Add more pre-commit hooks

.github/.licenserc.yaml

@@ -32,25 +32,25 @@ header:
       limitations under the License\.
 
   paths:
-    - '**'
+  - '**'
 
   paths-ignore: # `paths-ignore` are the path list that will be ignored by license-eye.
-    - '.clang-format'
-    - '.clang-tidy'
-    - '.gitignore'
-    - '.github/scripts/setup_apt_repo_linux.sh'
-    - 'HISTORY.md'
-    - 'NEWS.md'
-    - 'LICENSE'
-    - 'THIRD-PARTY-PROGRAMS'
-    - '.github/renovate.json'
-    - '.github/CODEOWNERS'
-    - 'cmake/mkl_functions'
-    - 'cmake/mkl_functions_ivf'
-    - 'cmake/patches/tomlplusplus_v330.patch'
-    - 'docker/x86_64/manylinux2014/oneAPI.repo'
-    - 'docs/cpp/index/loader-compatibility.csv'
-    - 'docs/requirements.txt'
+  - .clang-format
+  - .clang-tidy
+  - .gitignore
+  - .github/scripts/setup_apt_repo_linux.sh
+  - HISTORY.md
+  - NEWS.md
+  - LICENSE
+  - THIRD-PARTY-PROGRAMS
+  - .github/renovate.json
+  - .github/CODEOWNERS
+  - cmake/mkl_functions
+  - cmake/mkl_functions_ivf
+  - cmake/patches/tomlplusplus_v330.patch
+  - docker/x86_64/manylinux2014/oneAPI.repo
+  - docs/cpp/index/loader-compatibility.csv
+  - docs/requirements.txt
 
   comment: never
 

.github/CODEOWNERS

@@ -1,10 +1,10 @@
 # C/C++ library code
 /include/               @ibhati @ahuber21
-/cmake/                 @mihaic @ibhati @ahuber21 
-/tests/                 @mihaic @ibhati @ahuber21 @yuejiaointel 
-/benchmark/             @mihaic @ibhati @ahuber21 
-/tools/                 @mihaic @ibhati @ahuber21 
-/utils/                 @mihaic @ibhati @ahuber21 
+/cmake/                 @mihaic @ibhati @ahuber21
+/tests/                 @mihaic @ibhati @ahuber21 @yuejiaointel
+/benchmark/             @mihaic @ibhati @ahuber21
+/tools/                 @mihaic @ibhati @ahuber21
+/utils/                 @mihaic @ibhati @ahuber21
 
 # Python and other language bindings
 /bindings/              @ethanglaser @ibhati @ahuber21
@@ -14,7 +14,7 @@
 /data/                  @ibhati @ahuber21
 
 # Docker and build environment
-/docker/                @mihaic @ahuber21 
+/docker/                @mihaic @ahuber21
 
 # CI and infra
 /.github                @mihaic @homksei @yuejiaointel @ethanglaser

.github/workflows/build-linux-arm.yml

@@ -17,15 +17,15 @@ name: Linux Build and Test on ARM
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 permissions:
   contents: read
 
 # This allows a subsequently queued workflow run to interrupt previous runs
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
+  group: ${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -37,12 +37,12 @@ jobs:
         build_type: [RelWithDebugInfo]
         cxx: [g++-11, g++-12, clang++-15]
         include:
-          - cxx: g++-11
-            cc: gcc-11
-          - cxx: g++-12
-            cc: gcc-12
-          - cxx: clang++-15
-            cc: clang-15
+        - cxx: g++-11
+          cc: gcc-11
+        - cxx: g++-12
+          cc: gcc-12
+        - cxx: clang++-15
+          cc: clang-15
 
     steps:
     - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
@@ -67,6 +67,6 @@ jobs:
 
     - name: Run tests
       env:
-          CTEST_OUTPUT_ON_FAILURE: 1
+        CTEST_OUTPUT_ON_FAILURE: 1
       working-directory: ${{ runner.temp }}/build/tests
       run: ctest -C ${{ matrix.build_type }}

.github/workflows/build-linux.yml

@@ -17,15 +17,15 @@ name: Linux Build and Test
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 permissions:
   contents: read
 
 # This allows a subsequently queued workflow run to interrupt previous runs
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
+  group: ${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -38,45 +38,45 @@ jobs:
         ivf: [OFF, ON]
         cxx: [g++-11, g++-12, clang++-15]
         asan: [OFF]
-        cmake_extra_args: ["-DSVS_BUILD_BINARIES=YES -DSVS_BUILD_EXAMPLES=YES"]
-        ctest_args: [""]
+        cmake_extra_args: [-DSVS_BUILD_BINARIES=YES -DSVS_BUILD_EXAMPLES=YES]
+        ctest_args: ['']
         include:
-          - cxx: g++-11
-            cc: gcc-11
-          - cxx: g++-12
-            cc: gcc-12
-          - cxx: clang++-15
-            cc: clang-15
-          - cxx: clang++-18
-            cc: clang-18
-            build_type: Debug
-            ivf: OFF
-            asan: ON
+        - cxx: g++-11
+          cc: gcc-11
+        - cxx: g++-12
+          cc: gcc-12
+        - cxx: clang++-15
+          cc: clang-15
+        - cxx: clang++-18
+          cc: clang-18
+          build_type: Debug
+          ivf: OFF
+          asan: ON
             # address sanitizer flags
-            cmake_extra_args: >-
-              -DCMAKE_CXX_FLAGS='-fsanitize=address -fno-omit-frame-pointer -g'
-              -DCMAKE_C_FLAGS='-fsanitize=address -fno-omit-frame-pointer -g'
-              -DCMAKE_EXE_LINKER_FLAGS='-fsanitize=address'
-              -DCMAKE_SHARED_LINKER_FLAGS='-fsanitize=address'
-              -DSVS_BUILD_BINARIES=NO
-              -DSVS_BUILD_EXAMPLES=NO
-            # skip longer-running tests
-            ctest_args: "-LE long"
+          cmake_extra_args: >-
+            -DCMAKE_CXX_FLAGS='-fsanitize=address -fno-omit-frame-pointer -g'
+            -DCMAKE_C_FLAGS='-fsanitize=address -fno-omit-frame-pointer -g'
+            -DCMAKE_EXE_LINKER_FLAGS='-fsanitize=address'
+            -DCMAKE_SHARED_LINKER_FLAGS='-fsanitize=address'
+            -DSVS_BUILD_BINARIES=NO
+            -DSVS_BUILD_EXAMPLES=NO
+           # skip longer-running tests
+          ctest_args: -LE long
         exclude:
-          - cxx: g++-12
-            ivf: ON
+        - cxx: g++-12
+          ivf: ON
 
     steps:
     - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
     - name: Install MKL
       timeout-minutes: 5
       run: |
-       .github/scripts/setup_apt_repo_linux.sh
-       sudo apt install intel-oneapi-mkl intel-oneapi-mkl-devel
-       # Setup environment variables for building against MKL.
-       # Persist the environment variables for use across multiple subsequent actions.
-       source /opt/intel/oneapi/setvars.sh
-       printenv >> $GITHUB_ENV
+        .github/scripts/setup_apt_repo_linux.sh
+        sudo apt install intel-oneapi-mkl intel-oneapi-mkl-devel
+        # Setup environment variables for building against MKL.
+        # Persist the environment variables for use across multiple subsequent actions.
+        source /opt/intel/oneapi/setvars.sh
+        printenv >> $GITHUB_ENV
 
     - name: Install Clang 18
       if: matrix.cxx == 'clang++-18'

.github/workflows/build-macos.yaml

@@ -17,15 +17,15 @@ name: MacOS Build and Test
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 permissions:
   contents: read
 
 # This allows a subsequently queued workflow run to interrupt previous runs
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
+  group: ${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -37,11 +37,11 @@ jobs:
         build_type: [RelWithDebugInfo]
         cxx: [clang++-15]
         include:
-          - cxx: clang++-15
-            package: llvm@15
-            cc_name: clang
-            cxx_name: clang++
-            needs_prefix: true
+        - cxx: clang++-15
+          package: llvm@15
+          cc_name: clang
+          cxx_name: clang++
+          needs_prefix: true
 
     steps:
     - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
@@ -80,6 +80,6 @@ jobs:
 
     - name: Run tests
       env:
-          CTEST_OUTPUT_ON_FAILURE: 1
+        CTEST_OUTPUT_ON_FAILURE: 1
       working-directory: ${{ runner.temp }}/build/tests
       run: ctest -C ${{ matrix.build_type }}

.github/workflows/cibuildwheel.yml

@@ -17,14 +17,14 @@ name: CIBuildWheel
 on:
   push:
     branches:
-      - main
+    - main
   pull_request:
 
 permissions:
   contents: read
 
 concurrency:
-  group: '${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}'
+  group: ${{ github.workflow }} @ ${{ github.event.pull_request.head.label || github.head_ref || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -55,14 +55,14 @@ jobs:
     # Make sure to add the location of the generated wheel to the python path.
     - name: Run Default Tests
       env:
-          PYTHONPATH: ${{ runner.temp }}/usr
-          CTEST_OUTPUT_ON_FAILURE: 1
+        PYTHONPATH: ${{ runner.temp }}/usr
+        CTEST_OUTPUT_ON_FAILURE: 1
       working-directory: ${{ runner.temp }}
       run: python -m unittest discover -s ${GITHUB_WORKSPACE}/bindings/python
 
     - name: Run examples
       env:
-          PYTHONPATH: ${{ runner.temp }}/usr
-          CTEST_OUTPUT_ON_FAILURE: 1
+        PYTHONPATH: ${{ runner.temp }}/usr
+        CTEST_OUTPUT_ON_FAILURE: 1
       working-directory: ${{ runner.temp }}
       run: python -m unittest discover -p "example*.py" -s ${GITHUB_WORKSPACE}/examples/python

.github/workflows/skywalking-eyes.yml

@@ -17,10 +17,10 @@ name: Check License Header
 on:
   pull_request:
     branches:
-      - main
+    - main
   push:
     branches:
-      - main
+    - main
 
 permissions: read-all
 
@@ -33,10 +33,10 @@ jobs:
     name: Copyright Check
     runs-on: ubuntu-24.04
     steps:
-      - name: "Checkout code"
-        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
-      - name: "Run check"
-        uses: apache/skywalking-eyes/header@61275cc80d0798a405cb070f7d3a8aaf7cf2c2c1 # v0.8.0
-        with:
-          config: ".github/.licenserc.yaml"
-          mode: "check"
+    - name: Checkout code
+      uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8   # v6.0.1
+    - name: Run check
+      uses: apache/skywalking-eyes/header@61275cc80d0798a405cb070f7d3a8aaf7cf2c2c1   # v0.8.0
+      with:
+        config: .github/.licenserc.yaml
+        mode: check

.pre-commit-config.yaml

@@ -21,3 +21,19 @@ repos:
         entry: tools/clang-format.sh
         args: [clang-format]
         additional_dependencies: ["clang-format>=15,<16"]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: check-yaml
+        files: \.ya?ml$
+      - id: check-added-large-files
+      - id: check-illegal-windows-names
+      - id: check-json
+        files: \.json$
+      - id: check-merge-conflict
+      - id: check-toml
+        files: \.toml$
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: mixed-line-ending

CMakeLists.txt

@@ -177,4 +177,3 @@ install(FILES
     ${SVS_CMAKE_FIND_FILES}
     DESTINATION "${LIB_CONFIG_INSTALL_DIR}"
 )
-

HISTORY.md

@@ -707,4 +707,3 @@ affect performance or users relying on internal APIs.
 ## Third Party
 
 * Bump [fmtlib](https://github.com/fmtlib/fmt) from 9.1.0 to 10.1.1.
-

LICENSE

@@ -202,10 +202,10 @@
    limitations under the License.
   ============================================================================
    Intel® oneAPI Math Kernel Library (Intel® oneMKL): Copyright 2022 Intel Corporation
-    
+
    Intel® Scalable Vector Search: Copyright (C) Intel Corporation provides shared library in binary form with optional algorithms implementations that can be used with Scalable Vector Search library
-   
-   ------------------------------   
+
+   ------------------------------
    Intel Simplified Software License (Version October 2022)
 
    Use and Redistribution.  You may use and redistribute the software, which is
@@ -277,4 +277,3 @@
    objections. THE UNITED NATIONS CONVENTION ON CONTRACTS FOR THE INTERNATIONAL
    SALE OF GOODS (1980) IS SPECIFICALLY EXCLUDED AND WILL NOT APPLY TO THE
    SOFTWARE.
-

SECURITY.md

@@ -19,4 +19,3 @@ Intel is committed to rapidly addressing security vulnerabilities affecting our
 
 ## Reporting a Vulnerability
 Please report any security vulnerabilities in this project [utilizing the guidelines here](https://www.intel.com/content/www/us/en/security-center/vulnerability-handling-guidelines.html).
-

bindings/python/.gitignore

@@ -2,4 +2,3 @@
 _skbuild/
 build/
 *.egg-info
-

bindings/python/CMakeLists.txt

@@ -90,4 +90,3 @@ if(DEFINED SKBUILD)
     # wheel.
     install(FILES "${CMAKE_CURRENT_LIST_DIR}/../../data/serialization.toml" DESTINATION .)
 endif()
-

bindings/python/src/svs/__init__.py

@@ -30,4 +30,3 @@
 
 # Make the upgrader available without explicit import.
 from . import upgrader
-

bindings/python/src/svs/upgrader.py

@@ -297,4 +297,3 @@ def upgrade(
         )
 
     print(f"File {path} is up to date!")
-

bindings/python/tests/__init__.py

@@ -11,4 +11,3 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-