros/json_ubjson_valueless_elements_per_byte.md), 4 by
|
||||
default; 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 20 _K_ bytes per byte of input (81 at the default, measured; 312 for _K_ = 16) 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. Leave the macro at the
|
||||
default for input you do not control; raise it only to read trusted files that version 3.12.0 or earlier wrote with
|
||||
long arrays of these types, and see its page for how a value is chosen and what it costs. The limit of one array
|
||||
does not depend on the macro.
|
||||
|
||||
## Strings
|
||||
|
||||
@@ -140,6 +182,20 @@ values for a repeated key ends up in the parsed object. If your application must
|
||||
silently resolving them one way or another, see the
|
||||
[parser callback recipe for rejecting duplicate keys](parser_callbacks.md#recipe-rejecting-duplicate-object-keys).
|
||||
|
||||
## Objects with many keys in `ordered_json`
|
||||
|
||||
[`ordered_json`](../../api/ordered_json.md) keeps the members of an object in a vector in insertion order
|
||||
([`ordered_map`](../../api/ordered_map.md)) and finds a key by searching all members. Parsing JSON text into an
|
||||
`ordered_json` avoids that search for objects with many keys and takes linear time. The binary readers
|
||||
([`from_cbor`](../../api/basic_json/from_cbor.md), [`from_msgpack`](../../api/basic_json/from_msgpack.md),
|
||||
[`from_ubjson`](../../api/basic_json/from_ubjson.md), [`from_bjdata`](../../api/basic_json/from_bjdata.md),
|
||||
[`from_bson`](../../api/basic_json/from_bson.md), and [`from_bon8`](../../api/basic_json/from_bon8.md)) do not yet:
|
||||
reading an object of `n` keys into an `ordered_json` costs time proportional to `n²`. A flat object of 40,000 keys
|
||||
(about 300 KB of CBOR) takes about 1.3 s, against a few milliseconds as JSON text or into a `json`
|
||||
([#6104](https://github.com/nlohmann/json/issues/6104)). `json` is not affected. If you read untrusted binary input
|
||||
into `ordered_json`, bound the input size more tightly, read it into a `json`, or reject objects with many keys in a
|
||||
[SAX handler](sax_interface.md).
|
||||
|
||||
## Numbers
|
||||
|
||||
A number whose value cannot be represented — for instance `1E1000`, which overflows `double` — is rejected while
|
||||
@@ -171,9 +227,11 @@ indices (or the pointer as a whole) before using them, or use [`at`](../../api/b
|
||||
|
||||
- Wrap parsing in a `#!cpp try`/`#!cpp catch` block, or use `allow_exceptions=false`/`accept()` if your environment
|
||||
cannot use exceptions; never let `JSON_NOEXCEPTION`'s `abort()` be the first time you think about error handling.
|
||||
- If the input's nesting depth matters to you, enforce your own limit with a
|
||||
[parser callback](parser_callbacks.md#recipe-max-nesting-depth-via-a-callback) or a
|
||||
- If the input's nesting depth matters to you (for example because you pretty-print, log, or flatten it), enforce your
|
||||
own limit with a [parser callback](parser_callbacks.md#recipe-max-nesting-depth-via-a-callback) or a
|
||||
[SAX handler](sax_interface.md); the library bounds the call stack but not memory use.
|
||||
- If you read untrusted binary input into `ordered_json`, mind that objects with many keys are
|
||||
[slow to read](#objects-with-many-keys-in-ordered_json).
|
||||
- Bound the size of the input itself before parsing, independent of the library's own bounded allocations for binary
|
||||
format lengths.
|
||||
- Decide up front how you want a string with invalid UTF-8 — from any source, not only parsing — to be serialized
|
||||
|
||||
@@ -98,7 +98,7 @@ serialization fails by default. The fourth argument of `dump` selects an
|
||||
|
||||
## Using `std::format`, `std::print`, and `fmt`
|
||||
|
||||
Since version 3.12.0, JSON values can be formatted directly with C++20's
|
||||
Since version 3.13.0, JSON values can be formatted directly with C++20's
|
||||
[`std::format`](https://en.cppreference.com/w/cpp/utility/format/format) whenever the standard library provides the
|
||||
`<format>` header (controlled by [`JSON_HAS_STD_FORMAT`](../api/macros/json_has_std_format.md)). This is enabled by the
|
||||
[`std::formatter<basic_json>`](../api/basic_json/std_formatter.md) specialization, which also makes JSON values work with
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Recipes for Common Types
|
||||
|
||||
The library converts the standard containers, strings, numbers, tuples, `std::optional`, and `std::filesystem::path`
|
||||
(the last two since version 3.12.0, C++17) out of the box, and your own types once you write conversion functions or use
|
||||
The library converts the standard containers, strings, numbers, tuples, `std::optional` (since version 3.12.0), and
|
||||
`std::filesystem::path` (since version 3.10.5), the last two with C++17, out of the box, and your own types once you write conversion functions or use
|
||||
the macros (see [Arbitrary type conversions](arbitrary_types.md)). It deliberately does **not** convert smart pointers,
|
||||
`std::variant`, `std::chrono` types, or class hierarchies, because there is more than one reasonable JSON
|
||||
representation for each of them. This page shows a representation for each that you can copy and adapt.
|
||||
|
||||
@@ -102,7 +102,7 @@ the result of an internet search. If you know further customers of the library,
|
||||
|
||||
- [**Apple iOS and macOS**](https://www.apple.com/macos), a family of operating systems developed by Apple, including iOS for mobile devices and macOS for desktop computers
|
||||
- [**Chromium**](https://chromium.googlesource.com/chromium/src/+/main/third_party/nlohmann_json/), the open-source browser project that Google Chrome, Microsoft Edge, and many other browsers are built on, where the library is used as data container for on-device model execution
|
||||
- [**Google Fuchsia**](https://fuchsia.googlesource.com/third_party/json/), an open-source operating system developed by Google, designed to be secure, updatable, and adaptable across various devices
|
||||
- [**Google Fuchsia**](https://fuchsia.googlesource.com/fuchsia/+/refs/heads/main/scripts/prebuilts/swiftshader/build_config), an open-source operating system developed by Google, designed to be secure, updatable, and adaptable across various devices, where the library is used indirectly through bundled dependencies such as SwiftShader's debugger support and cppdap
|
||||
- [**LG webOS**](https://github.com/webosose/com.webos.service.camera), a Linux-based operating system used in LG smart TVs, signage, and embedded devices
|
||||
- [**Microsoft Azure Linux**](https://github.com/microsoft/azurelinux), a Linux distribution developed by Microsoft for Azure infrastructure and edge workloads
|
||||
- [**OpenHarmony**](https://github.com/openharmony/third_party_json), an open-source operating system for smart devices and the foundation of HarmonyOS
|
||||
@@ -174,7 +174,7 @@ the result of an internet search. If you know further customers of the library,
|
||||
- [**NVIDIA Instant NGP**](https://github.com/NVlabs/instant-ngp/blob/master/src/nerf_loader.cu), an implementation of instant neural graphics primitives for rapid scene reconstruction
|
||||
- [**NVIDIA TensorRT**](https://github.com/NVIDIA/TensorRT), an SDK for high-performance deep learning inference, including its TensorRT-LLM extension for large language models
|
||||
- [**NVIDIA TensorRT-LLM**](https://github.com/NVIDIA/TensorRT-LLM/blob/main/cpp/tensorrt_llm/common/safetensors.cpp), a toolkit for optimizing and serving large language model inference on GPUs
|
||||
- [**ONNX Runtime**](https://github.com/microsoft/onnxruntime), a cross-platform inference and training accelerator for machine learning models
|
||||
- [**ONNX Runtime**](https://onnxruntime.ai), a cross-platform inference and training accelerator for machine learning models
|
||||
- [**OpenVINO**](https://github.com/openvinotoolkit/openvino), Intel's toolkit for optimizing and deploying deep learning inference across CPUs, GPUs, and NPUs
|
||||
- [**PaddleOCR**](https://github.com/PaddlePaddle/PaddleOCR/blob/main/deploy/cpp_infer/src/modules/text_detection/result.cc), an optical character recognition toolkit that turns documents and images into structured data
|
||||
- [**PaddlePaddle**](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/ap/src/axpr/anf_expr.cc), a deep learning framework for distributed training and inference
|
||||
@@ -216,7 +216,7 @@ the result of an internet search. If you know further customers of the library,
|
||||
- [**Check Point**](https://www.checkpoint.com/about-us/copyright-and-trademarks/), a cybersecurity company specializing in threat prevention and network security solutions, offering a range of products designed to protect enterprises from cyber threats and ensure data integrity
|
||||
- [**EasyEffects**](https://github.com/wwmm/easyeffects/blob/master/src/presets_manager.hpp), an audio effects processor for PipeWire offering limiting, compression and equalization
|
||||
- [**espanso**](https://github.com/espanso/espanso/blob/dev/espanso-ui/src/win32/native.cpp), a cross-platform text expander
|
||||
- [**Karabiner-Elements**](https://github.com/pqrs-org/Karabiner-Elements/blob/main/src/share/app_icon.hpp), a keyboard customizer for macOS
|
||||
- [**Karabiner-Elements**](https://github.com/pqrs-org/Karabiner-Elements/blob/main/src/share/json_utility.hpp), a keyboard customizer for macOS
|
||||
- [**MacType**](https://github.com/snowie2000/mactype/blob/directwrite/settings.h), a font rendering engine for Windows
|
||||
- [**magicplan**](https://help.magicplan.app/acknowledgments), a mobile application for creating floor plans and interior designs using augmented reality
|
||||
- [**Microsoft Office for Mac**](https://officecdnmac.microsoft.com/pr/legal/mac/OfficeforMacAttributions.html), a suite of productivity applications developed by Microsoft for macOS, including tools for word processing, spreadsheets, and presentations
|
||||
|
||||
@@ -140,6 +140,8 @@ Exceptions have ids 1xx.
|
||||
|
||||
This error indicates a syntax error while deserializing a JSON text. The error message describes that an unexpected token (character) was encountered, and the member `byte` indicates the error position.
|
||||
|
||||
The message ends with the last read token (`last read: '...'`), with control characters written as `<U+XXXX>`. A token of more than 8192 characters is shown by its first and its last 4096 characters, separated by `...`.
|
||||
|
||||
!!! failure "Example message"
|
||||
|
||||
Input ended prematurely:
|
||||
@@ -985,7 +987,9 @@ contains other characters (e.g., `1a`), or `-` where it cannot be used.
|
||||
|
||||
The JSON Patch operations 'remove' and 'move' cannot be applied to the root element of the JSON value. The exception is
|
||||
also thrown when the parent or a reference token of an empty JSON Pointer is requested, for instance by
|
||||
[`back`](../api/json_pointer/back.md) or [`pop_back`](../api/json_pointer/pop_back.md).
|
||||
[`front`](../api/json_pointer/front.md), [`back`](../api/json_pointer/back.md),
|
||||
[`pop_front`](../api/json_pointer/pop_front.md), or [`pop_back`](../api/json_pointer/pop_back.md), and when
|
||||
[`basic_json_document::erase`](../api/basic_json_document/erase.md) is called with an empty JSON Pointer.
|
||||
|
||||
!!! failure "Example message"
|
||||
|
||||
@@ -1050,11 +1054,21 @@ 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 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.
|
||||
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. The 4 is the
|
||||
default of the macro
|
||||
[`JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE`](../api/macros/json_ubjson_valueless_elements_per_byte.md), which raises it
|
||||
(for the limit of the whole input; the limit of one array stays).
|
||||
[`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, 8
|
||||
above 32,767), so rows of 20 or fewer such values are never rejected at the default; define the macro to a larger value
|
||||
to read them.
|
||||
|
||||
!!! failure "Example messages"
|
||||
|
||||
@@ -1070,6 +1084,9 @@ count and one marker per element are kept), so any value it produces can still b
|
||||
```
|
||||
[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
|
||||
|
||||
@@ -1248,9 +1265,9 @@ A JSON Patch operation 'test' failed. The unsuccessful operation is also printed
|
||||
### json.exception.other_error.502
|
||||
|
||||
[`to_ubjson`](../api/basic_json/to_ubjson.md) and [`to_bjdata`](../api/basic_json/to_bjdata.md) were called with
|
||||
`use_type = true` but `use_size = false`, and the value contains a non-empty array or object (or, with BJData Draft 3,
|
||||
any binary value). UBJSON requires a size marker (`#`) after a type marker (`$`); scalars and empty arrays or objects
|
||||
do not throw.
|
||||
`use_type = true` but `use_size = false`, and the value contains a non-empty array, object, or binary value (with
|
||||
BJData Draft 3, any binary value, including an empty one). UBJSON requires a size marker (`#`) after a type marker
|
||||
(`$`); scalars and empty arrays or objects do not throw.
|
||||
|
||||
!!! failure "Example message"
|
||||
|
||||
|
||||
@@ -0,0 +1,187 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<!-- Created with Inkscape (http://www.inkscape.org/) -->
|
||||
|
||||
<svg
|
||||
width="535"
|
||||
height="535"
|
||||
viewBox="0 0 501.56251 501.56249"
|
||||
id="svg2"
|
||||
version="1.1"
|
||||
inkscape:version="1.3.2 (091e20ef0f, 2023-11-25)"
|
||||
sodipodi:docname="nix-snowflake-colours.svg"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:xlink="http://www.w3.org/1999/xlink"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/">
|
||||
<defs
|
||||
id="defs4">
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient5562">
|
||||
<stop
|
||||
style="stop-color:#699ad7;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop5564" />
|
||||
<stop
|
||||
id="stop5566"
|
||||
offset="0.24345198"
|
||||
style="stop-color:#7eb1dd;stop-opacity:1" />
|
||||
<stop
|
||||
style="stop-color:#7ebae4;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop5568" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient5053">
|
||||
<stop
|
||||
style="stop-color:#415e9a;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop5055" />
|
||||
<stop
|
||||
id="stop5057"
|
||||
offset="0.23168644"
|
||||
style="stop-color:#4a6baf;stop-opacity:1" />
|
||||
<stop
|
||||
style="stop-color:#5277c3;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop5059" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
xlink:href="#linearGradient5562"
|
||||
id="linearGradient4328"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
gradientTransform="translate(70.650339,-1055.1511)"
|
||||
x1="200.59668"
|
||||
y1="351.41116"
|
||||
x2="290.08701"
|
||||
y2="506.18814" />
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
xlink:href="#linearGradient5053"
|
||||
id="linearGradient4330"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
gradientTransform="translate(864.69589,-1491.3405)"
|
||||
x1="-584.19934"
|
||||
y1="782.33563"
|
||||
x2="-496.29703"
|
||||
y2="937.71399" />
|
||||
</defs>
|
||||
<sodipodi:namedview
|
||||
id="base"
|
||||
pagecolor="#ffffff"
|
||||
bordercolor="#666666"
|
||||
borderopacity="1.0"
|
||||
inkscape:pageopacity="0.0"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:zoom="0.70904368"
|
||||
inkscape:cx="99.429699"
|
||||
inkscape:cy="195.33352"
|
||||
inkscape:document-units="px"
|
||||
inkscape:current-layer="layer3"
|
||||
showgrid="false"
|
||||
inkscape:window-width="1920"
|
||||
inkscape:window-height="1050"
|
||||
inkscape:window-x="1920"
|
||||
inkscape:window-y="30"
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:snap-global="true"
|
||||
fit-margin-top="0"
|
||||
fit-margin-left="0"
|
||||
fit-margin-right="0"
|
||||
fit-margin-bottom="0"
|
||||
inkscape:showpageshadow="2"
|
||||
inkscape:pagecheckerboard="0"
|
||||
inkscape:deskcolor="#d1d1d1" />
|
||||
<metadata
|
||||
id="metadata7">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<g
|
||||
inkscape:groupmode="layer"
|
||||
id="layer3"
|
||||
inkscape:label="gradient-logo"
|
||||
style="display:inline;opacity:1"
|
||||
transform="translate(-156.41121,933.30685)">
|
||||
<g
|
||||
id="g2"
|
||||
transform="matrix(0.99994059,0,0,0.99994059,-0.06321798,33.188377)"
|
||||
style="stroke-width:1.00006">
|
||||
<path
|
||||
sodipodi:nodetypes="cccccccccc"
|
||||
inkscape:connector-curvature="0"
|
||||
id="path3336-6"
|
||||
d="m 309.54892,-710.38827 122.19683,211.67512 -56.15706,0.5268 -32.6236,-56.8692 -32.85645,56.5653 -27.90237,-0.011 -14.29086,-24.6896 46.81047,-80.4901 -33.22946,-57.8257 z"
|
||||
style="opacity:1;fill:url(#linearGradient4328);fill-opacity:1;fill-rule:evenodd;stroke:none;stroke-width:3.00018;stroke-linecap:butt;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" />
|
||||
<use
|
||||
height="100%"
|
||||
width="100%"
|
||||
transform="rotate(60,407.11155,-715.78724)"
|
||||
id="use3439-6"
|
||||
inkscape:transform-center-y="151.59082"
|
||||
inkscape:transform-center-x="124.43045"
|
||||
xlink:href="#path3336-6"
|
||||
y="0"
|
||||
x="0"
|
||||
style="stroke-width:1.00006" />
|
||||
<use
|
||||
height="100%"
|
||||
width="100%"
|
||||
transform="rotate(-60,407.31177,-715.70016)"
|
||||
id="use3445-0"
|
||||
inkscape:transform-center-y="75.573958"
|
||||
inkscape:transform-center-x="-168.20651"
|
||||
xlink:href="#path3336-6"
|
||||
y="0"
|
||||
x="0"
|
||||
style="stroke-width:1.00006" />
|
||||
<use
|
||||
height="100%"
|
||||
width="100%"
|
||||
transform="rotate(180,407.41868,-715.7565)"
|
||||
id="use3449-5"
|
||||
inkscape:transform-center-y="-139.94592"
|
||||
inkscape:transform-center-x="59.669705"
|
||||
xlink:href="#path3336-6"
|
||||
y="0"
|
||||
x="0"
|
||||
style="stroke-width:1.00006" />
|
||||
<path
|
||||
style="color:#000000;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;fill:url(#linearGradient4330);fill-opacity:1;fill-rule:evenodd;stroke:none;stroke-width:3.00018;stroke-linecap:butt;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate"
|
||||
d="m 309.54892,-710.38827 122.19683,211.67512 -56.15706,0.5268 -32.6236,-56.8692 -32.85645,56.5653 -27.90237,-0.011 -14.29086,-24.6896 46.81047,-80.4901 -33.22946,-57.8256 z"
|
||||
id="path4260-0"
|
||||
inkscape:connector-curvature="0"
|
||||
sodipodi:nodetypes="cccccccccc" />
|
||||
<use
|
||||
height="100%"
|
||||
width="100%"
|
||||
transform="rotate(120,407.33916,-716.08356)"
|
||||
id="use4354-5"
|
||||
xlink:href="#path4260-0"
|
||||
y="0"
|
||||
x="0"
|
||||
style="display:inline;stroke-width:1.00006" />
|
||||
<use
|
||||
height="100%"
|
||||
width="100%"
|
||||
transform="rotate(-120,407.28823,-715.86995)"
|
||||
id="use4362-2"
|
||||
xlink:href="#path4260-0"
|
||||
y="0"
|
||||
x="0"
|
||||
style="display:inline;stroke-width:1.00006" />
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 6.4 KiB |
@@ -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
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
cmake_minimum_required(VERSION 3.15)
|
||||
project(json_example)
|
||||
|
||||
find_package(nlohmann_json CONFIG REQUIRED)
|
||||
|
||||
add_executable(json_example example.cpp)
|
||||
target_link_libraries(json_example PRIVATE nlohmann_json::nlohmann_json)
|
||||
@@ -0,0 +1,10 @@
|
||||
#include <nlohmann/json.hpp>
|
||||
#include <iostream>
|
||||
#include <iomanip>
|
||||
|
||||
using nlohmann::json;
|
||||
|
||||
int main()
|
||||
{
|
||||
std::cout << std::setw(4) << json::meta() << std::endl;
|
||||
}
|
||||
@@ -14,7 +14,8 @@
|
||||
{: style="height:1em"} [**Conda**](#conda) `nlohmann_json`  
|
||||
{: style="height:1em"} [**MacPorts**](#macports) `nlohmann-json`<br>
|
||||
{: style="height:1em"} [**CPM.cmake**](#cpmcmake) `gh:nlohmann/json`  
|
||||
{: style="height:1em"} [**xmake**](#xmake) `nlohmann_json`
|
||||
{: style="height:1em"} [**xmake**](#xmake) `nlohmann_json`  
|
||||
{: style="height:1em"} [**Nix**](#nix) `nlohmann_json`
|
||||
</p>
|
||||
|
||||
## Running example
|
||||
@@ -906,6 +907,56 @@ CPMAddPackage("gh:nlohmann/json@3.12.0")
|
||||
|
||||
* * *
|
||||
|
||||
## Nix
|
||||
|
||||
!!! abstract "Summary"
|
||||
|
||||
package: [**`nlohmann_json`**](https://search.nixos.org/packages?channel=unstable&show=nlohmann_json&query=nlohmann_json)
|
||||
|
||||
- :octicons-tag-24: Available versions: current version of each Nixpkgs channel (may lag behind the latest release)
|
||||
- :octicons-rocket-24: The package is maintained by the Nixpkgs community and updated after releases.
|
||||
- :octicons-file-24: File issues at the [Nixpkgs issue tracker](https://github.com/NixOS/nixpkgs/issues)
|
||||
- :octicons-question-24: [Nix website](https://nixos.org)
|
||||
|
||||
If you are using [Nix](https://nixos.org) or [NixOS](https://nixos.org/manual/nixos/stable/), the library is available
|
||||
as the [nlohmann_json](https://search.nixos.org/packages?channel=unstable&show=nlohmann_json&query=nlohmann_json)
|
||||
package in [Nixpkgs](https://github.com/NixOS/nixpkgs). To try it in a temporary shell, execute
|
||||
|
||||
```shell
|
||||
nix-shell -p nlohmann_json
|
||||
```
|
||||
|
||||
On NixOS, the package can be installed system-wide by adding it to `configuration.nix`:
|
||||
|
||||
```nix
|
||||
environment.systemPackages = [ pkgs.nlohmann_json ];
|
||||
```
|
||||
|
||||
??? example "Example: CMake"
|
||||
|
||||
1. Create the following files:
|
||||
|
||||
```cpp title="example.cpp"
|
||||
--8<-- "integration/nix/example.cpp"
|
||||
```
|
||||
|
||||
```cmake title="CMakeLists.txt"
|
||||
--8<-- "integration/nix/CMakeLists.txt"
|
||||
```
|
||||
|
||||
2. Enter a shell that provides the package, CMake, and a C++ compiler:
|
||||
|
||||
```sh
|
||||
nix-shell -p nlohmann_json cmake
|
||||
```
|
||||
|
||||
3. Compile the code:
|
||||
|
||||
```sh
|
||||
cmake -S . -B build
|
||||
cmake --build build
|
||||
```
|
||||
|
||||
## Other package managers
|
||||
|
||||
The library is also contained in many other package repositories; [Repology](https://repology.org/project/nlohmann-json/versions) tracks the packaged
|
||||
|
||||
@@ -459,6 +459,7 @@ nav:
|
||||
- 'JSON_SKIP_UNSUPPORTED_COMPILER_CHECK': api/macros/json_skip_unsupported_compiler_check.md
|
||||
- 'JSON_STRICT_BINARY_UTF8': api/macros/json_strict_binary_utf8.md
|
||||
- 'JSON_STRICT_NUL_HANDLING': api/macros/json_strict_nul_handling.md
|
||||
- 'JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE': api/macros/json_ubjson_valueless_elements_per_byte.md
|
||||
- 'JSON_USE_GLOBAL_UDLS': api/macros/json_use_global_udls.md
|
||||
- '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
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
wheel==0.48.0
|
||||
|
||||
mkdocs==1.6.1 # documentation framework
|
||||
mkdocs-git-revision-date-localized-plugin==1.6.3 # plugin "git-revision-date-localized"
|
||||
mkdocs-material==9.8.0 # theme for mkdocs
|
||||
mkdocs-git-revision-date-localized-plugin==1.7.0 # plugin "git-revision-date-localized"
|
||||
mkdocs-material==9.8.1 # theme for mkdocs
|
||||
mkdocs-material-extensions==1.3.1 # extensions
|
||||
mkdocs-minify-plugin==0.8.0 # plugin "minify"
|
||||
mkdocs-redirects==1.2.3 # plugin "redirects"
|
||||
|
||||
+4
-4
@@ -6,7 +6,7 @@
|
||||
"": {
|
||||
"name": "check-mermaid",
|
||||
"dependencies": {
|
||||
"jsdom": "31.0.0",
|
||||
"jsdom": "31.0.1",
|
||||
"mermaid": "12.3.0"
|
||||
}
|
||||
},
|
||||
@@ -1109,9 +1109,9 @@
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/jsdom": {
|
||||
"version": "31.0.0",
|
||||
"resolved": "https://registry.npmjs.org/jsdom/-/jsdom-31.0.0.tgz",
|
||||
"integrity": "sha512-xAkhD9z1eyFC5+QUi9K24CaZJgdCQ2GOGLW1GdVDoQvkp/AxEH9TQ0pAplPOlIiV92hfcgnFOADZypbjgbBT6Q==",
|
||||
"version": "31.0.1",
|
||||
"resolved": "https://registry.npmjs.org/jsdom/-/jsdom-31.0.1.tgz",
|
||||
"integrity": "sha512-CbhJL8ZQg3eKswxSZth4QO9tW0jPIhmR0vtSXQSbKSfWbwIT6hoRc17wdHIVTQ43KI0mdV5iTJr3281IDgVZ5g==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@exodus/bytes": "^1.16.0",
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
"description": "Validate the Mermaid diagrams of the documentation (see check_mermaid.mjs)",
|
||||
"type": "module",
|
||||
"dependencies": {
|
||||
"jsdom": "31.0.0",
|
||||
"jsdom": "31.0.1",
|
||||
"mermaid": "12.3.0"
|
||||
}
|
||||
}
|
||||
@@ -48,10 +48,11 @@ namespace detail
|
||||
{
|
||||
|
||||
/*!
|
||||
@brief implements the Grisu2 algorithm for binary to decimal floating-point
|
||||
conversion.
|
||||
@brief implements binary to decimal floating-point conversion: the shortest
|
||||
digits of Zmij (see zmij.hpp) for IEEE 754 binary64 numbers, and the Grisu2
|
||||
algorithm for all other formats.
|
||||
|
||||
This implementation is a slightly modified version of the reference
|
||||
The Grisu2 implementation is a slightly modified version of the reference
|
||||
implementation which may be obtained from
|
||||
http://florian.loitsch.com/publications (bench.tar.gz).
|
||||
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
#include <iterator> // back_inserter
|
||||
#include <limits> // numeric_limits
|
||||
#include <string> // char_traits, string
|
||||
#include <type_traits> // false_type, integral_constant, is_convertible, is_integral, is_same, remove_cv, remove_reference, true_type
|
||||
#include <utility> // make_pair, move
|
||||
#include <vector> // vector
|
||||
#ifdef __cpp_lib_byteswap
|
||||
@@ -73,13 +74,133 @@ 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, so that a value serialized by
|
||||
this library can always be read back.
|
||||
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.
|
||||
|
||||
@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
|
||||
8 bytes (a row of an optimized array of arrays) 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;
|
||||
|
||||
/// the value of JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE as a std::size_t:
|
||||
/// saturated at the largest one, not truncated, for a value that is wider
|
||||
template<typename T>
|
||||
constexpr std::size_t valueless_elements_rate(const T value) noexcept
|
||||
{
|
||||
return static_cast<std::uintmax_t>(value) > (std::numeric_limits<std::size_t>::max)()
|
||||
? (std::numeric_limits<std::size_t>::max)()
|
||||
: static_cast<std::size_t>(value);
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief number of elements of valueless UBJSON containers accepted per byte of
|
||||
input, in addition to @ref valueless_elements_base
|
||||
|
||||
This is the value of the macro JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE (4 by
|
||||
default), see docs/mkdocs/docs/api/macros/json_ubjson_valueless_elements_per_byte.md.
|
||||
|
||||
An element of a value that has a payload costs at least one byte of input, but
|
||||
an element of a valueless type costs none, so these are the only elements whose
|
||||
number the input does not bound. They are accepted at this rate per byte read,
|
||||
which bounds the memory they take in a DOM: a value takes 16 bytes there, so
|
||||
the arrays at the limit take about 20 times this rate bytes of memory per byte
|
||||
of input (16 for the value, the rest is allocator rounding and the arrays
|
||||
themselves; measured on macOS, DOM, with containers of 9 times the rate
|
||||
elements: 25 bytes per byte at a rate of 1, 81 at 4, 312 at 16, 1226 at 64 and
|
||||
5493 at 256), plus about 33 MB for the first elements of the base (16 bytes for
|
||||
each of the 1048576 elements, and a vector that grows by reallocation, as only
|
||||
16384 elements are reserved upfront, needs the old and the new storage at once).
|
||||
|
||||
The bound is meant for input written by other encoders and by versions before
|
||||
3.13.0, which wrote long arrays of this type optimized without a limit: input
|
||||
written by @ref binary_writer never needs more than the base, because the
|
||||
writer falls back to the unoptimized form once the arrays written so far and
|
||||
the next one add up to more than that, whatever the rate is.
|
||||
|
||||
Range: a positive integer. A value that is not one is a compile-time error (a
|
||||
reader with a rate of 0 would accept nothing beyond the base, and a negative or
|
||||
fractional rate has no meaning). A value that does not fit into std::size_t is
|
||||
used as the largest std::size_t: the rate is so high then that the bound is
|
||||
out of reach anyway, and a project can use one spelling (for example
|
||||
`0xFFFFFFFFFFFFFFFFu`) for 32 and 64 bit targets. The type of the value must
|
||||
be an integer type that is not wider than std::uintmax_t and not bool or a
|
||||
character type. A rate of at least 2^20 / 8 = 131072 effectively switches the
|
||||
whole-input bound off: an array of more than 32767 elements needs a count of
|
||||
type `l`, so its shortest header is `$Z#l` and four bytes (8 bytes) inside an
|
||||
optimized array of arrays (9 bytes, `[$Z#l`, at the top level), and a shorter
|
||||
header (`$Z#I` and two bytes) announces at most 32767. Every container thus has
|
||||
at most (rate * header bytes) elements, which never exceeds the limit. With a
|
||||
rate of 131071 an input that is refused exists (rows of 1048576 elements gain
|
||||
8 elements each); the per-container limit still applies.
|
||||
|
||||
The value must be the same in every translation unit of a program (it is
|
||||
compiled into member functions of binary_reader, which are inline), and it is
|
||||
not part of the ABI tag of the namespace.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_per_byte =
|
||||
// a value that does not fit into std::size_t is the largest one (see above);
|
||||
// the comparison is made in the widest unsigned type, so that nothing is
|
||||
// truncated before it is made. A function template, so that the casts are
|
||||
// not "useless" (-Wuseless-cast) where the macro already has the type
|
||||
valueless_elements_rate((JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE));
|
||||
|
||||
/// the type of the macro's value is char8_t (C++20)
|
||||
template<typename T>
|
||||
#if defined(__cpp_char8_t)
|
||||
struct valueless_elements_rate_is_char8 : std::is_same<T, char8_t> {};
|
||||
#else
|
||||
struct valueless_elements_rate_is_char8 : std::false_type {};
|
||||
#endif
|
||||
|
||||
/// the type of the macro's value is a character or boolean type
|
||||
template<typename T>
|
||||
struct valueless_elements_rate_is_char_or_bool
|
||||
: disjunction<std::is_same<T, bool>, std::is_same<T, char>, std::is_same<T, signed char>,
|
||||
std::is_same<T, unsigned char>, std::is_same<T, wchar_t>, std::is_same<T, char16_t>,
|
||||
std::is_same<T, char32_t>, valueless_elements_rate_is_char8<T>>
|
||||
{};
|
||||
|
||||
// these messages are what a user sees for a wrong value of the macro. The
|
||||
// integer test comes first because a fractional value would also fail the
|
||||
// positivity test; a value wider than std::uintmax_t would be truncated by
|
||||
// the conversion above, so it is rejected
|
||||
static_assert(std::is_integral<typename std::remove_reference<decltype((JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE))>::type>::value
|
||||
&& !valueless_elements_rate_is_char_or_bool<typename std::remove_cv<typename std::remove_reference<decltype((JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE))>::type>::type>::value,
|
||||
"JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must be an integer (not bool or a character type)");
|
||||
static_assert(sizeof(decltype((JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE))) <= sizeof(std::uintmax_t),
|
||||
"JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must not be wider than std::uintmax_t");
|
||||
static_assert((JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE) > 0,
|
||||
"JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE must be a positive integer");
|
||||
|
||||
/*!
|
||||
@brief the number of bytes read up to which
|
||||
@ref valueless_elements_base plus @ref valueless_elements_per_byte times
|
||||
that number can be computed in std::size_t
|
||||
|
||||
For more bytes than this the limit of the valueless elements is the largest
|
||||
std::size_t, which is saturation: the sum is not computed, because it would wrap
|
||||
around, which happens for a rate that is large (the largest std::size_t as the
|
||||
rate wraps already at the first byte) or an input that is large (more than
|
||||
about a billion bytes for the default rate with a 32-bit std::size_t). It is a
|
||||
constant of the build, so no division is made while reading.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t valueless_elements_saturation_chars =
|
||||
((std::numeric_limits<std::size_t>::max)() - valueless_elements_base) / (valueless_elements_per_byte == 0 ? 1 : valueless_elements_per_byte);
|
||||
///////////////////
|
||||
// binary reader //
|
||||
///////////////////
|
||||
@@ -147,6 +268,8 @@ class binary_reader
|
||||
sax = sax_;
|
||||
container_stack.clear();
|
||||
bon8_pushback_size = 0;
|
||||
// the position is only known to the DOM parser while this reader lives
|
||||
const position_binding binding(bound_parser(sax, std::is_convertible<SAX*, json_sax_dom_error_state*> {}), &chars_read);
|
||||
bool result = false;
|
||||
|
||||
switch (input_format)
|
||||
@@ -177,6 +300,17 @@ class binary_reader
|
||||
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
|
||||
}
|
||||
|
||||
// BON8: a string ends at the first byte that cannot continue it. If
|
||||
// that byte follows the value, the reader has already taken it from
|
||||
// the input and holds it in bon8_pushback. Without the end-of-input
|
||||
// check below it would be dropped, and the next read would start
|
||||
// behind it, so report the missing 0xFF instead.
|
||||
if (result && !strict && input_format == input_format_t::bon8 && bon8_pushback_size != 0)
|
||||
{
|
||||
get_bon8();
|
||||
return last_byte_error(exception_id::unexpected_end_of_input, "string at the end of the value is not terminated by 0xFF", "value", "");
|
||||
}
|
||||
|
||||
// strict mode: next byte must be EOF
|
||||
if (result && strict)
|
||||
{
|
||||
@@ -204,6 +338,61 @@ class binary_reader
|
||||
}
|
||||
|
||||
private:
|
||||
/// the DOM parser of @a s whose reserved storage is bounded by the input
|
||||
/// read so far; nullptr for any other SAX parser, which does not reserve,
|
||||
/// and for one that derives from a DOM parser privately or protectedly
|
||||
/// (or ambiguously), which the reader cannot reach
|
||||
static json_sax_dom_error_state* bound_parser(SAX* s, std::true_type /*is a DOM parser*/) noexcept
|
||||
{
|
||||
return s;
|
||||
}
|
||||
|
||||
static json_sax_dom_error_state* bound_parser(SAX* /*s*/, std::false_type /*is a DOM parser*/) noexcept
|
||||
{
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief tells a DOM parser where to find the number of characters read
|
||||
while sax_parse() runs, and puts back what it knew before when
|
||||
sax_parse() returns or throws
|
||||
|
||||
The reader is a local of the caller and is gone then, so the parser must
|
||||
not keep its position. A parser that was bound by a reader that is still
|
||||
running (a parse inside a parse) gets that binding back; that reader is
|
||||
still alive, as it encloses this one.
|
||||
*/
|
||||
class position_binding
|
||||
{
|
||||
public:
|
||||
position_binding(json_sax_dom_error_state* parser_, const std::size_t* position) noexcept
|
||||
: parser(parser_), saved()
|
||||
{
|
||||
if (parser != nullptr)
|
||||
{
|
||||
saved = parser->get_reserve_state();
|
||||
parser->set_input_position(position);
|
||||
}
|
||||
}
|
||||
|
||||
position_binding(const position_binding&) = delete;
|
||||
position_binding(position_binding&&) = delete;
|
||||
position_binding& operator=(const position_binding&) = delete;
|
||||
position_binding& operator=(position_binding&&) = delete;
|
||||
|
||||
~position_binding()
|
||||
{
|
||||
if (parser != nullptr)
|
||||
{
|
||||
parser->set_reserve_state(saved);
|
||||
}
|
||||
}
|
||||
|
||||
private:
|
||||
json_sax_dom_error_state* parser;
|
||||
json_sax_dom_error_state::reserve_state saved;
|
||||
};
|
||||
|
||||
////////////////////////
|
||||
// nested containers //
|
||||
////////////////////////
|
||||
@@ -1738,6 +1927,21 @@ class binary_reader
|
||||
return result;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief move past a value of @a size bytes, starting with @a head, that a
|
||||
bulk run reads, as get() and get_number() would
|
||||
|
||||
Called before the value is passed on, so that an error reported while
|
||||
passing it on (see @ref emit_float) has the position and the last byte
|
||||
that reading the value byte by byte gives.
|
||||
*/
|
||||
void bulk_advance(const std::size_t size, const unsigned char head)
|
||||
{
|
||||
ia.bulk_skip(size);
|
||||
chars_read += size;
|
||||
current = head;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief read the integers, floats, booleans, and nulls that follow in a
|
||||
definite-length array, without the per-element bookkeeping of
|
||||
@@ -1763,71 +1967,70 @@ class binary_reader
|
||||
{
|
||||
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
|
||||
const unsigned char head = data[0];
|
||||
std::size_t size = 0;
|
||||
bool accepted = false;
|
||||
switch (head)
|
||||
{
|
||||
case 0x18:
|
||||
size = 2;
|
||||
bulk_advance(2, head);
|
||||
accepted = emit_unsigned(data[1]);
|
||||
break;
|
||||
case 0x19:
|
||||
size = 3;
|
||||
bulk_advance(3, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
|
||||
break;
|
||||
case 0x1A:
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
|
||||
break;
|
||||
case 0x1B:
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
|
||||
break;
|
||||
case 0x38:
|
||||
size = 2;
|
||||
bulk_advance(2, head);
|
||||
accepted = emit_cbor_negative_integer(data[1]);
|
||||
break;
|
||||
case 0x39:
|
||||
size = 3;
|
||||
bulk_advance(3, head);
|
||||
accepted = emit_cbor_negative_integer(load_big_endian<std::uint16_t>(data + 1));
|
||||
break;
|
||||
case 0x3A:
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_cbor_negative_integer(load_big_endian<std::uint32_t>(data + 1));
|
||||
break;
|
||||
case 0x3B:
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_cbor_negative_integer(load_big_endian<std::uint64_t>(data + 1));
|
||||
break;
|
||||
case 0xF4:
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->boolean(false);
|
||||
break;
|
||||
case 0xF5:
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->boolean(true);
|
||||
break;
|
||||
case 0xF6:
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->null();
|
||||
break;
|
||||
case 0xFA:
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_float(load_big_endian<float>(data + 1));
|
||||
break;
|
||||
case 0xFB:
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_float(load_big_endian<double>(data + 1));
|
||||
break;
|
||||
default:
|
||||
if (head <= 0x17)
|
||||
{
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
|
||||
}
|
||||
else if (head >= 0x20 && head <= 0x37)
|
||||
{
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->number_integer(static_cast<std::int8_t>(0x20 - 1 - head));
|
||||
}
|
||||
else
|
||||
@@ -1837,10 +2040,6 @@ class binary_reader
|
||||
}
|
||||
break;
|
||||
}
|
||||
// as if read by get() and get_number(): current is the head byte
|
||||
ia.bulk_skip(size);
|
||||
chars_read += size;
|
||||
current = head;
|
||||
--remaining;
|
||||
if (JSON_HEDLEY_UNLIKELY(!accepted))
|
||||
{
|
||||
@@ -2678,73 +2877,72 @@ class binary_reader
|
||||
{
|
||||
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
|
||||
const unsigned char head = data[0];
|
||||
std::size_t size = 0;
|
||||
bool accepted = false;
|
||||
switch (head)
|
||||
{
|
||||
case 0xC0: // nil
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->null();
|
||||
break;
|
||||
case 0xC2: // false
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->boolean(false);
|
||||
break;
|
||||
case 0xC3: // true
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->boolean(true);
|
||||
break;
|
||||
case 0xCA: // float 32
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_float(load_big_endian<float>(data + 1));
|
||||
break;
|
||||
case 0xCB: // float 64
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_float(load_big_endian<double>(data + 1));
|
||||
break;
|
||||
case 0xCC: // uint 8
|
||||
size = 2;
|
||||
bulk_advance(2, head);
|
||||
accepted = emit_unsigned(data[1]);
|
||||
break;
|
||||
case 0xCD: // uint 16
|
||||
size = 3;
|
||||
bulk_advance(3, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint16_t>(data + 1));
|
||||
break;
|
||||
case 0xCE: // uint 32
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint32_t>(data + 1));
|
||||
break;
|
||||
case 0xCF: // uint 64
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_unsigned(load_big_endian<std::uint64_t>(data + 1));
|
||||
break;
|
||||
case 0xD0: // int 8
|
||||
size = 2;
|
||||
bulk_advance(2, head);
|
||||
accepted = emit_signed(static_cast<std::int8_t>(data[1]));
|
||||
break;
|
||||
case 0xD1: // int 16
|
||||
size = 3;
|
||||
bulk_advance(3, head);
|
||||
accepted = emit_signed(load_big_endian<std::int16_t>(data + 1));
|
||||
break;
|
||||
case 0xD2: // int 32
|
||||
size = 5;
|
||||
bulk_advance(5, head);
|
||||
accepted = emit_signed(load_big_endian<std::int32_t>(data + 1));
|
||||
break;
|
||||
case 0xD3: // int 64
|
||||
size = 9;
|
||||
bulk_advance(9, head);
|
||||
accepted = emit_signed(load_big_endian<std::int64_t>(data + 1));
|
||||
break;
|
||||
default:
|
||||
if (head <= 0x7F)
|
||||
{
|
||||
// positive fixint
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->number_unsigned(static_cast<number_unsigned_t>(head));
|
||||
}
|
||||
else if (head >= 0xE0)
|
||||
{
|
||||
// negative fixint
|
||||
size = 1;
|
||||
bulk_advance(1, head);
|
||||
accepted = sax->number_integer(static_cast<std::int8_t>(head));
|
||||
}
|
||||
else
|
||||
@@ -2754,10 +2952,6 @@ class binary_reader
|
||||
}
|
||||
break;
|
||||
}
|
||||
// as if read by get() and get_number(): current is the last byte
|
||||
ia.bulk_skip(size);
|
||||
chars_read += size;
|
||||
current = data[size - 1];
|
||||
--remaining;
|
||||
if (JSON_HEDLEY_UNLIKELY(!accepted))
|
||||
{
|
||||
@@ -3661,6 +3855,7 @@ class binary_reader
|
||||
const auto* const data = reinterpret_cast<const unsigned char*>(ia.bulk_data());
|
||||
// UBJSON stores numbers big-endian, BJData little-endian
|
||||
const bool swap = is_little_endian != (input_format == input_format_t::bjdata);
|
||||
const std::size_t start = chars_read;
|
||||
std::size_t read = 0;
|
||||
bool accepted = true;
|
||||
while (read < count && accepted)
|
||||
@@ -3672,16 +3867,39 @@ class binary_reader
|
||||
byte_swap(number);
|
||||
}
|
||||
++read;
|
||||
// where passing the value on can report an error (see
|
||||
// emit_float), the position is that after the value, as if it
|
||||
// was read by get_number()
|
||||
set_chars_read(start + (read * size), std::integral_constant<bool, may_overflow_number_float<NumberType>()> {});
|
||||
accepted = emit_ubjson_number(number);
|
||||
}
|
||||
// as if read by get_number(): current is the last byte read
|
||||
// get_number() does not change current
|
||||
ia.bulk_skip(read * size);
|
||||
chars_read += read * size;
|
||||
current = data[(read * size) - 1];
|
||||
chars_read = start + (read * size);
|
||||
remaining -= read;
|
||||
return accepted;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief whether a value of type @a NumberType can be finite and still
|
||||
overflow number_float_t, which @ref emit_float reports as an error
|
||||
|
||||
False for the default number types, so that the loop in @ref
|
||||
parse_ubjson_typed_run need not track the position per value.
|
||||
*/
|
||||
template<typename NumberType>
|
||||
static constexpr bool may_overflow_number_float() noexcept
|
||||
{
|
||||
return static_cast<long double>((std::numeric_limits<number_float_t>::max)()) < static_cast<long double>((std::numeric_limits<NumberType>::max)());
|
||||
}
|
||||
|
||||
void set_chars_read(const std::size_t position, std::true_type /*track*/) noexcept
|
||||
{
|
||||
chars_read = position;
|
||||
}
|
||||
|
||||
void set_chars_read(const std::size_t /*position*/, std::false_type /*track*/) const noexcept {}
|
||||
|
||||
template<typename NumberType, enable_if_t<std::is_floating_point<NumberType>::value, int> = 0>
|
||||
bool emit_ubjson_number(const NumberType number)
|
||||
{
|
||||
@@ -3700,6 +3918,38 @@ 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
|
||||
{
|
||||
// limit = base + rate * chars_read, saturating at the largest size_t
|
||||
// instead of wrapping around, which would make a huge rate or input
|
||||
// reject everything. valueless_elements never exceeds the limit of an
|
||||
// earlier call, and the limit does not decrease, so the difference
|
||||
// below cannot underflow.
|
||||
const std::size_t limit = chars_read <= valueless_elements_saturation_chars
|
||||
? valueless_elements_base + (valueless_elements_per_byte * chars_read)
|
||||
: (std::numeric_limits<std::size_t>::max)();
|
||||
if (JSON_HEDLEY_UNLIKELY(count > limit - valueless_elements))
|
||||
{
|
||||
return false;
|
||||
}
|
||||
valueless_elements += count;
|
||||
return true;
|
||||
}
|
||||
|
||||
/*!
|
||||
@return whether array creation completed
|
||||
*/
|
||||
@@ -3785,24 +4035,27 @@ 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')
|
||||
&& size_and_type.first > max_valueless_container_size))
|
||||
if (JSON_HEDLEY_UNLIKELY(size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F'))
|
||||
{
|
||||
return out_of_range_error(exception_id::container_too_large, "excessive array size", "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");
|
||||
}
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!enter_array(size_and_type.first, size_and_type.second)))
|
||||
// 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)))
|
||||
{
|
||||
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> {});
|
||||
}
|
||||
@@ -3872,6 +4125,10 @@ class binary_reader
|
||||
auto number_lexer = detail::lexer<BasicJsonType, ia_type>(detail::input_adapter(number_vector), false);
|
||||
const auto result_number = number_lexer.scan();
|
||||
const auto number_string = number_lexer.get_token_string();
|
||||
// the number as the lexer read it, for SAX number_float(): unlike
|
||||
// get_token_string(), which is meant for error messages and shortens
|
||||
// long tokens, it is complete; the next scan() replaces it
|
||||
const string_t number_text = number_lexer.get_string();
|
||||
const auto result_remainder = number_lexer.scan();
|
||||
|
||||
using token_type = typename detail::lexer_base<BasicJsonType>::token_type;
|
||||
@@ -3898,10 +4155,7 @@ class binary_reader
|
||||
number_string,
|
||||
out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", number_string, '\''), nullptr));
|
||||
}
|
||||
// number_string is a std::string, while the SAX interface takes a
|
||||
// string_t; convert explicitly, as the two are only implicitly
|
||||
// convertible for some string types
|
||||
return sax->number_float(parsed_float, string_t(number_string.data(), number_string.size()));
|
||||
return sax->number_float(parsed_float, number_text);
|
||||
}
|
||||
case token_type::uninitialized:
|
||||
case token_type::literal_true:
|
||||
@@ -5114,6 +5368,10 @@ 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();
|
||||
|
||||
|
||||
@@ -110,87 +110,164 @@ inline const char* empty_input_message() noexcept
|
||||
return "attempting to parse an empty input; check that your input string or stream contains the expected JSON";
|
||||
}
|
||||
|
||||
////////////////////
|
||||
// input adapters //
|
||||
////////////////////
|
||||
|
||||
#ifndef JSON_NO_IO
|
||||
/*!
|
||||
@brief the characters of the last read token, kept for error messages
|
||||
|
||||
A growable array of characters for the part of a token that an input adapter
|
||||
copied out of its window: unlike std::vector<char>::push_back(), appending a
|
||||
character takes no reference to a local, and is a few instructions when there
|
||||
is room.
|
||||
copied out of its window, or that the lexer copies while it scans input it
|
||||
cannot read again: unlike std::vector::push_back(), appending a character
|
||||
takes no reference to a local, and is a few instructions when there is room.
|
||||
|
||||
The token is only needed for error messages, which show its first head()
|
||||
characters and its last head() characters (see lexer::get_token_string). The
|
||||
buffer therefore keeps the first head() and at least the last tail()
|
||||
characters: when it is full and holds more than limit() characters, it drops
|
||||
the characters in between instead of growing. That happens where it would
|
||||
otherwise reallocate, so appending stays as cheap as before, and a long string
|
||||
or a long run of whitespace read from a stream is not kept a second time.
|
||||
*/
|
||||
class token_carry_buffer
|
||||
template<typename CharType>
|
||||
class token_text_buffer
|
||||
{
|
||||
public:
|
||||
token_carry_buffer() = default;
|
||||
token_carry_buffer(const token_carry_buffer&) = delete;
|
||||
token_carry_buffer& operator=(const token_carry_buffer&) = delete;
|
||||
token_carry_buffer(token_carry_buffer&& rhs) noexcept
|
||||
static constexpr std::size_t head() noexcept
|
||||
{
|
||||
return 4096;
|
||||
}
|
||||
/// a little more than head(), as the last character may be handed back
|
||||
static constexpr std::size_t tail() noexcept
|
||||
{
|
||||
return head() + 16;
|
||||
}
|
||||
static constexpr std::size_t limit() noexcept
|
||||
{
|
||||
return head() + (2 * tail());
|
||||
}
|
||||
|
||||
token_text_buffer() = default;
|
||||
token_text_buffer(const token_text_buffer&) = delete;
|
||||
token_text_buffer& operator=(const token_text_buffer&) = delete;
|
||||
token_text_buffer(token_text_buffer&& rhs) noexcept
|
||||
: m_data(std::move(rhs.m_data)), m_end(rhs.m_end), m_capacity_end(rhs.m_capacity_end)
|
||||
{
|
||||
rhs.m_end = rhs.m_capacity_end = nullptr;
|
||||
}
|
||||
token_carry_buffer& operator=(token_carry_buffer&&) = delete;
|
||||
~token_carry_buffer() = default;
|
||||
token_text_buffer& operator=(token_text_buffer&& rhs) noexcept
|
||||
{
|
||||
m_data = std::move(rhs.m_data);
|
||||
m_end = rhs.m_end;
|
||||
m_capacity_end = rhs.m_capacity_end;
|
||||
rhs.m_end = rhs.m_capacity_end = nullptr;
|
||||
return *this;
|
||||
}
|
||||
~token_text_buffer() = default;
|
||||
|
||||
void clear() noexcept
|
||||
{
|
||||
m_end = m_data.get();
|
||||
}
|
||||
|
||||
void push_back(char c)
|
||||
bool empty() const noexcept
|
||||
{
|
||||
return m_end == m_data.get();
|
||||
}
|
||||
|
||||
void push_back(CharType c)
|
||||
{
|
||||
if (JSON_HEDLEY_UNLIKELY(m_end == m_capacity_end))
|
||||
{
|
||||
grow(1);
|
||||
make_room(1);
|
||||
}
|
||||
*m_end++ = c;
|
||||
}
|
||||
|
||||
void append(const char* first, const char* last)
|
||||
/// drop the last character
|
||||
void pop_back() noexcept
|
||||
{
|
||||
JSON_ASSERT(!empty());
|
||||
--m_end;
|
||||
}
|
||||
|
||||
void append(const CharType* first, const CharType* last)
|
||||
{
|
||||
const auto n = static_cast<std::size_t>(last - first);
|
||||
const auto room = static_cast<std::size_t>(m_capacity_end - m_end);
|
||||
if (n > room)
|
||||
if (JSON_HEDLEY_UNLIKELY(n > room))
|
||||
{
|
||||
grow(n);
|
||||
append_long(first, n);
|
||||
return;
|
||||
}
|
||||
if (n != 0)
|
||||
{
|
||||
std::memcpy(m_end, first, n);
|
||||
std::memcpy(m_end, first, n * sizeof(CharType));
|
||||
}
|
||||
m_end += n;
|
||||
}
|
||||
|
||||
/// replace the contents of @a out
|
||||
void copy_to(std::vector<char>& out) const
|
||||
void copy_to(std::vector<CharType>& out) const
|
||||
{
|
||||
out.assign(m_data.get(), m_end);
|
||||
}
|
||||
|
||||
private:
|
||||
/// make room for @a extra more characters
|
||||
JSON_HEDLEY_NEVER_INLINE void grow(std::size_t extra)
|
||||
/// append @a n characters that do not fit, in pieces of at most tail()
|
||||
/// characters, so that dropping the middle keeps the last tail() of them
|
||||
JSON_HEDLEY_NEVER_INLINE void append_long(const CharType* first, std::size_t n)
|
||||
{
|
||||
const auto size = static_cast<std::size_t>(m_end - m_data.get());
|
||||
const auto capacity = static_cast<std::size_t>(m_capacity_end - m_data.get());
|
||||
const std::size_t new_capacity = (std::max)(capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity, size + extra);
|
||||
std::unique_ptr<char[]> data(new char[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
if (size != 0)
|
||||
while (n != 0)
|
||||
{
|
||||
std::memcpy(data.get(), m_data.get(), size);
|
||||
const std::size_t piece = n < tail() ? n : tail();
|
||||
make_room(piece);
|
||||
std::memcpy(m_end, first, piece * sizeof(CharType));
|
||||
m_end += piece;
|
||||
first += piece;
|
||||
n -= piece;
|
||||
}
|
||||
m_data = std::move(data);
|
||||
m_end = m_data.get() + size;
|
||||
m_capacity_end = m_data.get() + new_capacity;
|
||||
}
|
||||
|
||||
std::unique_ptr<char[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
|
||||
char* m_end = nullptr;
|
||||
char* m_capacity_end = nullptr;
|
||||
/// make room for @a extra (at most tail()) more characters: drop the
|
||||
/// middle of a long token instead of growing beyond limit()
|
||||
JSON_HEDLEY_NEVER_INLINE void make_room(std::size_t extra)
|
||||
{
|
||||
// nothing is allocated before the first character
|
||||
std::size_t size = m_data ? static_cast<std::size_t>(m_end - m_data.get()) : 0;
|
||||
if (size + extra > limit() && size > head() + tail())
|
||||
{
|
||||
std::memmove(m_data.get() + head(), m_end - tail(), tail() * sizeof(CharType));
|
||||
m_end = m_data.get() + head() + tail();
|
||||
size = head() + tail();
|
||||
}
|
||||
const std::size_t capacity = m_data ? static_cast<std::size_t>(m_capacity_end - m_data.get()) : 0;
|
||||
if (size + extra > capacity)
|
||||
{
|
||||
// never more than limit(): from there on, the middle is dropped
|
||||
const std::size_t doubled = capacity < 32 ? static_cast<std::size_t>(32) : 2 * capacity;
|
||||
const std::size_t new_capacity = (std::max)(doubled < limit() ? doubled : limit(), size + extra);
|
||||
std::unique_ptr<CharType[]> data(new CharType[new_capacity]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
if (size != 0)
|
||||
{
|
||||
std::memcpy(data.get(), m_data.get(), size * sizeof(CharType));
|
||||
}
|
||||
m_data = std::move(data);
|
||||
m_end = m_data.get() + size;
|
||||
m_capacity_end = m_data.get() + new_capacity;
|
||||
}
|
||||
}
|
||||
|
||||
std::unique_ptr<CharType[]> m_data{}; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,readability-redundant-member-init)
|
||||
CharType* m_end = nullptr;
|
||||
CharType* m_capacity_end = nullptr;
|
||||
};
|
||||
|
||||
/// the part of a token that an input adapter copied out of its window
|
||||
using token_carry_buffer = token_text_buffer<char>;
|
||||
|
||||
////////////////////
|
||||
// input adapters //
|
||||
////////////////////
|
||||
|
||||
#ifndef JSON_NO_IO
|
||||
/*!
|
||||
Input adapter for stdio file access. The file is locked for the lifetime of the
|
||||
adapter and read with the unlocked stdio functions (see
|
||||
|
||||
@@ -159,6 +159,40 @@ constexpr std::size_t unknown_size()
|
||||
return (std::numeric_limits<std::size_t>::max)();
|
||||
}
|
||||
|
||||
/// the largest number of elements the DOM parsers reserve for one array upfront
|
||||
constexpr std::size_t reserve_cap()
|
||||
{
|
||||
return 16384;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief number of array elements a DOM parser may reserve upfront on top of
|
||||
@ref reserved_elements_per_byte
|
||||
|
||||
An array that announces its size is given storage for that many elements when
|
||||
it opens (at most @ref reserve_cap of them), before any input backs the
|
||||
announcement, and the arrays that are open at the same time keep their storage
|
||||
until the input is complete: 100000 nested headers of three bytes each that
|
||||
announce 16384 elements would otherwise need 1.7 GB. The elements reserved for
|
||||
all arrays of an input are therefore added up, and the sum must stay below
|
||||
this base plus @ref reserved_elements_per_byte for every byte read so far; an
|
||||
array that would go beyond reserves what is left, and grows as its elements
|
||||
arrive. The base is four arrays of the maximum size, so the first nested
|
||||
arrays of an input are not affected.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t reserved_elements_base = 4 * reserve_cap();
|
||||
|
||||
/*!
|
||||
@brief number of array elements a DOM parser may reserve upfront per byte of
|
||||
input, in addition to @ref reserved_elements_base
|
||||
|
||||
An element of an array takes at least one byte of input, so an array that
|
||||
completes has used what was reserved for it. At a rate of 2 elements per
|
||||
byte, an array that announces more than the input provides keeps at most
|
||||
32 bytes of memory per byte of input, plus the base, until the parse fails.
|
||||
*/
|
||||
JSON_INLINE_VARIABLE constexpr std::size_t reserved_elements_per_byte = 2;
|
||||
|
||||
/*!
|
||||
@brief reserve capacity for @a len elements in array @a arr
|
||||
|
||||
@@ -174,14 +208,26 @@ template<typename ArrayType>
|
||||
auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
|
||||
-> decltype(arr.reserve(len), void())
|
||||
{
|
||||
constexpr std::size_t reserve_cap = 16384;
|
||||
arr.reserve((std::min)(len, reserve_cap));
|
||||
arr.reserve((std::min)(len, reserve_cap()));
|
||||
}
|
||||
|
||||
template<typename ArrayType>
|
||||
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
|
||||
{}
|
||||
|
||||
/// reserve capacity for @a count elements in array @a arr, where @a count is
|
||||
/// at most reserve_cap() already (see json_sax_dom_error_state::reserve_count)
|
||||
template<typename ArrayType>
|
||||
auto reserve_array_capped(ArrayType& arr, std::size_t count, priority_tag<1> /*unused*/)
|
||||
-> decltype(arr.reserve(count), void())
|
||||
{
|
||||
arr.reserve(count);
|
||||
}
|
||||
|
||||
template<typename ArrayType>
|
||||
inline void reserve_array_capped(ArrayType& /*arr*/, std::size_t /*count*/, priority_tag<0> /*unused*/)
|
||||
{}
|
||||
|
||||
/*!
|
||||
@brief reports an object or array whose announced size exceeds max_size()
|
||||
|
||||
@@ -342,6 +388,13 @@ struct diagnostic_positions
|
||||
Holds whether a parse error occurred and whether errors are thrown, and
|
||||
implements the parse_error() and is_errored() members of the SAX interface for
|
||||
json_sax_dom_parser and json_sax_dom_callback_parser.
|
||||
|
||||
It also bounds what the parsers reserve for arrays that announce their size
|
||||
(reserve_count()): the announced size is not backed by input yet when the
|
||||
array opens, and the arrays that are open at the same time each keep what was
|
||||
reserved for them, so the binary_reader tells the parser where to find the
|
||||
number of characters it has read (set_input_position()), which the bound
|
||||
is derived from.
|
||||
*/
|
||||
class json_sax_dom_error_state
|
||||
{
|
||||
@@ -375,7 +428,105 @@ class json_sax_dom_error_state
|
||||
return errored;
|
||||
}
|
||||
|
||||
/// bind the number of characters the input has provided so far; see
|
||||
/// @ref reserve_count
|
||||
/// (nullptr: not known, which bounds only the size of each array)
|
||||
void set_input_position(const std::size_t* position) noexcept
|
||||
{
|
||||
input_position = position;
|
||||
credit_position = 0;
|
||||
reserve_credit = position != nullptr ? reserved_elements_base : (std::numeric_limits<std::size_t>::max)();
|
||||
}
|
||||
|
||||
/// what set_input_position() changes, so that a binding can be undone
|
||||
struct reserve_state
|
||||
{
|
||||
const std::size_t* position;
|
||||
std::size_t position_at_refill;
|
||||
std::size_t credit;
|
||||
};
|
||||
|
||||
reserve_state get_reserve_state() const noexcept
|
||||
{
|
||||
return {input_position, credit_position, reserve_credit};
|
||||
}
|
||||
|
||||
void set_reserve_state(const reserve_state& state) noexcept
|
||||
{
|
||||
input_position = state.position;
|
||||
credit_position = state.position_at_refill;
|
||||
reserve_credit = state.credit;
|
||||
}
|
||||
|
||||
protected:
|
||||
/*!
|
||||
@brief the number of elements to reserve for an array that announces @a len
|
||||
|
||||
The announced number is not backed by input when the array opens, and the
|
||||
arrays that are open at the same time each keep what was reserved for
|
||||
them, so what is reserved for all arrays together is bounded by the
|
||||
input read so far: @ref reserved_elements_base plus
|
||||
@ref reserved_elements_per_byte for every character. An array that
|
||||
announces more than what is left of that is given what is left, and
|
||||
grows as its elements arrive. Without the position of the input (the
|
||||
parser is not driven by a binary_reader that is running) nothing is
|
||||
bounded but reserve_cap() for each array.
|
||||
|
||||
The common case, an array whose reservation is no more than the credit
|
||||
left, costs a comparison and a subtraction. An array is charged what is
|
||||
reserved for it, at most reserve_cap() elements, not what it announces, so
|
||||
an array of more elements does not take credit from the arrays nested in
|
||||
it.
|
||||
*/
|
||||
std::size_t reserve_count(const std::size_t len) noexcept
|
||||
{
|
||||
const std::size_t count = (std::min)(len, reserve_cap());
|
||||
if (JSON_HEDLEY_LIKELY(count <= reserve_credit))
|
||||
{
|
||||
reserve_credit -= count;
|
||||
return count;
|
||||
}
|
||||
return reserve_count_slowly(count);
|
||||
}
|
||||
|
||||
private:
|
||||
/// @a count is at most reserve_cap()
|
||||
JSON_HEDLEY_NEVER_INLINE
|
||||
std::size_t reserve_count_slowly(std::size_t count) noexcept
|
||||
{
|
||||
constexpr std::size_t max_size = (std::numeric_limits<std::size_t>::max)();
|
||||
if (input_position == nullptr)
|
||||
{
|
||||
reserve_credit = max_size;
|
||||
return count;
|
||||
}
|
||||
|
||||
// refill the credit with 'reserved_elements_per_byte' for every
|
||||
// character read since the last refill; it saturates instead of
|
||||
// overflowing when size_t is 32 bits wide and a very large input has
|
||||
// been read (the position goes back by up to two in BON8, which has
|
||||
// no sizes)
|
||||
const std::size_t position = *input_position;
|
||||
if (position > credit_position)
|
||||
{
|
||||
const std::size_t bytes = position - credit_position;
|
||||
reserve_credit = bytes <= (max_size - reserve_credit) / reserved_elements_per_byte
|
||||
? reserve_credit + (reserved_elements_per_byte * bytes)
|
||||
: max_size;
|
||||
credit_position = position;
|
||||
}
|
||||
|
||||
count = (std::min)(count, reserve_credit);
|
||||
reserve_credit -= count;
|
||||
return count;
|
||||
}
|
||||
|
||||
/// the number of characters the input has provided so far, if known
|
||||
const std::size_t* input_position = nullptr;
|
||||
/// the number of characters the input had provided when the credit was refilled
|
||||
std::size_t credit_position = 0;
|
||||
/// the number of elements that may still be reserved
|
||||
std::size_t reserve_credit = reserved_elements_base;
|
||||
/// whether a syntax error occurred
|
||||
bool errored = false;
|
||||
/// whether to throw exceptions in case of errors
|
||||
@@ -1210,7 +1361,7 @@ class json_sax_dom_parser : public json_sax_dom_error_state
|
||||
|
||||
if (len != detail::unknown_size())
|
||||
{
|
||||
reserve_array(*ref->m_data.m_value.array, len, priority_tag<1> {});
|
||||
reserve_array_capped(*ref->m_data.m_value.array, reserve_count(len), priority_tag<1> {});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1558,7 +1709,7 @@ class json_sax_dom_binary_parser : public json_sax_dom_error_state
|
||||
|
||||
if (len != detail::unknown_size())
|
||||
{
|
||||
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
|
||||
reserve_array_capped(*ref_stack.back()->m_data.m_value.array, reserve_count(len), priority_tag<1> {});
|
||||
}
|
||||
|
||||
return true;
|
||||
@@ -1850,7 +2001,7 @@ class json_sax_dom_callback_parser : public json_sax_dom_error_state
|
||||
|
||||
if (len != detail::unknown_size())
|
||||
{
|
||||
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
|
||||
reserve_array_capped(*ref_stack.back()->m_data.m_value.array, reserve_count(len), priority_tag<1> {});
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -494,7 +494,10 @@ class lexer : public lexer_base<BasicJsonType>
|
||||
/// streaming adapter: capture the characters
|
||||
void bulk_track_token(const char* data, std::size_t n, std::false_type /*lazy*/)
|
||||
{
|
||||
token_string.insert(token_string.end(), data, data + n);
|
||||
for (std::size_t i = 0; i < n; ++i)
|
||||
{
|
||||
token_string.push_back(static_cast<char_type>(data[i]));
|
||||
}
|
||||
}
|
||||
|
||||
/// streaming input: no bulk fast path
|
||||
@@ -2237,15 +2240,28 @@ scan_number_done:
|
||||
const std::size_t stop = ia.get_consumed_count() - (pending_real_unget ? 1u : 0u);
|
||||
if (JSON_HEDLEY_LIKELY(stop >= token_string_start))
|
||||
{
|
||||
ia.copy_consumed_range(token_string_start, stop, out);
|
||||
// only the beginning and the end of a long token are shown (see
|
||||
// get_token_string), so copy only these
|
||||
constexpr std::size_t head = token_text_buffer<char_type>::head();
|
||||
constexpr std::size_t tail = token_text_buffer<char_type>::tail();
|
||||
if (stop - token_string_start > head + tail)
|
||||
{
|
||||
ia.copy_consumed_range(token_string_start, token_string_start + head, out);
|
||||
ia.copy_consumed_range(stop - tail, stop, out);
|
||||
}
|
||||
else
|
||||
{
|
||||
ia.copy_consumed_range(token_string_start, stop, out);
|
||||
}
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
/// streaming adapter: the token was copied eagerly while scanning
|
||||
const std::vector<char_type>& collect_token_chars(std::vector<char_type>& /*out*/, std::false_type /*lazy*/) const
|
||||
const std::vector<char_type>& collect_token_chars(std::vector<char_type>& out, std::false_type /*lazy*/) const
|
||||
{
|
||||
return token_string;
|
||||
token_string.copy_to(out);
|
||||
return out;
|
||||
}
|
||||
|
||||
/// return the last read token (for errors only). Will never contain EOF
|
||||
@@ -2256,10 +2272,32 @@ scan_number_done:
|
||||
std::vector<char_type> reconstructed;
|
||||
const std::vector<char_type>& chars = collect_token_chars(reconstructed, std::integral_constant<bool, lazy_token_string> {});
|
||||
|
||||
// escape control characters
|
||||
// a long token is shown by its first and its last head() characters;
|
||||
// the buffers that keep it while it is read keep no more than these
|
||||
// and a few more (see token_text_buffer)
|
||||
constexpr std::size_t shown = token_text_buffer<char_type>::head();
|
||||
std::string result;
|
||||
for (const auto c : chars)
|
||||
if (chars.size() > 2 * shown)
|
||||
{
|
||||
append_escaped(result, chars.begin(), chars.begin() + static_cast<std::ptrdiff_t>(shown));
|
||||
result += "...";
|
||||
append_escaped(result, chars.end() - static_cast<std::ptrdiff_t>(shown), chars.end());
|
||||
}
|
||||
else
|
||||
{
|
||||
append_escaped(result, chars.begin(), chars.end());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
private:
|
||||
/// append the characters [first, last) to @a result, escaping control characters
|
||||
template<typename Iterator>
|
||||
static void append_escaped(std::string& result, Iterator first, Iterator last)
|
||||
{
|
||||
for (; first != last; ++first)
|
||||
{
|
||||
const auto c = *first;
|
||||
if (static_cast<unsigned char>(c) <= '\x1F')
|
||||
{
|
||||
// escape control characters
|
||||
@@ -2273,10 +2311,10 @@ scan_number_done:
|
||||
result.push_back(static_cast<std::string::value_type>(c));
|
||||
}
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
public:
|
||||
|
||||
/// return syntax error message
|
||||
JSON_HEDLEY_RETURNS_NON_NULL
|
||||
constexpr const char* get_error_message() const noexcept
|
||||
@@ -2525,7 +2563,7 @@ scan_number_done:
|
||||
|
||||
/// raw input token string for error messages; only populated for streaming
|
||||
/// adapters (seekable adapters reconstruct it lazily via token_string_start)
|
||||
std::vector<char_type> token_string {};
|
||||
token_text_buffer<char_type> token_string {};
|
||||
|
||||
/// start offset of the current token within the input, used to reconstruct
|
||||
/// the last read token on error for seekable adapters (see collect_token_chars)
|
||||
|
||||
@@ -257,7 +257,7 @@ struct ieee_binary_format<53> // binary64
|
||||
|
||||
These formats (float, double, and long double where it is binary64, e.g.
|
||||
with MSVC or on Apple arm64) are converted by parse_float_native(). The
|
||||
predicate is the one the serializer uses to choose Grisu2.
|
||||
predicate is the one the serializer uses to choose to_chars() over snprintf.
|
||||
*/
|
||||
template<typename FloatType>
|
||||
struct has_native_float_format
|
||||
|
||||
@@ -108,7 +108,9 @@ class json_reverse_iterator : public std::reverse_iterator<Base>
|
||||
/// access to successor
|
||||
reference operator[](difference_type n) const
|
||||
{
|
||||
return *(this->operator+(n));
|
||||
// the element n positions after *this is the one n + 1 positions before base();
|
||||
// Base::operator[] then reports invalid_iterator.208 for object iterators
|
||||
return this->base()[-n - 1];
|
||||
}
|
||||
|
||||
/// return the key of an object iterator
|
||||
|
||||
@@ -852,139 +852,6 @@ class json_pointer
|
||||
}
|
||||
|
||||
private:
|
||||
/*!
|
||||
@brief the pointer prefixes of a flattened object that denote arrays
|
||||
|
||||
@ref unflatten creates arrays exactly below the prefixes that have a
|
||||
reference token 0 among their children, and objects everywhere else.
|
||||
Deciding this up front keeps the result independent of the order in which
|
||||
the flattened object is iterated, which is unspecified for some object
|
||||
types.
|
||||
|
||||
A prefix is identified by the text of the key it is the beginning of:
|
||||
escaping is unambiguous, so equal prefixes of valid keys are equal texts.
|
||||
The set refers to the keys, which must outlive it.
|
||||
*/
|
||||
class array_prefix_set
|
||||
{
|
||||
public:
|
||||
void insert(const char* data, std::size_t size)
|
||||
{
|
||||
// flattened objects are usually sorted, so most keys that have a
|
||||
// 0 yield the prefix of the previous one
|
||||
if (last_data != nullptr && last_size == size && std::memcmp(last_data, data, size) == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
last_data = data;
|
||||
last_size = size;
|
||||
|
||||
if (table.empty())
|
||||
{
|
||||
table.resize(16);
|
||||
}
|
||||
const std::size_t hash = hash_of(data, size);
|
||||
const std::size_t mask = table.size() - 1;
|
||||
std::size_t i = hash & mask;
|
||||
while (table[i].data != nullptr)
|
||||
{
|
||||
if (table[i].hash == hash && table[i].size == size && std::memcmp(table[i].data, data, size) == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
i = (i + 1) & mask;
|
||||
}
|
||||
table[i] = slot(hash, data, size);
|
||||
|
||||
// keep the load factor below 1/2
|
||||
if (++used * 2 > table.size())
|
||||
{
|
||||
grow();
|
||||
}
|
||||
}
|
||||
|
||||
bool empty() const noexcept
|
||||
{
|
||||
return used == 0;
|
||||
}
|
||||
|
||||
bool contains(const char* data, std::size_t size) const noexcept
|
||||
{
|
||||
if (used == 0)
|
||||
{
|
||||
return false;
|
||||
}
|
||||
const std::size_t hash = hash_of(data, size);
|
||||
const std::size_t mask = table.size() - 1;
|
||||
for (std::size_t i = hash & mask; table[i].data != nullptr; i = (i + 1) & mask)
|
||||
{
|
||||
if (table[i].hash == hash && table[i].size == size && std::memcmp(table[i].data, data, size) == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
private:
|
||||
struct slot
|
||||
{
|
||||
slot() noexcept = default;
|
||||
|
||||
slot(std::size_t h, const char* d, std::size_t s) noexcept
|
||||
: hash(h), data(d), size(s)
|
||||
{}
|
||||
|
||||
std::size_t hash = 0;
|
||||
const char* data = nullptr; // nullptr: the slot is empty
|
||||
std::size_t size = 0;
|
||||
};
|
||||
|
||||
static std::size_t hash_of(const char* data, std::size_t size) noexcept
|
||||
{
|
||||
std::uint64_t h = 0x9E3779B97F4A7C15ULL ^ size;
|
||||
std::size_t i = 0;
|
||||
for (; i + 8 <= size; i += 8)
|
||||
{
|
||||
std::uint64_t w = 0;
|
||||
std::memcpy(&w, data + i, 8);
|
||||
h = (h ^ w) * 0x100000001B3ULL;
|
||||
h ^= h >> 32u;
|
||||
}
|
||||
std::uint64_t w = 0;
|
||||
if (i < size)
|
||||
{
|
||||
std::memcpy(&w, data + i, size - i);
|
||||
}
|
||||
h = (h ^ w) * 0x9E3779B97F4A7C15ULL;
|
||||
return detail::conditional_static_cast<std::size_t>(h ^ (h >> 29u));
|
||||
}
|
||||
|
||||
void grow()
|
||||
{
|
||||
std::vector<slot> old(table.size() * 2);
|
||||
old.swap(table);
|
||||
const std::size_t mask = table.size() - 1;
|
||||
for (const auto& s : old)
|
||||
{
|
||||
if (s.data != nullptr)
|
||||
{
|
||||
std::size_t i = s.hash & mask;
|
||||
while (table[i].data != nullptr)
|
||||
{
|
||||
i = (i + 1) & mask;
|
||||
}
|
||||
table[i] = s;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
std::vector<slot> table{};
|
||||
std::size_t used = 0;
|
||||
const char* last_data = nullptr;
|
||||
std::size_t last_size = 0;
|
||||
};
|
||||
|
||||
/// @brief the length of the longest common prefix of the first @a limit bytes of @a a and @a b
|
||||
static std::size_t common_prefix_length(const char* a, const char* b, const std::size_t limit) noexcept
|
||||
{
|
||||
@@ -1007,6 +874,355 @@ class json_pointer
|
||||
return i;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief the prefixes of a flattened object that are marked as arrays, for
|
||||
prefixes that are not short
|
||||
|
||||
A prefix is identified by the tokens it consists of: a node of a tree
|
||||
stands for the prefix of its parent followed by a token, and is looked up
|
||||
by its parent and the text of the token. The node of a prefix is found by
|
||||
walking the tokens of the key from the root, so identifying all prefixes
|
||||
of a key together costs one pass over the key, however long the prefixes
|
||||
are, and no prefix is ever compared byte by byte as a whole. The nodes
|
||||
along the key that was walked last are kept, and the walk of the next key
|
||||
starts below the beginning it has in common with that key. The tree refers
|
||||
to the keys, which must outlive it.
|
||||
*/
|
||||
class prefix_tree
|
||||
{
|
||||
public:
|
||||
/// @brief set the seed of the hash function, before anything is added
|
||||
void reseed(const std::uint64_t seed_value) noexcept
|
||||
{
|
||||
seed = seed_value;
|
||||
}
|
||||
|
||||
/// @brief mark the first @a prefix_size bytes of the key of @a key_size bytes at @a data
|
||||
void mark(const char* data, std::size_t key_size, std::size_t prefix_size)
|
||||
{
|
||||
nodes[walk(data, key_size, prefix_size)].marked = true;
|
||||
any_marked = true;
|
||||
}
|
||||
|
||||
bool is_marked(const char* data, std::size_t key_size, std::size_t prefix_size)
|
||||
{
|
||||
return any_marked && nodes[walk(data, key_size, prefix_size)].marked;
|
||||
}
|
||||
|
||||
bool empty() const noexcept
|
||||
{
|
||||
return !any_marked;
|
||||
}
|
||||
|
||||
/// @brief the hash of the first @a size bytes at @a data, for the seed @a seed_value
|
||||
static std::size_t hash_bytes(const char* data, std::size_t size, const std::uint64_t seed_value) noexcept
|
||||
{
|
||||
std::uint64_t h = seed_value ^ size;
|
||||
std::size_t i = 0;
|
||||
for (; i + 8 <= size; i += 8)
|
||||
{
|
||||
std::uint64_t w = 0;
|
||||
std::memcpy(&w, data + i, 8);
|
||||
h = (h ^ w) * 0x100000001B3ULL;
|
||||
h ^= h >> 32u;
|
||||
}
|
||||
std::uint64_t w = 0;
|
||||
if (i < size)
|
||||
{
|
||||
std::memcpy(&w, data + i, size - i);
|
||||
}
|
||||
h = (h ^ w) * 0x9E3779B97F4A7C15ULL;
|
||||
return detail::conditional_static_cast<std::size_t>(h ^ (h >> 29u));
|
||||
}
|
||||
|
||||
private:
|
||||
struct node
|
||||
{
|
||||
std::size_t parent = 0;
|
||||
std::size_t hash = 0;
|
||||
const char* token = nullptr;
|
||||
std::size_t token_size = 0;
|
||||
bool marked = false;
|
||||
};
|
||||
|
||||
/// @brief a slot of the hash table; the index of a node, 0 if the slot is empty
|
||||
struct bucket
|
||||
{
|
||||
std::size_t index = 0;
|
||||
};
|
||||
|
||||
/// @brief the node after a token of the key that was walked last, and where the token ends
|
||||
struct step
|
||||
{
|
||||
std::size_t node = 0;
|
||||
std::size_t end = 0;
|
||||
};
|
||||
|
||||
/// @brief the index of the node of the prefix that ends at the slash (or the end) at @a prefix_size
|
||||
std::size_t walk(const char* data, std::size_t key_size, std::size_t prefix_size)
|
||||
{
|
||||
if (nodes.empty())
|
||||
{
|
||||
nodes.emplace_back();
|
||||
table.resize(16);
|
||||
chain.emplace_back();
|
||||
}
|
||||
|
||||
if (data != last_key)
|
||||
{
|
||||
// keep the nodes within the beginning that this key has in common
|
||||
// with the key they were found for; a prefix that ends inside a
|
||||
// token of this key is not one of its prefixes
|
||||
const std::size_t same = common_prefix_length(data, last_key, (std::min)(key_size, last_key_size));
|
||||
std::size_t keep = chain.size();
|
||||
while (keep > 1 && (chain[keep - 1].end > same || (chain[keep - 1].end == same && same < key_size && data[same] != '/')))
|
||||
{
|
||||
--keep;
|
||||
}
|
||||
chain.resize(keep);
|
||||
last_key = data;
|
||||
last_key_size = key_size;
|
||||
}
|
||||
|
||||
// walk the tokens that are not walked yet
|
||||
while (chain.back().end < prefix_size && chain.back().end < key_size)
|
||||
{
|
||||
const std::size_t start = chain.back().end + 1;
|
||||
const void* const slash = std::memchr(data + start, '/', key_size - start);
|
||||
const std::size_t end = slash == nullptr ? key_size : static_cast<std::size_t>(static_cast<const char*>(slash) - data);
|
||||
step next;
|
||||
next.node = child(chain.back().node, data + start, end - start);
|
||||
next.end = end;
|
||||
chain.push_back(next);
|
||||
}
|
||||
|
||||
if (chain.back().end == prefix_size)
|
||||
{
|
||||
return chain.back().node;
|
||||
}
|
||||
// an earlier call walked further
|
||||
const auto it = std::lower_bound(chain.begin(), chain.end(), prefix_size, [](const step & s, std::size_t size)
|
||||
{
|
||||
return s.end < size;
|
||||
});
|
||||
return it->node;
|
||||
}
|
||||
|
||||
std::size_t slot_of(std::size_t parent, std::size_t hash) const noexcept
|
||||
{
|
||||
std::uint64_t x = static_cast<std::uint64_t>(hash) ^ (static_cast<std::uint64_t>(parent) * 0x9E3779B97F4A7C15ULL);
|
||||
x ^= x >> 32u;
|
||||
x *= 0xD6E8FEB86659FD93ULL;
|
||||
x ^= x >> 32u;
|
||||
return static_cast<std::size_t>(x) & (table.size() - 1);
|
||||
}
|
||||
|
||||
/// @brief the node of the prefix of the node @a parent followed by the token, which is added if it is not there
|
||||
std::size_t child(std::size_t parent, const char* token, std::size_t token_size)
|
||||
{
|
||||
const std::size_t hash = hash_bytes(token, token_size, seed);
|
||||
std::size_t i = slot_of(parent, hash);
|
||||
while (table[i].index != 0)
|
||||
{
|
||||
const node& n = nodes[table[i].index];
|
||||
if (n.parent == parent && n.hash == hash && n.token_size == token_size && std::memcmp(n.token, token, token_size) == 0)
|
||||
{
|
||||
return table[i].index;
|
||||
}
|
||||
i = (i + 1) & (table.size() - 1);
|
||||
}
|
||||
|
||||
node created;
|
||||
created.parent = parent;
|
||||
created.hash = hash;
|
||||
created.token = token;
|
||||
created.token_size = token_size;
|
||||
nodes.push_back(created);
|
||||
table[i].index = nodes.size() - 1;
|
||||
|
||||
// keep the load factor below 1/2
|
||||
if (nodes.size() * 2 > table.size())
|
||||
{
|
||||
std::vector<bucket> old(table.size() * 2);
|
||||
old.swap(table);
|
||||
for (std::size_t k = 1; k < nodes.size(); ++k)
|
||||
{
|
||||
std::size_t j = slot_of(nodes[k].parent, nodes[k].hash);
|
||||
while (table[j].index != 0)
|
||||
{
|
||||
j = (j + 1) & (table.size() - 1);
|
||||
}
|
||||
table[j].index = k;
|
||||
}
|
||||
}
|
||||
return nodes.size() - 1;
|
||||
}
|
||||
|
||||
std::uint64_t seed = 0;
|
||||
/// @brief the nodes; the first is the root, the empty prefix
|
||||
std::vector<node> nodes{};
|
||||
/// @brief the nodes (not the root) in a hash table
|
||||
std::vector<bucket> table{};
|
||||
/// @brief the root, and the node after each token of the key that was walked last
|
||||
std::vector<step> chain{};
|
||||
const char* last_key = nullptr;
|
||||
std::size_t last_key_size = 0;
|
||||
bool any_marked = false;
|
||||
};
|
||||
|
||||
/*!
|
||||
@brief the pointer prefixes of a flattened object that denote arrays
|
||||
|
||||
@ref unflatten creates arrays exactly below the prefixes that have a
|
||||
reference token 0 among their children, and objects everywhere else.
|
||||
Deciding this up front keeps the result independent of the order in which
|
||||
the flattened object is iterated, which is unspecified for some object
|
||||
types.
|
||||
|
||||
A prefix is identified by the text of the key it is the beginning of:
|
||||
escaping is unambiguous, so equal prefixes of valid keys are equal texts.
|
||||
The set refers to the keys, which must outlive it. Short prefixes are
|
||||
kept in a hash table and compared as texts, which costs at most the length
|
||||
of the bound. Longer prefixes are kept in a @ref prefix_tree, because
|
||||
hashing and comparing every one of the prefixes of a key with many tokens
|
||||
from its beginning would take quadratic time.
|
||||
|
||||
The hash function depends on a seed that is derived from the address of a
|
||||
local variable, which address space layout randomization changes between
|
||||
processes, so keys cannot be crafted to collide in advance; the result
|
||||
does not depend on the seed. Where the addresses are not randomized, or
|
||||
when the seed is known, keys can collide: k short prefixes then cost
|
||||
k^2 / 2 comparisons of fewer than 64 bytes each. The long prefixes are not
|
||||
hashed as a whole.
|
||||
*/
|
||||
class array_prefix_set
|
||||
{
|
||||
public:
|
||||
/// @brief choose the seed of the hash function, before anything is added: it is derived from the address that is passed
|
||||
void reseed(const void* address) noexcept
|
||||
{
|
||||
// NOLINTNEXTLINE(cppcoreguidelines-pro-type-reinterpret-cast,hicpp-use-auto,modernize-use-auto): the address is only a source of entropy
|
||||
std::uint64_t x = reinterpret_cast<std::uintptr_t>(address);
|
||||
x ^= 0x9E3779B97F4A7C15ULL;
|
||||
x *= 0xBF58476D1CE4E5B9ULL;
|
||||
seed = x ^ (x >> 31u);
|
||||
tree.reseed(seed);
|
||||
}
|
||||
|
||||
/// @brief add the first @a prefix_size bytes of the key of @a key_size bytes at @a data
|
||||
void insert(const char* data, std::size_t key_size, std::size_t prefix_size)
|
||||
{
|
||||
if (prefix_size >= short_limit)
|
||||
{
|
||||
tree.mark(data, key_size, prefix_size);
|
||||
return;
|
||||
}
|
||||
|
||||
// flattened objects are usually sorted, so most keys that have a
|
||||
// 0 yield the prefix of the previous one
|
||||
if (last_data != nullptr && last_size == prefix_size && std::memcmp(last_data, data, prefix_size) == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
last_data = data;
|
||||
last_size = prefix_size;
|
||||
|
||||
const std::size_t hash = prefix_tree::hash_bytes(data, prefix_size, seed);
|
||||
if (table.empty())
|
||||
{
|
||||
table.resize(16);
|
||||
}
|
||||
const std::size_t mask = table.size() - 1;
|
||||
std::size_t i = hash & mask;
|
||||
while (table[i].data != nullptr)
|
||||
{
|
||||
if (table[i].hash == hash && table[i].size == prefix_size && std::memcmp(table[i].data, data, prefix_size) == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
i = (i + 1) & mask;
|
||||
}
|
||||
table[i] = slot(hash, data, prefix_size);
|
||||
|
||||
// keep the load factor below 1/2
|
||||
if (++used * 2 > table.size())
|
||||
{
|
||||
grow();
|
||||
}
|
||||
}
|
||||
|
||||
bool empty() const noexcept
|
||||
{
|
||||
return used == 0 && tree.empty();
|
||||
}
|
||||
|
||||
/// @brief whether the first @a prefix_size bytes of the key of @a key_size bytes at @a data were added
|
||||
bool contains(const char* data, std::size_t key_size, std::size_t prefix_size)
|
||||
{
|
||||
if (prefix_size >= short_limit)
|
||||
{
|
||||
return tree.is_marked(data, key_size, prefix_size);
|
||||
}
|
||||
if (used == 0)
|
||||
{
|
||||
return false;
|
||||
}
|
||||
const std::size_t hash = prefix_tree::hash_bytes(data, prefix_size, seed);
|
||||
const std::size_t mask = table.size() - 1;
|
||||
for (std::size_t i = hash & mask; table[i].data != nullptr; i = (i + 1) & mask)
|
||||
{
|
||||
if (table[i].hash == hash && table[i].size == prefix_size && std::memcmp(table[i].data, data, prefix_size) == 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
private:
|
||||
/// @brief prefixes of fewer bytes are kept in the hash table
|
||||
static constexpr std::size_t short_limit = 64;
|
||||
|
||||
struct slot
|
||||
{
|
||||
slot() noexcept = default;
|
||||
|
||||
slot(std::size_t h, const char* d, std::size_t s) noexcept
|
||||
: hash(h), data(d), size(s)
|
||||
{}
|
||||
|
||||
std::size_t hash = 0;
|
||||
const char* data = nullptr; // nullptr: the slot is empty
|
||||
std::size_t size = 0;
|
||||
};
|
||||
|
||||
void grow()
|
||||
{
|
||||
std::vector<slot> old(table.size() * 2);
|
||||
old.swap(table);
|
||||
const std::size_t mask = table.size() - 1;
|
||||
for (const auto& s : old)
|
||||
{
|
||||
if (s.data != nullptr)
|
||||
{
|
||||
std::size_t i = s.hash & mask;
|
||||
while (table[i].data != nullptr)
|
||||
{
|
||||
i = (i + 1) & mask;
|
||||
}
|
||||
table[i] = s;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
std::uint64_t seed = 0;
|
||||
prefix_tree tree{};
|
||||
std::vector<slot> table{};
|
||||
std::size_t used = 0;
|
||||
const char* last_data = nullptr;
|
||||
std::size_t last_size = 0;
|
||||
};
|
||||
|
||||
/*!
|
||||
@brief check that @a key is a valid JSON pointer, and add the prefixes of
|
||||
it that denote arrays to @a arrays
|
||||
@@ -1052,7 +1268,7 @@ class json_pointer
|
||||
// a token 0 makes the pointer before it an array
|
||||
if (i - begin == 1 && data[begin] == '0')
|
||||
{
|
||||
arrays.insert(data, begin - 1);
|
||||
arrays.insert(data, size, begin - 1);
|
||||
}
|
||||
begin = i + 1;
|
||||
}
|
||||
@@ -2095,6 +2311,7 @@ class json_pointer
|
||||
// token 0 among their children; the values below them are arrays,
|
||||
// all others are objects (see array_prefix_set)
|
||||
array_prefix_set arrays;
|
||||
arrays.reseed(&arrays);
|
||||
const string_t* previous_key = nullptr;
|
||||
for (const auto& element : *value.m_data.m_value.object)
|
||||
{
|
||||
@@ -2186,7 +2403,7 @@ class json_pointer
|
||||
case detail::value_t::null:
|
||||
{
|
||||
// a first child 0 makes the value an array without a look-up
|
||||
if ((token_size == 1 && data[pos + 1] == '0') || arrays.contains(data, pos))
|
||||
if ((token_size == 1 && data[pos + 1] == '0') || arrays.contains(data, key.size(), pos))
|
||||
{
|
||||
// some reference token below this position is 0, so the
|
||||
// value is an array
|
||||
@@ -2238,6 +2455,19 @@ class json_pointer
|
||||
pos = end;
|
||||
}
|
||||
|
||||
if (JSON_HEDLEY_UNLIKELY(!current->is_null()))
|
||||
{
|
||||
// the key is a prefix of an earlier key (only possible if the
|
||||
// object type does not sort its keys), so the value is the
|
||||
// array or object built for that key: a null leaves it as it
|
||||
// is (as when the shorter key comes first), any other value
|
||||
// conflicts with it
|
||||
if (element.second.is_null())
|
||||
{
|
||||
continue;
|
||||
}
|
||||
JSON_THROW(detail::type_error::create(detail::exception_id::unflatten_invalid_value, "invalid value to unflatten", &result));
|
||||
}
|
||||
*current = element.second;
|
||||
}
|
||||
|
||||
|
||||
@@ -230,6 +230,16 @@
|
||||
// detail/recursion_depth_limit.hpp. Like JSON_NO_THREAD_LOCAL it is neither part
|
||||
// of the ABI tag nor undefined at the end of json.hpp.
|
||||
|
||||
// forced inlining of the serializer's helpers only in optimized builds: at -O0,
|
||||
// GCC and Clang give every inlined copy its own stack slots, which made the
|
||||
// recursive frame of serializer::dump_container() about 2.3 KB (MSVC does not
|
||||
// expand __forceinline at /Ob0, so it keeps it)
|
||||
#if defined(__OPTIMIZE__) || defined(_MSC_VER)
|
||||
#define JSON_INTERNAL_SERIALIZER_INLINE JSON_HEDLEY_ALWAYS_INLINE
|
||||
#else
|
||||
#define JSON_INTERNAL_SERIALIZER_INLINE inline
|
||||
#endif
|
||||
|
||||
// allow disabling exceptions
|
||||
#if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
|
||||
#define JSON_THROW(exception) throw exception
|
||||
@@ -923,3 +933,14 @@
|
||||
#ifndef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
|
||||
#define JSON_DISABLE_TUPLE_REFERENCE_CONVERSION 0
|
||||
#endif
|
||||
|
||||
// JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE: how many elements of optimized
|
||||
// UBJSON containers of type Z, T or F (which have no payload) a reader accepts
|
||||
// per byte of input, on top of a fixed base. The value is checked and converted
|
||||
// in binary_reader.hpp; the macro is documented in
|
||||
// docs/mkdocs/docs/api/macros/json_ubjson_valueless_elements_per_byte.md.
|
||||
// It is not part of the ABI tag: it must have the same value in every
|
||||
// translation unit of a program.
|
||||
#ifndef JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE
|
||||
#define JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE 4
|
||||
#endif
|
||||
@@ -11,6 +11,7 @@
|
||||
// clean up
|
||||
#undef JSON_ASSERT
|
||||
#undef JSON_INTERNAL_CATCH
|
||||
#undef JSON_INTERNAL_SERIALIZER_INLINE
|
||||
#undef JSON_THROW
|
||||
#undef JSON_PRIVATE_UNLESS_TESTED
|
||||
#undef NLOHMANN_BASIC_JSON_TPL_DECLARATION
|
||||
@@ -60,6 +61,7 @@
|
||||
#undef JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS
|
||||
#undef JSON_DISABLE_STREAM_BULK_SCAN
|
||||
#undef JSON_DISABLE_UNLOCKED_FILE_IO
|
||||
#undef JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE
|
||||
#endif
|
||||
|
||||
#include <nlohmann/thirdparty/hedley/hedley_undef.hpp>
|
||||
@@ -915,7 +915,7 @@ class binary_writer
|
||||
JSON_THROW(out_of_range::create(exception_id::subtype_out_of_range, concat("subtype ", std::to_string(subtype), " is too large for ", what, " (max 255)"), &j));
|
||||
}
|
||||
|
||||
/// @throw other_error.407 always
|
||||
/// @throw other_error.502 always
|
||||
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE
|
||||
static void throw_size_marker_required(const BasicJsonType& j)
|
||||
{
|
||||
@@ -1169,6 +1169,14 @@ 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
|
||||
@@ -1204,20 +1212,29 @@ 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 and refuses an excessive one. Write the unoptimized form for
|
||||
// those, at one byte per element, so the result can be read back.
|
||||
// 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
|
||||
// JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE 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, whatever the macro is set to, so the writer does not use
|
||||
// it (and a reader with a larger rate reads this output as well).
|
||||
// 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)))
|
||||
if (same_prefix && !(use_bjdata && is_bjdata_excluded_type_marker(first_prefix)))
|
||||
{
|
||||
prefix_required = false;
|
||||
oa.write_character(to_char_type('$'));
|
||||
oa.write_character(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;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5441,6 +5458,10 @@ 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
|
||||
|
||||
@@ -265,7 +265,7 @@ class serializer
|
||||
for a container; writing them from here spares each the entry and exit of
|
||||
that function.
|
||||
*/
|
||||
JSON_HEDLEY_ALWAYS_INLINE void dump_element(const BasicJsonType& val,
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void dump_element(const BasicJsonType& val,
|
||||
const std::size_t current_indent,
|
||||
const std::size_t depth)
|
||||
{
|
||||
@@ -636,7 +636,7 @@ class serializer
|
||||
put_literal("\"subtype\": ");
|
||||
if (binary.has_subtype())
|
||||
{
|
||||
dump_integer(binary.subtype());
|
||||
dump_subtype(binary.subtype());
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -662,7 +662,7 @@ class serializer
|
||||
put_literal("],\"subtype\":");
|
||||
if (binary.has_subtype())
|
||||
{
|
||||
dump_integer(binary.subtype());
|
||||
dump_subtype(binary.subtype());
|
||||
put_char('}');
|
||||
}
|
||||
else
|
||||
@@ -971,7 +971,7 @@ class serializer
|
||||
}
|
||||
|
||||
/// write out the bytes pending in @ref string_buffer and reset @a bytes
|
||||
JSON_HEDLEY_ALWAYS_INLINE void emit_pending(std::size_t& bytes)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void emit_pending(std::size_t& bytes)
|
||||
{
|
||||
if (bytes != 0)
|
||||
{
|
||||
@@ -983,7 +983,7 @@ class serializer
|
||||
/// write buffer and reset index if fewer than 13 bytes are left, as this
|
||||
/// is the maximal number of bytes to be written ("\uxxxx\uxxxx\0") for one
|
||||
/// code point
|
||||
JSON_HEDLEY_ALWAYS_INLINE void reserve_string_buffer(std::size_t& bytes)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void reserve_string_buffer(std::size_t& bytes)
|
||||
{
|
||||
if (string_buffer.size() - bytes < 13)
|
||||
{
|
||||
@@ -1344,7 +1344,7 @@ class serializer
|
||||
inlining both into the pretty-printing loops once @ref dump_escaped
|
||||
has grown, which made indented output up to 13% slower
|
||||
*/
|
||||
JSON_HEDLEY_ALWAYS_INLINE void put_indent(std::size_t indent)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void put_indent(std::size_t indent)
|
||||
{
|
||||
// closing braces at the outermost level ask for no indentation at all
|
||||
if (indent == 0)
|
||||
@@ -1398,7 +1398,7 @@ class serializer
|
||||
its room and four stores of the indentation, see @ref put_short_literal_indent.
|
||||
*/
|
||||
template<std::size_t N>
|
||||
JSON_HEDLEY_ALWAYS_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void put_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
{
|
||||
if (JSON_HEDLEY_LIKELY(put_short_literal_indent(s, indent)))
|
||||
{
|
||||
@@ -1418,7 +1418,7 @@ class serializer
|
||||
@a indent is wider or the write buffer lacks the room.
|
||||
*/
|
||||
template<std::size_t N>
|
||||
JSON_HEDLEY_ALWAYS_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE bool put_short_literal_indent(const char (&s)[N], const std::size_t indent) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
{
|
||||
constexpr std::size_t length = N - 1;
|
||||
if (indent > 32 || write_buffer_pos + length + 32 > write_buffer.size())
|
||||
@@ -1445,7 +1445,7 @@ class serializer
|
||||
write-through path for oversized runs.
|
||||
*/
|
||||
template<std::size_t N>
|
||||
JSON_HEDLEY_ALWAYS_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
JSON_INTERNAL_SERIALIZER_INLINE void put_literal(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
|
||||
{
|
||||
static_assert(N >= 2, "put_literal expects a non-empty string literal");
|
||||
// the array bound counts the terminating NUL, which is not written
|
||||
@@ -1571,7 +1571,7 @@ class serializer
|
||||
{
|
||||
return n_digits + 3;
|
||||
}
|
||||
x = x / 10000u;
|
||||
x = static_cast<number_magnitude_t>(x / 10000u);
|
||||
n_digits += 4;
|
||||
}
|
||||
}
|
||||
@@ -1883,6 +1883,40 @@ class serializer
|
||||
write_buffer_pos = pos;
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief dump the subtype of a binary value
|
||||
|
||||
The subtype is a std::uint64_t, whatever the number types are. @ref
|
||||
dump_integer converts its argument to the magnitude type of
|
||||
number_unsigned_t, so it writes the subtype only if that type has at least
|
||||
64 bits; otherwise (it would truncate the subtype) the digits are written
|
||||
one by one.
|
||||
|
||||
@param[in] subtype the subtype to dump
|
||||
*/
|
||||
void dump_subtype(std::uint64_t subtype)
|
||||
{
|
||||
dump_subtype(subtype, std::integral_constant<bool, magnitude_has_at_least_64_bits> {});
|
||||
}
|
||||
|
||||
void dump_subtype(std::uint64_t subtype, std::true_type /*magnitude has at least 64 bits*/)
|
||||
{
|
||||
dump_integer(subtype);
|
||||
}
|
||||
|
||||
void dump_subtype(std::uint64_t subtype, std::false_type /*magnitude has less than 64 bits*/)
|
||||
{
|
||||
std::array<char, 20> digits{{}}; // 2^64 - 1 has 20 digits
|
||||
std::size_t start = digits.size();
|
||||
do
|
||||
{
|
||||
digits[--start] = static_cast<char>('0' + (subtype % 10));
|
||||
subtype /= 10;
|
||||
}
|
||||
while (subtype != 0);
|
||||
put_string(digits, start, digits.size());
|
||||
}
|
||||
|
||||
/*!
|
||||
@brief dump an integer
|
||||
|
||||
@@ -2033,8 +2067,9 @@ class serializer
|
||||
}
|
||||
|
||||
// If number_float_t is an IEEE-754 single or double precision number,
|
||||
// use the Grisu2 algorithm to produce short numbers which are
|
||||
// guaranteed to round-trip, using strtof and strtod, resp.
|
||||
// use to_chars() to produce short numbers which are guaranteed to
|
||||
// round-trip, using strtof and strtod, resp. (the shortest digits of
|
||||
// Zmij for binary64, the Grisu2 algorithm for binary32).
|
||||
//
|
||||
// NB: The test below works if <long double> == <double>.
|
||||
static constexpr bool is_ieee_single_or_double
|
||||
@@ -2136,6 +2171,11 @@ class serializer
|
||||
static constexpr bool magnitude_has_at_most_64_bits = std::numeric_limits<number_magnitude_t>::is_specialized
|
||||
&& std::numeric_limits<number_magnitude_t>::digits <= 64;
|
||||
|
||||
/// whether every std::uint64_t fits number_magnitude_t (then dump_integer
|
||||
/// can write a binary subtype)
|
||||
static constexpr bool magnitude_has_at_least_64_bits = std::numeric_limits<number_magnitude_t>::is_specialized
|
||||
&& std::numeric_limits<number_magnitude_t>::digits >= 64;
|
||||
|
||||
/// whether @a x fits 64 bits: always if number_magnitude_t has at most
|
||||
/// 64 bits (selected by type, as the comparison would be reported as
|
||||
/// always true), else compared
|
||||
@@ -2161,7 +2201,7 @@ class serializer
|
||||
number_magnitude_t remove_sign(number_integer_t x) noexcept
|
||||
{
|
||||
JSON_ASSERT(x < 0);
|
||||
return static_cast<number_magnitude_t>(-(x + 1)) + 1;
|
||||
return static_cast<number_magnitude_t>(static_cast<number_magnitude_t>(-(x + 1)) + 1);
|
||||
}
|
||||
|
||||
private:
|
||||
|
||||
@@ -384,9 +384,22 @@ class editor
|
||||
// for the container is linear in the size of the document, so
|
||||
// links (which are marked in the slot) avoid it.
|
||||
node* const p = parent_known ? parent : find_parent(m_doc, slot);
|
||||
if (p != nullptr && ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0))
|
||||
if (p != nullptr)
|
||||
{
|
||||
block_of(m_doc, p, 0);
|
||||
if ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0)
|
||||
{
|
||||
block_of(m_doc, p, 0);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
// the slot is no longer part of the document, but the
|
||||
// (dropped) container it is in may still step over it
|
||||
node* const q = find_layout_parent(m_doc, slot);
|
||||
if (q != nullptr)
|
||||
{
|
||||
block_of(m_doc, q, 0);
|
||||
}
|
||||
}
|
||||
}
|
||||
*slot = e.scalar;
|
||||
|
||||
@@ -194,7 +194,9 @@ inline node* block_of(document_data& d, node* n, std::size_t extra)
|
||||
h->len = n->len;
|
||||
h->next = static_cast<std::uint32_t>(used);
|
||||
node* o = h + 1;
|
||||
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n); c != e;)
|
||||
// (the bound on o keeps the copy inside the block even if the elements
|
||||
// disagreed with the element count)
|
||||
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n), *const full = h + used; c != e && o != full;)
|
||||
{
|
||||
if (object)
|
||||
{
|
||||
@@ -276,6 +278,41 @@ inline node* find_parent(const document_data& d, const node* target)
|
||||
}
|
||||
}
|
||||
|
||||
/// The container whose contiguous layout (in the parsed index, or in a new
|
||||
/// value) steps over `target`, also when an edit dropped the container or a
|
||||
/// value that encloses it; nullptr if there is none, or if the container no
|
||||
/// longer walks that layout (its elements moved). An edit never gives a node a
|
||||
/// larger extent than it was parsed or encoded with (a scalar is one node, an
|
||||
/// assigned array/object keeps the extent of the slot), so the containers whose
|
||||
/// extent covers `target` are its original ancestors: the nearest one before it
|
||||
/// is its original parent. The root of a new value that is the element sequence
|
||||
/// of another container is walked by that container (which find_parent() finds
|
||||
/// while it still uses the sequence), not by itself.
|
||||
inline node* find_layout_parent(const document_data& d, const node* target)
|
||||
{
|
||||
const std::less<const node*> lt{};
|
||||
const node* lo = d.nodes;
|
||||
if (lt(target, lo) || !lt(target, d.nodes + d.node_count))
|
||||
{
|
||||
auto it = d.edits->regions.upper_bound(target);
|
||||
if (it == d.edits->regions.begin())
|
||||
{
|
||||
return nullptr; // LCOV_EXCL_LINE (an array/object with elements is in the index or a new value)
|
||||
}
|
||||
--it;
|
||||
lo = it->second != nullptr ? it->first + 1 : it->first;
|
||||
}
|
||||
for (const node* c = target; c != lo;)
|
||||
{
|
||||
--c;
|
||||
if (is_container(*c) && lt(target, c + c->next))
|
||||
{
|
||||
return (c->flags & node_flags::moved) == 0 ? const_cast<node*>(c) : nullptr; // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
|
||||
}
|
||||
}
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
} // namespace view
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
@@ -849,7 +849,7 @@ class basic_json_view
|
||||
return !navigation::editable() || m_doc->edits == nullptr;
|
||||
}
|
||||
|
||||
/// the member of this object with @a key (the last one if the key occurs more than once), or nullptr
|
||||
/// the member of this object with @a key (the first one if the key occurs more than once), or nullptr
|
||||
NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const
|
||||
{
|
||||
return find_key(key, std::integral_constant<bool, is_editable> {});
|
||||
|
||||
+1
-1
@@ -50,6 +50,7 @@
|
||||
#undef JSON_HEDLEY_EMSCRIPTEN_VERSION
|
||||
#undef JSON_HEDLEY_EMSCRIPTEN_VERSION_CHECK
|
||||
#undef JSON_HEDLEY_END_C_DECLS
|
||||
#undef JSON_HEDLEY_FALL_THROUGH
|
||||
#undef JSON_HEDLEY_FLAGS
|
||||
#undef JSON_HEDLEY_FLAGS_CAST
|
||||
#undef JSON_HEDLEY_GCC_HAS_ATTRIBUTE
|
||||
@@ -158,4 +159,3 @@
|
||||
#undef JSON_HEDLEY_WARNING
|
||||
#undef JSON_HEDLEY_WARN_UNUSED_RESULT
|
||||
#undef JSON_HEDLEY_WARN_UNUSED_RESULT_MSG
|
||||
#undef JSON_HEDLEY_FALL_THROUGH
|
||||
Generated
+1118
-277
File diff suppressed because it is too large.
Load diff
Generated
+54
-4
@@ -5564,7 +5564,9 @@ inline node* block_of(document_data& d, node* n, std::size_t extra)
|
||||
h->len = n->len;
|
||||
h->next = static_cast<std::uint32_t>(used);
|
||||
node* o = h + 1;
|
||||
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n); c != e;)
|
||||
// (the bound on o keeps the copy inside the block even if the elements
|
||||
// disagreed with the element count)
|
||||
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n), *const full = h + used; c != e && o != full;)
|
||||
{
|
||||
if (object)
|
||||
{
|
||||
@@ -5646,6 +5648,41 @@ inline node* find_parent(const document_data& d, const node* target)
|
||||
}
|
||||
}
|
||||
|
||||
/// The container whose contiguous layout (in the parsed index, or in a new
|
||||
/// value) steps over `target`, also when an edit dropped the container or a
|
||||
/// value that encloses it; nullptr if there is none, or if the container no
|
||||
/// longer walks that layout (its elements moved). An edit never gives a node a
|
||||
/// larger extent than it was parsed or encoded with (a scalar is one node, an
|
||||
/// assigned array/object keeps the extent of the slot), so the containers whose
|
||||
/// extent covers `target` are its original ancestors: the nearest one before it
|
||||
/// is its original parent. The root of a new value that is the element sequence
|
||||
/// of another container is walked by that container (which find_parent() finds
|
||||
/// while it still uses the sequence), not by itself.
|
||||
inline node* find_layout_parent(const document_data& d, const node* target)
|
||||
{
|
||||
const std::less<const node*> lt{};
|
||||
const node* lo = d.nodes;
|
||||
if (lt(target, lo) || !lt(target, d.nodes + d.node_count))
|
||||
{
|
||||
auto it = d.edits->regions.upper_bound(target);
|
||||
if (it == d.edits->regions.begin())
|
||||
{
|
||||
return nullptr; // LCOV_EXCL_LINE (an array/object with elements is in the index or a new value)
|
||||
}
|
||||
--it;
|
||||
lo = it->second != nullptr ? it->first + 1 : it->first;
|
||||
}
|
||||
for (const node* c = target; c != lo;)
|
||||
{
|
||||
--c;
|
||||
if (is_container(*c) && lt(target, c + c->next))
|
||||
{
|
||||
return (c->flags & node_flags::moved) == 0 ? const_cast<node*>(c) : nullptr; // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
|
||||
}
|
||||
}
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
} // namespace view
|
||||
} // namespace detail
|
||||
NLOHMANN_JSON_NAMESPACE_END
|
||||
@@ -6522,9 +6559,22 @@ class editor
|
||||
// for the container is linear in the size of the document, so
|
||||
// links (which are marked in the slot) avoid it.
|
||||
node* const p = parent_known ? parent : find_parent(m_doc, slot);
|
||||
if (p != nullptr && ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0))
|
||||
if (p != nullptr)
|
||||
{
|
||||
block_of(m_doc, p, 0);
|
||||
if ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0)
|
||||
{
|
||||
block_of(m_doc, p, 0);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
// the slot is no longer part of the document, but the
|
||||
// (dropped) container it is in may still step over it
|
||||
node* const q = find_layout_parent(m_doc, slot);
|
||||
if (q != nullptr)
|
||||
{
|
||||
block_of(m_doc, q, 0);
|
||||
}
|
||||
}
|
||||
}
|
||||
*slot = e.scalar;
|
||||
@@ -11016,7 +11066,7 @@ class basic_json_view
|
||||
return !navigation::editable() || m_doc->edits == nullptr;
|
||||
}
|
||||
|
||||
/// the member of this object with @a key (the last one if the key occurs more than once), or nullptr
|
||||
/// the member of this object with @a key (the first one if the key occurs more than once), or nullptr
|
||||
NLOHMANN_VIEW_ALWAYS_INLINE const node* find_key(string_view_t key) const
|
||||
{
|
||||
return find_key(key, std::integral_constant<bool, is_editable> {});
|
||||
|
||||
@@ -1,5 +1,12 @@
|
||||
cmake_minimum_required(VERSION 3.13...4.0)
|
||||
|
||||
# The unit tests use no C++ modules. Without this, CMake 4.5 scans the C++20 and
|
||||
# newer test targets and builds a `std` module for them, compiling the standard
|
||||
# library's module sources with the test warning flags (which fails with
|
||||
# -Werror) or failing to configure when the libc++ module sources are missing.
|
||||
# The module test in tests/module_cpp20 is a separate project and unaffected.
|
||||
set(CMAKE_CXX_SCAN_FOR_MODULES OFF)
|
||||
|
||||
option(JSON_Valgrind "Execute test suite with Valgrind." OFF)
|
||||
option(JSON_FastTests "Skip expensive/slow tests." OFF)
|
||||
option(JSON_TestSimdutf "Build the unit tests against the simdutf UTF-8 validation backend." OFF)
|
||||
@@ -434,6 +441,33 @@ json_test_add_test_for(src/unit-stream-bulk-scan.cpp
|
||||
MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
|
||||
)
|
||||
|
||||
# test the budget for the elements of UBJSON containers of a valueless type again
|
||||
# with other values of JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE: 1 (the smallest),
|
||||
# 1000000 (so large that the budget cannot be reached), and the largest value of
|
||||
# a 64-bit integer (which saturates the limit already at the first byte, and is
|
||||
# clamped to the largest std::size_t where that has 32 bits)
|
||||
json_test_set_test_options(test-ubjson_valueless_rate_1
|
||||
COMPILE_DEFINITIONS JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE=1
|
||||
)
|
||||
json_test_add_test_for(src/unit-ubjson_valueless.cpp
|
||||
NAME test-ubjson_valueless_rate_1
|
||||
MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
|
||||
)
|
||||
json_test_set_test_options(test-ubjson_valueless_rate_1000000
|
||||
COMPILE_DEFINITIONS JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE=1000000
|
||||
)
|
||||
json_test_add_test_for(src/unit-ubjson_valueless.cpp
|
||||
NAME test-ubjson_valueless_rate_1000000
|
||||
MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
|
||||
)
|
||||
json_test_set_test_options(test-ubjson_valueless_rate_max
|
||||
COMPILE_DEFINITIONS JSON_UBJSON_VALUELESS_ELEMENTS_PER_BYTE=0xFFFFFFFFFFFFFFFFu
|
||||
)
|
||||
json_test_add_test_for(src/unit-ubjson_valueless.cpp
|
||||
NAME test-ubjson_valueless_rate_max
|
||||
MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force}
|
||||
)
|
||||
|
||||
# test reading from a FILE* again with the locking stdio functions
|
||||
json_test_set_test_options(test-file_input_unlocked_io_disabled
|
||||
COMPILE_DEFINITIONS JSON_DISABLE_UNLOCKED_FILE_IO=1
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
// __ _____ _____ _____
|
||||
// __| | __| | | | 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
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <algorithm> // max
|
||||
#include <cstddef> // size_t
|
||||
#include <cstdint> // uint8_t
|
||||
#include <memory> // allocator
|
||||
#include <vector> // vector
|
||||
|
||||
#include <nlohmann/json.hpp>
|
||||
|
||||
namespace utils
|
||||
{
|
||||
/// the allocations of the values of a JSON type that uses counting_allocator
|
||||
struct allocation_counts
|
||||
{
|
||||
/// bytes allocated and not yet deallocated
|
||||
std::size_t current = 0;
|
||||
/// the largest value current had
|
||||
std::size_t peak = 0;
|
||||
/// number of allocations
|
||||
std::size_t allocations = 0;
|
||||
};
|
||||
|
||||
/// the counts of all counting_allocators; the tests are single-threaded
|
||||
inline allocation_counts& counts()
|
||||
{
|
||||
static allocation_counts c; // NOLINT(misc-const-correctness)
|
||||
return c;
|
||||
}
|
||||
|
||||
/// an allocator that counts the bytes and the number of allocations of a
|
||||
/// JSON type, so that a test can check how much memory a parse holds at any
|
||||
/// time without measuring the memory of the process
|
||||
template<class T>
|
||||
struct counting_allocator : std::allocator<T>
|
||||
{
|
||||
using std::allocator<T>::allocator;
|
||||
|
||||
counting_allocator() = default;
|
||||
template<class U> counting_allocator(const counting_allocator<U>& /*unused*/) noexcept {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
|
||||
|
||||
template <class U>
|
||||
struct rebind
|
||||
{
|
||||
using other = counting_allocator<U>;
|
||||
};
|
||||
|
||||
T* allocate(const std::size_t n)
|
||||
{
|
||||
T* const result = std::allocator<T>::allocate(n);
|
||||
allocation_counts& c = counts();
|
||||
c.current += n * sizeof(T);
|
||||
c.peak = (std::max)(c.peak, c.current);
|
||||
++c.allocations;
|
||||
return result;
|
||||
}
|
||||
|
||||
void deallocate(T* p, const std::size_t n)
|
||||
{
|
||||
counts().current -= n * sizeof(T);
|
||||
std::allocator<T>::deallocate(p, n);
|
||||
}
|
||||
};
|
||||
|
||||
using counted_json = nlohmann::json::with_allocator_t<counting_allocator>;
|
||||
|
||||
/// @a count times the bytes of @a unit
|
||||
inline std::vector<std::uint8_t> repeated(const std::vector<std::uint8_t>& unit, const std::size_t count)
|
||||
{
|
||||
std::vector<std::uint8_t> result;
|
||||
result.reserve(unit.size() * count);
|
||||
for (std::size_t i = 0; i < count; ++i)
|
||||
{
|
||||
result.insert(result.end(), unit.begin(), unit.end());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
} // namespace utils
|
||||
@@ -0,0 +1,125 @@
|
||||
// __ _____ _____ _____
|
||||
// __| | __| | | | 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
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <cstddef> // size_t
|
||||
#include <cstdint> // uint8_t, uint32_t
|
||||
#include <limits> // numeric_limits
|
||||
#include <string> // string
|
||||
#include <vector> // vector
|
||||
|
||||
#include <nlohmann/json.hpp>
|
||||
|
||||
// helpers of the tests of the budget for the elements of UBJSON containers of
|
||||
// a valueless type (unit-ubjson.cpp and unit-ubjson_valueless.cpp)
|
||||
#if defined(__clang__)
|
||||
#pragma clang diagnostic push
|
||||
#pragma clang diagnostic ignored "-Wweak-vtables"
|
||||
#endif
|
||||
|
||||
namespace utils
|
||||
{
|
||||
/// SAX consumer that counts the values and keeps the id of a parse error
|
||||
struct ValuelessEventCounter : public nlohmann::json_sax<nlohmann::json>
|
||||
{
|
||||
bool null() override
|
||||
{
|
||||
return ++values < stop_after;
|
||||
}
|
||||
bool boolean(bool /*val*/) override
|
||||
{
|
||||
return ++values < stop_after;
|
||||
}
|
||||
bool number_integer(nlohmann::json::number_integer_t /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool number_unsigned(nlohmann::json::number_unsigned_t /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool number_float(nlohmann::json::number_float_t /*val*/, const std::string& /*s*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool string(std::string& /*val*/) override
|
||||
{
|
||||
++values;
|
||||
return true;
|
||||
}
|
||||
bool binary(nlohmann::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 nlohmann::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
|
||||
inline 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 `]`
|
||||
inline 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 utils
|
||||
|
||||
#if defined(__clang__)
|
||||
#pragma clang diagnostic pop
|
||||
#endif
|
||||
@@ -6,6 +6,13 @@
|
||||
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
|
||||
// SPDX-License-Identifier: MIT
|
||||
|
||||
// cmake/test.cmake selects the C++ standard versions with which to build a
|
||||
// unit test based on the presence of JSON_HAS_CPP_<VERSION> macros.
|
||||
// When using macros that are only defined for particular versions of the standard
|
||||
// (e.g., JSON_HAS_FILESYSTEM for C++17 and up), please mention the corresponding
|
||||
// version macro in a comment close by, like this:
|
||||
// JSON_HAS_CPP_<VERSION> (do not remove; see note at top of file)
|
||||
|
||||
#include "doctest_compatibility.h"
|
||||
|
||||
#define JSON_TESTS_PRIVATE
|
||||
@@ -15,6 +22,7 @@ using nlohmann::json;
|
||||
#include <functional>
|
||||
#include <limits>
|
||||
#include <valarray>
|
||||
// JSON_HAS_CPP_20 (do not remove; see note at top of file)
|
||||
#if JSON_HAS_RANGES
|
||||
#include <ranges>
|
||||
#endif
|
||||
|
||||
@@ -14,6 +14,7 @@ using nlohmann::json;
|
||||
#include <cmath>
|
||||
#include <fstream>
|
||||
#include <limits>
|
||||
#include <list>
|
||||
#include <map>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
@@ -367,3 +368,125 @@ TEST_CASE("Binary formats with narrow number types")
|
||||
CHECK(format.decode(format.encode(json(1e300)), false).is_discarded());
|
||||
}
|
||||
}
|
||||
|
||||
namespace
|
||||
{
|
||||
// records the SAX events of narrow_json, including the arguments of parse_error
|
||||
struct narrow_event_recorder
|
||||
{
|
||||
using number_integer_t = narrow_json::number_integer_t;
|
||||
using number_unsigned_t = narrow_json::number_unsigned_t;
|
||||
using number_float_t = narrow_json::number_float_t;
|
||||
using string_t = narrow_json::string_t;
|
||||
using binary_t = narrow_json::binary_t;
|
||||
|
||||
bool null()
|
||||
{
|
||||
events.emplace_back("null");
|
||||
return true;
|
||||
}
|
||||
bool boolean(bool val)
|
||||
{
|
||||
events.emplace_back(val ? "true" : "false");
|
||||
return true;
|
||||
}
|
||||
bool number_integer(number_integer_t val)
|
||||
{
|
||||
events.push_back(std::to_string(val));
|
||||
return true;
|
||||
}
|
||||
bool number_unsigned(number_unsigned_t val)
|
||||
{
|
||||
events.push_back(std::to_string(val));
|
||||
return true;
|
||||
}
|
||||
bool number_float(number_float_t val, const string_t& /*unused*/)
|
||||
{
|
||||
events.push_back(std::to_string(val));
|
||||
return true;
|
||||
}
|
||||
bool string(string_t& val)
|
||||
{
|
||||
events.push_back(val);
|
||||
return true;
|
||||
}
|
||||
bool binary(binary_t& /*unused*/)
|
||||
{
|
||||
events.emplace_back("binary");
|
||||
return true;
|
||||
}
|
||||
bool start_object(std::size_t /*unused*/)
|
||||
{
|
||||
events.emplace_back("{");
|
||||
return true;
|
||||
}
|
||||
bool key(string_t& val)
|
||||
{
|
||||
events.push_back(val);
|
||||
return true;
|
||||
}
|
||||
bool end_object()
|
||||
{
|
||||
events.emplace_back("}");
|
||||
return true;
|
||||
}
|
||||
bool start_array(std::size_t /*unused*/)
|
||||
{
|
||||
events.emplace_back("[");
|
||||
return true;
|
||||
}
|
||||
bool end_array()
|
||||
{
|
||||
events.emplace_back("]");
|
||||
return true;
|
||||
}
|
||||
bool parse_error(std::size_t position, const std::string& last_token, const nlohmann::detail::exception& ex)
|
||||
{
|
||||
events.push_back("parse_error(" + std::to_string(position) + ", " + last_token + ", " + ex.what() + ")");
|
||||
return false;
|
||||
}
|
||||
|
||||
std::vector<std::string> events {}; // NOLINT(readability-redundant-member-init)
|
||||
};
|
||||
} // namespace
|
||||
|
||||
TEST_CASE("Binary formats with narrow number types from contiguous and non-contiguous input")
|
||||
{
|
||||
// contiguous input reads runs of numbers in one loop; a number that
|
||||
// overflows number_float_t must be reported with the same position and
|
||||
// last byte as when the input is read byte by byte
|
||||
const json values = {1, 70000, -70000, 1.5, 2.5, 1e300, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5};
|
||||
const json doubles = {1.5, 2.5, 3.5, 1e300, 4.5, 5.5, 6.5, 7.5, 8.5};
|
||||
|
||||
struct binary_input
|
||||
{
|
||||
const char* name;
|
||||
json::input_format_t format;
|
||||
bytes data;
|
||||
};
|
||||
const std::vector<binary_input> inputs =
|
||||
{
|
||||
{"CBOR", json::input_format_t::cbor, json::to_cbor(values)},
|
||||
{"CBOR doubles", json::input_format_t::cbor, json::to_cbor(doubles)},
|
||||
{"MessagePack", json::input_format_t::msgpack, json::to_msgpack(values)},
|
||||
{"MessagePack doubles", json::input_format_t::msgpack, json::to_msgpack(doubles)},
|
||||
{"UBJSON", json::input_format_t::ubjson, json::to_ubjson(values, true)},
|
||||
{"UBJSON typed doubles", json::input_format_t::ubjson, json::to_ubjson(doubles, true, true)},
|
||||
{"BJData", json::input_format_t::bjdata, json::to_bjdata(values, true)},
|
||||
{"BJData typed doubles", json::input_format_t::bjdata, json::to_bjdata(doubles, true, true)},
|
||||
};
|
||||
|
||||
for (const auto& input : inputs)
|
||||
{
|
||||
const std::string name = input.name;
|
||||
CAPTURE(name)
|
||||
const std::list<std::uint8_t> bytewise(input.data.begin(), input.data.end());
|
||||
narrow_event_recorder from_contiguous;
|
||||
narrow_event_recorder from_bytewise;
|
||||
CHECK_FALSE(narrow_json::sax_parse(input.data, &from_contiguous, input.format));
|
||||
CHECK_FALSE(narrow_json::sax_parse(bytewise.begin(), bytewise.end(), &from_bytewise, input.format));
|
||||
CHECK(from_contiguous.events == from_bytewise.events);
|
||||
REQUIRE(!from_contiguous.events.empty());
|
||||
CHECK(from_contiguous.events.back().find("out_of_range.406") != std::string::npos);
|
||||
}
|
||||
}
|
||||
Loaded 100 of 116 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user