hdiffpatch 1.1.0__tar.gz → 2.1.0__tar.gz

hdiffpatch-2.1.0/.github/workflows/build_wheels.yaml

@@ -0,0 +1,183 @@
+name: Build Wheels
+
+on:
+  workflow_dispatch:
+  pull_request:
+    # Only build wheels on PRs when compiled code (or the build itself) changes.
+    paths:
+      - "**.pyx"
+      - "**.pxd"
+      - "hdiffpatch/_c_src/**"
+      - "setup.py"
+      - "cythonize.py"
+      - "pyproject.toml"
+      - ".github/workflows/build_wheels.yaml"
+  push:
+    tags:
+      - "v*.*.*"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  build_sdist:
+    name: "sdist"
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: "3.13"
+
+      - name: Build sdist
+        run: uv build --sdist
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: wheels-sdist
+          path: dist/*.tar.gz
+
+  build_wheels_windows:
+    name: "${{ matrix.os }} ${{ matrix.cibw_archs }} ${{ matrix.cibw_build }}"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [windows-latest]
+        cibw_build: ["cp310-*", "cp311-*", "cp312-*", "cp313-*", "cp314-*"]
+        cibw_archs: ["AMD64"]
+
+    steps:
+      - name: "Set environment variables (Windows)"
+        shell: pwsh
+        run: |
+          (Get-ItemProperty "HKLM:System\CurrentControlSet\Control\FileSystem").LongPathsEnabled
+
+      - name: Sanitize matrix.cibw_build
+        id: sanitize_build
+        run: echo "CIBW_BUILD_SANITIZED=$(echo '${{ matrix.cibw_build }}' | sed 's/\*/_/g')" >> $GITHUB_ENV
+        shell: bash
+
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v4.1
+        env:
+          CIBW_ARCHS: ${{ matrix.cibw_archs }}
+          CIBW_BUILD: ${{ matrix.cibw_build }}
+          CIBW_TEST_REQUIRES: pytest
+          CIBW_TEST_COMMAND: pytest {package}/tests
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: wheels-${{ matrix.os }}-${{ env.CIBW_BUILD_SANITIZED }}-${{ matrix.cibw_archs }}
+          path: wheelhouse/*.whl
+
+  build_wheels_linux:
+    name: "${{ matrix.os }} ${{ matrix.cibw_build }}"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        # ubuntu-24.04-arm builds aarch64 wheels natively (much faster than QEMU).
+        os: [ubuntu-latest, ubuntu-24.04-arm]
+        cibw_build: ["cp310-*", "cp311-*", "cp312-*", "cp313-*", "cp314-*"]
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Sanitize matrix.cibw_build
+        id: sanitize_build
+        run: echo "CIBW_BUILD_SANITIZED=$(echo '${{ matrix.cibw_build }}' | sed 's/\*/_/g')" >> $GITHUB_ENV
+        shell: bash
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v4.1
+        env:
+          CIBW_BUILD: ${{ matrix.cibw_build }}
+          CIBW_TEST_REQUIRES: pytest
+          CIBW_TEST_COMMAND: pytest {package}/tests
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: wheels-${{ matrix.os }}-${{ env.CIBW_BUILD_SANITIZED }}
+          path: wheelhouse/*.whl
+
+  build_wheels_macos:
+    name: "${{ matrix.os }} ${{ matrix.cibw_archs }} ${{ matrix.cibw_build }}"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-latest]
+        cibw_build: ["cp310-*", "cp311-*", "cp312-*", "cp313-*", "cp314-*"]
+        cibw_archs: ["arm64", "x86_64"]
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Sanitize matrix.cibw_build
+        id: sanitize_build
+        run: echo "CIBW_BUILD_SANITIZED=$(echo '${{ matrix.cibw_build }}' | sed 's/\*/_/g')" >> $GITHUB_ENV
+        shell: bash
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v4.1
+        env:
+          CIBW_ARCHS: ${{ matrix.cibw_archs }}
+          CIBW_BUILD: ${{ matrix.cibw_build }}
+          # x86_64 wheels are cross-compiled on arm64 runners; their tests can't run natively.
+          CIBW_TEST_SKIP: "*-macosx_x86_64"
+          CIBW_TEST_REQUIRES: pytest
+          CIBW_TEST_COMMAND: pytest {package}/tests
+
+      - uses: actions/upload-artifact@v7
+        with:
+          name: wheels-${{ matrix.os }}-${{ env.CIBW_BUILD_SANITIZED }}-${{ matrix.cibw_archs }}
+          path: wheelhouse/*.whl
+
+  upload_to_pypi:
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    needs:
+      [
+        "build_sdist",
+        "build_wheels_windows",
+        "build_wheels_linux",
+        "build_wheels_macos",
+      ]
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      # Required for PyPI Trusted Publishing (OIDC); no API token needed.
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v8
+        with:
+          path: wheels
+          pattern: wheels-*
+          merge-multiple: true
+
+      - uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: wheels/
+          skip-existing: true

hdiffpatch-2.1.0/.github/workflows/tests.yaml

@@ -0,0 +1,90 @@
+# Regular tests
+#
+# Use this to ensure your tests are passing on every push and PR.
+#
+# You should make sure you run jobs on at least the *oldest* and the *newest*
+# versions of python that your codebase is intended to support.
+
+name: tests
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  # Lint doesn't depend on OS or python version; run it once.
+  lint:
+    timeout-minutes: 30
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: "3.13"
+          enable-cache: true
+
+      - name: Install library
+        run: uv sync --locked
+
+      - name: Cache pre-commit
+        uses: actions/cache@v6
+        with:
+          path: ~/.cache/pre-commit/
+          key: pre-commit-${{ runner.os }}-${{ hashFiles('.pre-commit-config.yaml') }}
+
+      - name: Pre-commit run
+        run: uv run pre-commit run --show-diff-on-failure --color=always --all-files
+
+  test:
+    timeout-minutes: 45
+    defaults:
+      run:
+        shell: bash
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python-version }}
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v7
+        with:
+          submodules: recursive
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+
+      - name: Install library
+        run: uv sync --locked
+
+      - name: Run tests
+        run: |
+          uv run python -m pytest --cov=hdiffpatch --cov-report term --cov-report xml --junitxml=testresults.xml
+          uv run coverage report
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v7
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          flags: unittests
+          env_vars: OS,PYTHON
+          name: Python ${{ matrix.python-version }} on ${{ runner.os }}

hdiffpatch-2.1.0/.gitignore

@@ -0,0 +1,253 @@
+##---------------------------------------------------
+# Automated documentation .gitignore files
+##---------------------------------------------------
+
+# Automatically generated API documentation stubs from sphinx-apidoc
+docs/source/packages
+
+# Automatically converting README from markdown to rST
+docs/bin
+docs/source/readme.rst
+docs/source/assets
+
+
+##---------------------------------------------------
+# Continuous Integration .gitignore files
+##---------------------------------------------------
+
+# Ignore test result XML files
+testresults.xml
+coverage.xml
+
+
+##---------------------------------------------------
+# Python default .gitignore
+##---------------------------------------------------
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+*.pyd
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+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
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+/docs/_build/
+/docs/build/
+
+# PyBuilder
+target/
+
+# Pycharm
+/.idea/dictionaries
+/.idea/modules.xml
+/.idea/shelf
+/.idea/usage.statistics.xml
+/.idea/workspace.xml
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# celery beat schedule file
+celerybeat-schedule
+
+# 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/
+
+
+##---------------------------------------------------
+# Windows default .gitignore
+##---------------------------------------------------
+
+# Windows thumbnail cache files
+Thumbs.db
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+
+##---------------------------------------------------
+# Linux default .gitignore
+##---------------------------------------------------
+
+# Editor backup files
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+
+##---------------------------------------------------
+# Mac OSX default .gitignore
+##---------------------------------------------------
+
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# Cython
+hdiffpatch/_c_extension.c
+hdiffpatch/_c_extension.cpp
+hdiffpatch/*.html
+# Poetry
+poetry.toml
+
+# Claude Code (local session state, agent worktrees, etc.)
+.claude/
+CLAUDE.local.md

hdiffpatch-2.1.0/.gitmodules

@@ -0,0 +1,24 @@
+[submodule "hdiffpatch/_c_src/HDiffPatch"]
+	path = hdiffpatch/_c_src/HDiffPatch
+	url = https://github.com/sisong/HDiffPatch.git
+[submodule "hdiffpatch/_c_src/libmd5"]
+	path = hdiffpatch/_c_src/libmd5
+	url = https://github.com/sisong/libmd5.git
+[submodule "hdiffpatch/_c_src/lzma"]
+	path = hdiffpatch/_c_src/lzma
+	url = https://github.com/sisong/lzma.git
+[submodule "hdiffpatch/_c_src/zstd"]
+	path = hdiffpatch/_c_src/zstd
+	url = https://github.com/sisong/zstd.git
+[submodule "hdiffpatch/_c_src/zlib"]
+	path = hdiffpatch/_c_src/zlib
+	url = https://github.com/sisong/zlib.git
+[submodule "hdiffpatch/_c_src/bzip2"]
+	path = hdiffpatch/_c_src/bzip2
+	url = https://github.com/sisong/bzip2.git
+[submodule "hdiffpatch/_c_src/libdeflate"]
+	path = hdiffpatch/_c_src/libdeflate
+	url = https://github.com/sisong/libdeflate.git
+[submodule "hdiffpatch/_c_src/tamp"]
+	path = hdiffpatch/_c_src/tamp
+	url = https://github.com/BrianPugh/tamp.git

hdiffpatch-2.1.0/.readthedocs.yaml

@@ -0,0 +1,35 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+# Derived from: https://docs.readthedocs.io/en/stable/build-customization.html#install-dependencies-with-uv
+
+# Required
+version: 2
+
+# The C extension statically embeds the vendored C/C++ submodules.
+submodules:
+  include: all
+  recursive: true
+
+build:
+  os: "ubuntu-24.04"
+  tools:
+    python: "3.12"
+  jobs:
+    pre_create_environment:
+      - asdf plugin add uv
+      - asdf install uv latest
+      - asdf global uv latest
+    create_environment:
+      - uv venv "${READTHEDOCS_VIRTUALENV_PATH}"
+    install:
+      # Install the project (builds the C extension) and its 'docs' dependency group.
+      - UV_PROJECT_ENVIRONMENT="${READTHEDOCS_VIRTUALENV_PATH}" uv sync --no-group dev
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+  fail_on_warning: true
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+formats:
+  - pdf

hdiffpatch-2.1.0/CLAUDE.md

@@ -0,0 +1,97 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Repository Overview
+
+hdiffpatch-python is a high-performance Python wrapper around the [HDiffPatch](https://github.com/sisong/HDiffPatch) C++ library providing efficient binary diff/patch operations with comprehensive compression support. The project uses Cython for C++ integration and supports Python 3.10+. It is a library only — there is no CLI.
+
+## Development Commands
+
+### Setup and Installation
+
+```bash
+# Install development dependencies
+uv sync
+
+# Build Cython extensions (required after initial sync)
+uv run python rebuild.py
+
+# Install pre-commit hooks
+uv run pre-commit install
+```
+
+### Testing
+This project uses the `pytest` framework for unit testing:
+
+```bash
+# Run all tests
+uv run pytest
+
+# Run specific test file
+uv run pytest tests/test_compression.py
+
+# Run specific test function
+uv run pytest tests/test_compression.py::TestCompressionTypes::test_compression_type_constants
+
+# Run tests with coverage
+uv run pytest --cov=hdiffpatch --cov-report=html
+
+# Run tests matching a keyword
+uv run pytest -k "compression"
+```
+
+### Code Quality
+
+```bash
+# Run all pre-commit hooks; this only runs on files tracked by git.
+uv run pre-commit run --all-files
+```
+
+Linting/typing is configured in `pyproject.toml`: ruff (line length 120, numpy docstring convention, target Python 3.10) and pyright (checks `tests/`).
+
+## Architecture
+
+### Build pipeline
+
+- **`cythonize.py`**: compiles `hdiffpatch/_c_extension.pyx` to C++ with optimization directives.
+- **`rebuild.py`**: runs `cythonize.py`, then reinstalls the package in editable mode. This is the one command to run after editing `.pyx` files.
+- **`setup.py`**: builds a single extension module (`hdiffpatch._c_extension`) that statically embeds all C/C++ dependencies from `hdiffpatch/_c_src/` (HDiffPatch, zlib, libdeflate, lzma, zstd, bzip2, tamp, libmd5) with `-O3` and platform-specific optimizations. Compression plugins are enabled via preprocessor defines (e.g. `_CompressPlugin_lzma`).
+
+### Package layout
+
+- **`hdiffpatch/_c_extension.pyx`**: the entire Cython interface — core functions, constants, and the `HDiffPatchError` exception. `hdiffpatch/_c_extension.pyi` is the hand-maintained type stub; keep it in sync when changing the `.pyx` API.
+- **`hdiffpatch/_base_config.py`** + per-algorithm config modules (`_zlib_config.py`, `_lzma_config.py`, `_zstd_config.py`, `_bzip2_config.py`, `_tamp_config.py`): frozen attrs classes for fine-grained compression settings. `BaseConfig` defines classmethod presets (`fast`, `balanced`, `best_compression`, `minimal_memory`) that subclasses implement.
+- **`hdiffpatch/__init__.py`**: assembles the public API; `__version__` is managed by setuptools-scm — don't edit it.
+
+### Public API
+
+```python
+diff(old_data: bytes, new_data: bytes, compression=None, *, validate=True) -> bytes
+apply(old_data: bytes, diff_data: bytes) -> bytes      # auto-detects compression from diff header
+recompress(diff_data: bytes, compression=None) -> bytes  # re-encode an existing diff (incl. hdiffz output)
+```
+
+- `compression` accepts a `CompressionType` literal string (`"none"`, `"zlib"`, `"lzma"`, `"lzma2"`, `"zstd"`, `"bzip2"`, `"tamp"`), a config object (e.g. `ZStdConfig(level=22)`), or `None`.
+- There is a single exception type, `HDiffPatchError`, raised for all diff/patch/compression failures.
+- Uses Literal types instead of Enums for simplicity and type checker compatibility.
+
+### Tests
+
+- `tests/conftest.py` provides a comprehensive fixture system (e.g. `simple_text_data`, `binary_data`, `random_data`, `compression_types`, `all_compression_types`) — use these for consistent test data.
+- `tests/binaries/` holds real MicroPython firmware images and hdiffz-produced diffs used by `test_binary_compatibility.py` to verify compatibility with upstream HDiffPatch tooling.
+- `tools/micropython-binary-demo.py` is a demo script exercising the same firmware-diff use case.
+
+## Development Memories
+
+- Always run `uv run python rebuild.py` after `uv sync` for development setup
+- After changing Cython code: just run `uv run python rebuild.py` (handles cythonize automatically)
+- Always use `uv run python` instead of just `python` for running python code
+- Always prefer `pathlib.Path` over `os.path`
+- Only add comments if the action isn't immediately obvious from function or method names
+- **All docstrings must follow numpy-style format** with proper Parameters, Returns, and Raises sections
+- TAMP compression is supported as a first-class compression type alongside zlib, zstd, etc.
+- All compression types should be tested with round-trip validation
+- Use the comprehensive fixture system in `conftest.py` for consistent test data
+- Run `uv run pre-commit run --all-files` before asking to commit to ensure pre-commit passes all checks
+- When writing unit tests, prefer to use pytest functionality (such as `parametrize`)