[vpdq] Use scikit-build-core build backend for Python binding

.github/workflows/vpdq-release.yaml

@@ -20,24 +20,27 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
-      - name: Install packaging dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install -r packaging-requirements.txt
+          python-version: "3.11"
       - name: Install build dependencies
         run: |
           sudo apt-get update
           sudo apt-get install -y python3-dev pkg-config cmake ffmpeg libavcodec-dev libavformat-dev libavdevice-dev libavutil-dev libswscale-dev libswresample-dev libavfilter-dev
 
+      - name: Install packaging dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install -r packaging-requirements.txt
+          python -m pip list
+
       - name: Package
         run: |
           python -m build --sdist
 
       - name: Ensure packaged build runs
         run: |
           python -m pip install dist/vpdq*.tar.gz
-          python -c "import vpdq"
+          python -m pip list
+          python -c "import vpdq; print(dir(vpdq))"
 
       - name: Publish distribution to Test PyPI
         uses: pypa/gh-action-pypi-publish@release/v1

.gitignore

@@ -19,4 +19,5 @@ pdq/java/bazel-testlogs/
 .vscode/
 *.d.ts
 .idea/
-venv/
+venv/
+.venv/

vpdq/.gitignore

@@ -1,3 +1,8 @@
+# vpdq
+output-hashes/*
+python/vpdq.cpp
+
+# Misc
 *.o
 *.a
 *.dSYM
@@ -8,12 +13,207 @@
 *.swp
 *.swo
 
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
 build/
-cpp/libraries-dirs.txt
-cpp/test
-cpp/build
-output-hashes/*
-python/vpdq.cpp
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
 
 # CMake
 CMakeLists.txt.user

vpdq/CMakeLists.txt

@@ -0,0 +1,45 @@
+# CMake to build the Python binding for vpdq. This is built with the Python
+# scikit-build-core build backend. This compiles vpdq and compiles the Cython
+# and then links vpdq to the compiled Cython.
+
+cmake_minimum_required(VERSION 3.15...3.30)
+project(${SKBUILD_PROJECT_NAME} LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD
+    14
+    CACHE STRING "C++ version selection")
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+
+# Compile pdq and vpdq to produce their library files.
+add_subdirectory(cpp)
+
+# Build the Cython bindings. Create the cpp file from the Cython pyx file,
+# compile it, and link it to vpdq.
+
+find_package(
+  Python
+  COMPONENTS Interpreter Development.Module
+  REQUIRED)
+
+add_custom_command(
+  OUTPUT ${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.cpp
+  COMMENT
+    "Making ${CMAKE_CURRENT_BINARY_DIR}/python/vpdq.cpp from ${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.pyx"
+  COMMAND
+    Python::Interpreter -m cython "${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.pyx"
+    --output-file "${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.cpp"
+  DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.pyx
+  VERBATIM)
+
+python_add_library(vpdq MODULE ${CMAKE_CURRENT_SOURCE_DIR}/python/vpdq.cpp
+                   WITH_SOABI)
+
+# Link pdq and vpdq to the vpdq Cython library
+target_link_libraries(vpdq PUBLIC pdqlib)
+target_link_libraries(vpdq PUBLIC vpdqlib)
+
+# Note: The install directory determines the module directory. For example, if
+# it's changed to 'foo', then in python you would have to do 'from foo import
+# vpdq' to use the module. Leaving it at '.' allows for just 'import vpdq'.
+install(TARGETS vpdq DESTINATION .)

vpdq/CONTRIBUTING.md

@@ -93,17 +93,15 @@ Install dependencies:
 python -m pip install -r packaging-requirements.txt
 ```
 
-Build package:
+Build source distribution package:
 ```sh
 python -m build --sdist 
 ```
 
-Build wheel:
-```sh
-python -m build --wheel
-```
+The package should now be in `dist/`.
 
-The package/wheel should now be in `dist/`.
+> **Note:** Wheels are not currently distributed. But, in the future building wheels with manylinux and packaging the dynamically
+> linked libav* libraries may be useful to end users to skip the build and dependency process. 
 
 ### Publishing
 

vpdq/MANIFEST.in

@@ -5,6 +5,5 @@ include README.md
 
 graft cpp
 prune cpp/build
-exclude cpp/libraries-dirs.txt
 
 graft python

vpdq/cpp/CMakeLists.txt

@@ -91,9 +91,3 @@ add_subdirectory(vpdq)
 # CLI programs
 # TODO: Make this a custom command/option. This isn't necessary to just build the library.
 add_subdirectory(apps)
-
-# Write the libav* library dirs to a new-line delimited file for Cython to be able to locate LIBAV files
-# TODO: Make this a custom command or something. This isn't necessary on every run.
-string(REPLACE ";" "\n" LIBRARY_DIRS "${LIBAV_STATIC_LIBRARY_DIRS}")
-set(LIBRARY_DIRS_FILE "libraries-dirs.txt")
-file(WRITE ${LIBRARY_DIRS_FILE} "${LIBRARY_DIRS}")

vpdq/pyproject.toml

@@ -1,11 +1,6 @@
 [build-system]
-requires = [
-    "setuptools >= 61.0",
-    "wheel",
-    "cython",
-    "cmake",
-]
-build-backend = "setuptools.build_meta"
+requires = ["scikit-build-core", "cython"]
+build-backend = "scikit_build_core.build"
 
 [project]
 name = "vpdq"
@@ -14,13 +9,25 @@ description = "Python bindings for Facebook VPDQ hash"
 requires-python = ">= 3.8"
 readme = {file = "python/README.md", content-type = "text/markdown"}
 license = {file = "LICENSE.txt"}
-dynamic = ["version", "scripts", "entry-points"]
+dynamic = ["version"]
+
+[tool.scikit-build.metadata.version]
+provider = "scikit_build_core.metadata.regex"
+input = "version.txt"
 
-[tool.setuptools]
-include-package-data = true
+# Regex explanation:
+# ^ matches the start of the line.
+# ?P<value> is the named capture group with the name value. scikit is expecting this.
+# \S+ matches any non-whitespace characters, assuming the version is a single token.
+# $ ensures the match ends at the end of the line.
+regex = "^(?P<value>\\S+)$" 
 
-[tool.setuptools.packages.find]
-where = ["python"]  # list of folders that contain the packages (["."] by default)
-include = ["vpdq.pyx"]  # package names should match these glob patterns (["*"] by default)
-exclude = []  # exclude packages matching these glob patterns (empty by default)
-namespaces = false  # to disable scanning PEP 420 namespaces (true by default)
+[tool.scikit-build]
+minimum-version = "0.10"
+cmake.build-type = "RelWithDebInfo"
+
+[project.optional-dependencies]
+dev = [
+  "pytest",
+  "clang-format",
+]