cadar 0.1.3__tar.gz

cadar-0.1.3/.github/workflows/docs.yml

@@ -0,0 +1,127 @@
+name: Build and Deploy Documentation
+
+on:
+  push:
+    tags:
+      - 'v*.*.*'  # Triggers on tags like v0.1.0, v1.2.3, etc.
+    branches:
+      - main  # Also build docs on main branch
+
+permissions:
+  contents: write
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build-docs:
+    name: Build Documentation
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0  # Fetch all history for proper versioning
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+
+    - name: Set up Rust
+      uses: actions-rs/toolchain@v1
+      with:
+        profile: minimal
+        toolchain: stable
+        override: true
+
+    - name: Install dependencies
+      run: |
+        pip install --upgrade pip
+        pip install maturin
+        pip install mkdocs mkdocs-material mkdocstrings[python] markdown-include
+        pip install pymdown-extensions
+
+    - name: Build and install CaDaR
+      run: |
+        # Build wheel
+        maturin build --release --out dist
+        # Install the built wheel
+        pip install dist/*.whl
+
+    - name: Extract version
+      id: get_version
+      run: |
+        if [[ $GITHUB_REF == refs/tags/* ]]; then
+          VERSION=${GITHUB_REF#refs/tags/v}
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          echo "IS_TAG=true" >> $GITHUB_OUTPUT
+        else
+          VERSION="dev"
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          echo "IS_TAG=false" >> $GITHUB_OUTPUT
+        fi
+        echo "Building documentation for version: $VERSION"
+
+    - name: Generate Python API documentation
+      run: |
+        python3 docs/generate_api_docs.py
+
+    - name: Build Rust documentation
+      run: |
+        cargo doc --no-deps --document-private-items
+        mkdir -p site/rust
+        cp -r target/doc/* site/rust/
+
+    - name: Build MkDocs site
+      run: |
+        mkdocs build --strict
+
+    - name: Create version directory
+      if: steps.get_version.outputs.IS_TAG == 'true'
+      run: |
+        VERSION=${{ steps.get_version.outputs.VERSION }}
+        mkdir -p site/versions/$VERSION
+        cp -r site/* site/versions/$VERSION/ || true
+
+    - name: Generate versions index
+      run: |
+        python3 docs/generate_versions.py
+
+    - name: Upload artifact
+      uses: actions/upload-pages-artifact@v3
+      with:
+        path: site
+
+  deploy-docs:
+    name: Deploy to GitHub Pages
+    needs: build-docs
+    runs-on: ubuntu-latest
+    # Only deploy from main branch, not from tags (environment protection rules)
+    if: github.ref == 'refs/heads/main'
+
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    steps:
+    - name: Deploy to GitHub Pages
+      id: deployment
+      uses: actions/deploy-pages@v4
+
+    - name: Comment on PR (if applicable)
+      if: github.event_name == 'pull_request'
+      uses: actions/github-script@v7
+      with:
+        script: |
+          github.rest.issues.createComment({
+            issue_number: context.issue.number,
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            body: '📚 Documentation preview available at: ${{ steps.deployment.outputs.page_url }}'
+          })

cadar-0.1.3/.github/workflows/publish-pypi.yml

@@ -0,0 +1,195 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*.*.*'  # Triggers on tags like v0.1.0, v1.2.3, etc.
+
+permissions:
+  contents: write
+
+jobs:
+  build-and-publish:
+    name: Build and publish Python distribution to PyPI
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+        exclude:
+          # Reduce build matrix - only build all Python versions on Linux
+          - os: macos-latest
+            python-version: '3.8'
+          - os: macos-latest
+            python-version: '3.9'
+          - os: windows-latest
+            python-version: '3.8'
+          - os: windows-latest
+            python-version: '3.9'
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Set up Rust
+      uses: actions-rs/toolchain@v1
+      with:
+        profile: minimal
+        toolchain: stable
+        override: true
+
+    - name: Install maturin
+      run: pip install maturin
+
+    - name: Extract version from tag
+      id: get_version
+      shell: bash
+      run: |
+        # Remove 'v' prefix from tag (v0.1.0 -> 0.1.0)
+        VERSION=${GITHUB_REF#refs/tags/v}
+        echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+        echo "Building version: $VERSION"
+
+    - name: Update version in Cargo.toml
+      shell: bash
+      run: |
+        VERSION=${{ steps.get_version.outputs.VERSION }}
+        # Update version in Cargo.toml
+        if [[ "$OSTYPE" == "darwin"* ]]; then
+          sed -i '' "s/^version = .*/version = \"$VERSION\"/" Cargo.toml
+        else
+          sed -i "s/^version = .*/version = \"$VERSION\"/" Cargo.toml
+        fi
+
+    - name: Update version in pyproject.toml
+      shell: bash
+      run: |
+        VERSION=${{ steps.get_version.outputs.VERSION }}
+        # Update version in pyproject.toml
+        if [[ "$OSTYPE" == "darwin"* ]]; then
+          sed -i '' "s/^version = .*/version = \"$VERSION\"/" pyproject.toml
+        else
+          sed -i "s/^version = .*/version = \"$VERSION\"/" pyproject.toml
+        fi
+
+    - name: Build wheels
+      run: |
+        maturin build --release --strip --out dist
+
+    - name: Upload wheels as artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: wheels-${{ matrix.os }}-py${{ matrix.python-version }}
+        path: dist/
+
+  build-sdist:
+    name: Build source distribution
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.12'
+
+    - name: Set up Rust
+      uses: actions-rs/toolchain@v1
+      with:
+        profile: minimal
+        toolchain: stable
+        override: true
+
+    - name: Install maturin
+      run: pip install maturin
+
+    - name: Extract version from tag
+      id: get_version
+      shell: bash
+      run: |
+        VERSION=${GITHUB_REF#refs/tags/v}
+        echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+        echo "Building version: $VERSION"
+
+    - name: Update version in Cargo.toml
+      shell: bash
+      run: |
+        VERSION=${{ steps.get_version.outputs.VERSION }}
+        sed -i "s/^version = .*/version = \"$VERSION\"/" Cargo.toml
+
+    - name: Update version in pyproject.toml
+      shell: bash
+      run: |
+        VERSION=${{ steps.get_version.outputs.VERSION }}
+        sed -i "s/^version = .*/version = \"$VERSION\"/" pyproject.toml
+
+    - name: Build source distribution
+      run: |
+        maturin build --release --sdist --out dist
+
+    - name: Upload sdist as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: sdist
+        path: dist/*.tar.gz
+
+  publish:
+    name: Publish to PyPI
+    needs: [build-and-publish, build-sdist]
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # Required for trusted publishing
+
+    steps:
+    - name: Download wheel artifacts
+      uses: actions/download-artifact@v4
+      with:
+        path: dist/
+        pattern: wheels-*
+        merge-multiple: true
+
+    - name: Download sdist artifact
+      uses: actions/download-artifact@v4
+      with:
+        path: dist/
+        pattern: sdist
+        merge-multiple: true
+
+    - name: List distributions
+      run: ls -lh dist/
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }}
+        skip-existing: true
+        verbose: true
+
+    - name: Create GitHub Release
+      uses: softprops/action-gh-release@v1
+      with:
+        files: dist/*
+        generate_release_notes: true
+        body: |
+          ## CaDaR ${{ github.ref_name }}
+
+          Bidirectional transliteration for Darija (Moroccan Arabic)
+
+          ### Installation
+          ```bash
+          pip install cadar==${{ github.ref_name }}
+          ```
+
+          ### What's Changed
+          See the [CHANGELOG](https://github.com/Oit-Technologies/CaDaR/blob/main/CHANGELOG.md) for details.
+
+          ---
+          🤖 Published automatically by GitHub Actions
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

cadar-0.1.3/.gitignore

@@ -0,0 +1,64 @@
+# Rust
+/target/
+**/*.rs.bk
+Cargo.lock
+*.pdb
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+*.egg
+*.egg-info/
+dist/
+build/
+.eggs/
+pip-wheel-metadata/
+*.whl
+
+# Virtual environments
+venv/
+env/
+ENV/
+.venv/
+
+# PyO3/Maturin
+*.o
+*.a
+*.dylib
+*.dll
+*.so.*
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.mypy_cache/
+.hypothesis/
+
+# Documentation
+docs/_build/
+docs/.doctrees/
+site/
+
+# Benchmark results
+criterion/
+bench_results/
+
+# Logs
+*.log
+
+# OS
+Thumbs.db
+.Spotlight-V100
+.Trashes

cadar-0.1.3/CHANGELOG.md

@@ -0,0 +1,95 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1.3] - 2026-01-28
+
+### Fixed
+
+- **CI/CD**: Fixed Linux wheel builds in GitHub Actions (removed Docker, unified build process)
+- **PyPI**: Added missing source distribution (.tar.gz) to PyPI releases
+- **GitHub Pages**: Fixed deployment from tags (now only deploys from main branch)
+
+### Added
+
+- Source distribution build job in CI/CD workflow
+- All Python versions now build correctly on Linux
+
+### Changed
+
+- Simplified wheel building across all platforms (no platform-specific logic)
+- Updated publish workflow to download both wheels and source distribution
+
+## [0.1.2] - 2026-01-28
+
+### Fixed
+
+- **Security**: Upgraded PyO3 from 0.20.3 to 0.24.2 to fix buffer overflow vulnerability (CVE)
+- **Documentation**: Fixed MkDocs directory structure for proper builds
+- **Documentation**: Removed Rust API from navigation to fix strict mode build
+- **CI/CD**: Fixed GitHub Actions release permissions (403 error)
+- **Documentation**: Added comprehensive documentation for all sections
+
+### Added
+
+- Complete user guide with examples
+- API reference documentation
+- Development and contribution guides
+- Installation instructions
+- Architecture documentation
+
+### Changed
+
+- Updated Python bindings to use PyO3 0.24+ Bound API
+- Moved mkdocs.yml from docs/ to project root
+- Updated all documentation paths for new structure
+
+## [0.1.0] - 2026-01-28
+
+### Added
+
+- Initial release of CaDaR
+- 6-stage FST-style transliteration pipeline
+  - Stage 1: Script Detection
+  - Stage 2: Noise Cleaning & Normalization
+  - Stage 3: Darija-aware Tokenization
+  - Stage 4: Intermediate Canonical Representation (ICR)
+  - Stage 5: Target Script Generation
+  - Stage 6: Post-validation & Fixes
+- Python API with four main functions:
+  - `ara2bizi()` - Arabic to Latin transliteration
+  - `bizi2ara()` - Latin to Arabic transliteration
+  - `ara2ara()` - Arabic text standardization
+  - `bizi2bizi()` - Latin text standardization
+- `CaDaR` class for reusable transliteration operations
+- Convenience functions: `transliterate()` and `standardize()`
+- Support for Moroccan Darija (dialect code: "Ma")
+- Comprehensive documentation
+- 41 unit tests with 100% pass rate
+- Example scripts demonstrating usage
+- MIT License
+
+### Features
+
+- **Bidirectional transliteration**: Seamless conversion between Arabic and Latin scripts
+- **Intelligent normalization**: Handles diacritics, repeated characters, and common variations
+- **Darija-aware processing**: Recognizes Darija-specific patterns and constructs
+- **High performance**: Rust core with Python bindings via PyO3
+- **Extensible architecture**: Designed to support additional Darija dialects in future releases
+
+### Technical Details
+
+- Built with Rust 1.93.0
+- Python bindings using PyO3 0.20
+- Supports Python 3.8+
+- Cross-platform: Linux, macOS, Windows
+
+[Unreleased]: https://github.com/Oit-Technologies/CaDaR/compare/v0.1.3...HEAD
+[0.1.3]: https://github.com/Oit-Technologies/CaDaR/compare/v0.1.2...v0.1.3
+[0.1.2]: https://github.com/Oit-Technologies/CaDaR/compare/v0.1.0...v0.1.2
+[0.1.0]: https://github.com/Oit-Technologies/CaDaR/releases/tag/v0.1.0