vexy-pdf-werk 1.1.2.dev0__tar.gz

vexy_pdf_werk-1.1.2.dev0/.gitignore

@@ -0,0 +1,195 @@
+__pycache__/
+__pypackages__/
+__version__.py
+_deps
+_dev/
+_private/
+_version.py
+!.env.example
+!.env.template
+!.vscode/*.code-snippets
+!.vscode/extensions.json
+!.vscode/launch.json
+!.vscode/settings.json
+!.vscode/tasks.json
+!build/.gitkeep
+!dist/.gitkeep
+._*
+.\#*
+.apdisk
+.AppleDB
+.AppleDesktop
+.AppleDouble
+.atom/
+.benchmarks/
+.cache
+.com.apple.timemachine.donotpresent
+.conda/
+.coverage
+.coverage.*
+.dmypy.json
+.DocumentRevisions-V100
+.DS_Store
+.eggs/
+.env
+.env*
+.fseventsd
+.hatch/
+.history/
+.hypothesis/
+.idea/
+.installed.cfg
+.ionide/
+.ipynb_checkpoints
+.LSOverride
+.mypy_cache/
+.nox/
+.pdm-build/
+.pdm-python
+.pdm.toml
+.pybuilder/
+.pyre/
+.pytest_cache/
+.Python
+.python-version
+.pytype/
+.ropeproject
+.ruff_cache/
+.scrapy
+.Spotlight-V100
+.spyderproject
+.spyproject
+.TemporaryItems
+.tox/
+.Trashes
+.uv/
+.venv
+.vimrc.local
+.VolumeIcon.icns
+.vscode/
+.webassets-cache
+*.backup
+*.bak
+*.cover
+*.crt
+*.csr
+*.egg
+*.egg-info/
+*.elc
+*.key
+*.log
+*.make
+*.manifest
+*.mo
+*.p12
+*.pem
+*.pfx
+*.pot
+*.prof
+*.profile
+*.py,cover
+*.py[cod]
+*.sage.py
+*.secret
+*.so
+*.spec
+*.sublime-workspace
+*.swo
+*.swp
+*.temp
+*.tmp
+*~
+*$py.class
+/.emacs.desktop
+/.emacs.desktop.lock
+/site
+\#*\#
+$RECYCLE.BIN/
+artifacts/
+auto-save-list
+autom4te.cache/
+benchmark_results/
+benchmarks/results/
+build/
+celerybeat-schedule
+celerybeat.pid
+cmake_install.cmake
+CMakeCache.txt
+CMakeFiles/
+config.local.*
+config.log
+config.status
+configure
+cover/
+coverage.xml
+CTestTestfile.cmake
+cython_debug/
+db.sqlite3
+db.sqlite3-journal
+Desktop.ini
+dev/
+develop-eggs/
+dist/
+dmypy.json
+docs/_build/
+docs/build/
+downloads/
+eggs/
+ehthumbs_vista.db
+ehthumbs.db
+env.bak/
+env/
+ENV/
+external/
+htmlcov/
+Icon
+instance/
+ipython_config.py
+lib/
+lib64/
+local_config.*
+local_settings.py
+log/
+logs/
+Makefile
+Makefile.in
+MANIFEST
+Network Trash Folder
+node_modules/
+nosetests.xml
+npm-debug.log*
+outputs/
+package-lock.json
+parts/
+pip-delete-this-directory.txt
+pip-log.txt
+Pipfile.lock
+poetry.lock
+private/
+prof/
+profile_default/
+profiles/
+results/
+sdist/
+secret.*
+secrets/
+share/python-wheels/
+src/*/__version__.py
+src/*/_version.py
+src/*/version.py
+target/
+temp/
+Temporary Items
+Thumbs.db
+Thumbs.db:encryptable
+tmp/
+tramp
+uv.lock
+var/
+vendor/
+venv.bak/
+venv/
+wheels/
+yarn-debug.log*
+yarn-error.log*
+yarn.lock

vexy_pdf_werk-1.1.2.dev0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Fontlab Ltd
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

vexy_pdf_werk-1.1.2.dev0/PKG-INFO

@@ -0,0 +1,267 @@
+Metadata-Version: 2.4
+Name: vexy-pdf-werk
+Version: 1.1.2.dev0
+Project-URL: Documentation, https://github.com/vexyart/vexy-pdf-werk#readme
+Project-URL: Issues, https://github.com/vexyart/vexy-pdf-werk/issues
+Project-URL: Source, https://github.com/vexyart/vexy-pdf-werk
+Author-email: Fontlab Ltd <opensource@vexy.art>
+License: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Provides-Extra: all
+Provides-Extra: dev
+Requires-Dist: absolufy-imports>=0.3.1; extra == 'dev'
+Requires-Dist: isort>=6.0.1; extra == 'dev'
+Requires-Dist: mypy>=1.15.0; extra == 'dev'
+Requires-Dist: pre-commit>=4.1.0; extra == 'dev'
+Requires-Dist: pyupgrade>=3.19.1; extra == 'dev'
+Requires-Dist: ruff>=0.9.7; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: myst-parser>=3.0.0; extra == 'docs'
+Requires-Dist: sphinx-autodoc-typehints>=2.0.0; extra == 'docs'
+Requires-Dist: sphinx-rtd-theme>=2.0.0; extra == 'docs'
+Requires-Dist: sphinx>=7.2.6; extra == 'docs'
+Provides-Extra: test
+Requires-Dist: coverage[toml]>=7.6.12; extra == 'test'
+Requires-Dist: pytest-asyncio>=0.25.3; extra == 'test'
+Requires-Dist: pytest-benchmark[histogram]>=5.1.0; extra == 'test'
+Requires-Dist: pytest-cov>=6.0.0; extra == 'test'
+Requires-Dist: pytest-xdist>=3.6.1; extra == 'test'
+Requires-Dist: pytest>=8.3.4; extra == 'test'
+Description-Content-Type: text/markdown
+
+# this_file: README.md
+
+# Vexy PDF Werk
+
+**Transform PDFs into high-quality, accessible formats with AI-enhanced processing**
+
+Vexy PDF Werk (VPW) is a Python package that converts PDF documents into multiple high-quality formats using modern tools and optional AI enhancement. Transform your PDFs into PDF/A archives, paginated Markdown, ePub books, and structured bibliographic metadata.
+
+## Features
+
+🔧 **Modern PDF Processing**
+- PDF/A conversion for long-term archival
+- OCR enhancement using OCRmyPDF
+- Quality optimization with qpdf
+
+📚 **Multiple Output Formats**
+- Paginated Markdown documents with smart naming
+- ePub generation from Markdown
+- Structured bibliographic YAML metadata
+- Preserves original PDF alongside enhanced versions
+
+🤖 **Optional AI Enhancement**
+- Text correction using Claude or Gemini CLI
+- Content structure optimization
+- Fallback to proven traditional methods
+
+⚙️ **Flexible Architecture**
+- Multiple conversion backends (Marker, MarkItDown, Docling, basic)
+- Platform-appropriate configuration storage
+- Robust error handling with graceful fallbacks
+
+## Quick Start
+
+### Installation
+
+```bash
+# Install from PyPI
+pip install vexy-pdf-werk
+
+# Or install in development mode
+git clone https://github.com/vexyart/vexy-pdf-werk
+cd vexy-pdf-werk
+pip install -e .
+```
+
+### Basic Usage
+
+```python
+import vexy_pdf_werk
+
+# Process a PDF with default settings
+config = vexy_pdf_werk.Config(name="default", value="process")
+result = vexy_pdf_werk.process_data(["document.pdf"], config=config)
+```
+
+### CLI Usage (Coming Soon)
+
+```bash
+# Process a PDF into all formats
+vpw process document.pdf
+
+# Process with specific formats only
+vpw process document.pdf --formats pdfa,markdown
+
+# Enable AI enhancement
+vpw process document.pdf --ai-enabled --ai-provider claude
+```
+
+## Output Structure
+
+VPW creates organized output with consistent naming:
+
+```
+output/
+├── document_enhanced.pdf    # PDF/A version
+├── 000--introduction.md     # Paginated Markdown files
+├── 001--chapter-one.md
+├── 002--conclusions.md
+├── document.epub            # Generated ePub
+└── metadata.yaml            # Bibliographic data
+```
+
+## System Requirements
+
+### Required Dependencies
+- Python 3.10+
+- tesseract-ocr
+- qpdf
+- ghostscript
+
+### Optional Dependencies
+- pandoc (for ePub generation)
+- marker-pdf (advanced PDF conversion)
+- markitdown (Microsoft's document converter)
+- docling (IBM's document understanding)
+
+### Installation Commands
+
+**Ubuntu/Debian:**
+```bash
+sudo apt-get update
+sudo apt-get install tesseract-ocr tesseract-ocr-eng qpdf ghostscript pandoc
+```
+
+**macOS:**
+```bash
+brew install tesseract tesseract-lang qpdf ghostscript pandoc
+```
+
+**Windows:**
+```bash
+choco install tesseract qpdf ghostscript pandoc
+```
+
+## Configuration
+
+VPW stores configuration in platform-appropriate directories:
+
+- **Linux/macOS**: `~/.config/vexy-pdf-werk/config.toml`
+- **Windows**: `%APPDATA%\\vexy-pdf-werk\\config.toml`
+
+### Example Configuration
+
+```toml
+[processing]
+ocr_language = "eng"
+pdf_quality = "high"
+force_ocr = false
+
+[conversion]
+markdown_backend = "auto"  # auto, marker, markitdown, docling, basic
+paginate_markdown = true
+include_images = true
+
+[ai]
+enabled = false
+provider = "claude"  # claude, gemini
+correction_enabled = false
+
+[output]
+formats = ["pdfa", "markdown", "epub", "yaml"]
+preserve_original = true
+output_directory = "./output"
+```
+
+## Development
+
+This project uses modern Python tooling:
+
+- **Package Management**: uv + hatch
+- **Code Quality**: ruff + mypy
+- **Testing**: pytest
+- **Version Control**: git-tag-based semver with hatch-vcs
+
+### Development Setup
+
+```bash
+# Install uv and hatch
+curl -LsSf https://astral.sh/uv/install.sh | sh
+pip install hatch
+
+# Clone and setup
+git clone https://github.com/vexyart/vexy-pdf-werk
+cd vexy-pdf-werk
+
+# Run tests using hatch (automatically manages environment)
+hatch run test
+
+# Run linting and formatting
+hatch run lint
+
+# Type checking
+hatch run type-check
+
+# Or run individual commands
+hatch run python -c "import vexy_pdf_werk; print(vexy_pdf_werk.__version__)"
+```
+
+## Architecture
+
+VPW follows a modular pipeline architecture:
+
+```
+PDF Input → Analysis → OCR Enhancement → Content Extraction → Format Generation → Multi-Format Output
+                          ↓
+                   Optional AI Enhancement
+```
+
+### Core Components
+
+- **PDF Processor**: Handles OCR and PDF/A conversion
+- **Content Extractors**: Multiple backends for PDF-to-Markdown
+- **Format Generators**: Creates ePub and metadata outputs
+- **AI Integrations**: Optional LLM enhancement services
+- **Configuration System**: Platform-aware settings management
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/amazing-feature`)
+3. Make your changes following the code quality standards
+4. Run tests and linting
+5. Commit your changes (`git commit -m 'Add amazing feature'`)
+6. Push to the branch (`git push origin feature/amazing-feature`)
+7. Open a Pull Request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Authors
+
+- **Fontlab Ltd** - *Initial work* - [Vexy Art](https://vexy.art)
+
+## Acknowledgments
+
+- Built on proven tools: qpdf, OCRmyPDF, tesseract
+- Integration with cutting-edge AI services
+- Inspired by the need for better PDF accessibility and archival
+
+---
+
+**Project Status**: Under active development
+
+For detailed implementation specifications, see the [spec/](spec/) directory.

vexy_pdf_werk-1.1.2.dev0/README.md

@@ -0,0 +1,225 @@
+# this_file: README.md
+
+# Vexy PDF Werk
+
+**Transform PDFs into high-quality, accessible formats with AI-enhanced processing**
+
+Vexy PDF Werk (VPW) is a Python package that converts PDF documents into multiple high-quality formats using modern tools and optional AI enhancement. Transform your PDFs into PDF/A archives, paginated Markdown, ePub books, and structured bibliographic metadata.
+
+## Features
+
+🔧 **Modern PDF Processing**
+- PDF/A conversion for long-term archival
+- OCR enhancement using OCRmyPDF
+- Quality optimization with qpdf
+
+📚 **Multiple Output Formats**
+- Paginated Markdown documents with smart naming
+- ePub generation from Markdown
+- Structured bibliographic YAML metadata
+- Preserves original PDF alongside enhanced versions
+
+🤖 **Optional AI Enhancement**
+- Text correction using Claude or Gemini CLI
+- Content structure optimization
+- Fallback to proven traditional methods
+
+⚙️ **Flexible Architecture**
+- Multiple conversion backends (Marker, MarkItDown, Docling, basic)
+- Platform-appropriate configuration storage
+- Robust error handling with graceful fallbacks
+
+## Quick Start
+
+### Installation
+
+```bash
+# Install from PyPI
+pip install vexy-pdf-werk
+
+# Or install in development mode
+git clone https://github.com/vexyart/vexy-pdf-werk
+cd vexy-pdf-werk
+pip install -e .
+```
+
+### Basic Usage
+
+```python
+import vexy_pdf_werk
+
+# Process a PDF with default settings
+config = vexy_pdf_werk.Config(name="default", value="process")
+result = vexy_pdf_werk.process_data(["document.pdf"], config=config)
+```
+
+### CLI Usage (Coming Soon)
+
+```bash
+# Process a PDF into all formats
+vpw process document.pdf
+
+# Process with specific formats only
+vpw process document.pdf --formats pdfa,markdown
+
+# Enable AI enhancement
+vpw process document.pdf --ai-enabled --ai-provider claude
+```
+
+## Output Structure
+
+VPW creates organized output with consistent naming:
+
+```
+output/
+├── document_enhanced.pdf    # PDF/A version
+├── 000--introduction.md     # Paginated Markdown files
+├── 001--chapter-one.md
+├── 002--conclusions.md
+├── document.epub            # Generated ePub
+└── metadata.yaml            # Bibliographic data
+```
+
+## System Requirements
+
+### Required Dependencies
+- Python 3.10+
+- tesseract-ocr
+- qpdf
+- ghostscript
+
+### Optional Dependencies
+- pandoc (for ePub generation)
+- marker-pdf (advanced PDF conversion)
+- markitdown (Microsoft's document converter)
+- docling (IBM's document understanding)
+
+### Installation Commands
+
+**Ubuntu/Debian:**
+```bash
+sudo apt-get update
+sudo apt-get install tesseract-ocr tesseract-ocr-eng qpdf ghostscript pandoc
+```
+
+**macOS:**
+```bash
+brew install tesseract tesseract-lang qpdf ghostscript pandoc
+```
+
+**Windows:**
+```bash
+choco install tesseract qpdf ghostscript pandoc
+```
+
+## Configuration
+
+VPW stores configuration in platform-appropriate directories:
+
+- **Linux/macOS**: `~/.config/vexy-pdf-werk/config.toml`
+- **Windows**: `%APPDATA%\\vexy-pdf-werk\\config.toml`
+
+### Example Configuration
+
+```toml
+[processing]
+ocr_language = "eng"
+pdf_quality = "high"
+force_ocr = false
+
+[conversion]
+markdown_backend = "auto"  # auto, marker, markitdown, docling, basic
+paginate_markdown = true
+include_images = true
+
+[ai]
+enabled = false
+provider = "claude"  # claude, gemini
+correction_enabled = false
+
+[output]
+formats = ["pdfa", "markdown", "epub", "yaml"]
+preserve_original = true
+output_directory = "./output"
+```
+
+## Development
+
+This project uses modern Python tooling:
+
+- **Package Management**: uv + hatch
+- **Code Quality**: ruff + mypy
+- **Testing**: pytest
+- **Version Control**: git-tag-based semver with hatch-vcs
+
+### Development Setup
+
+```bash
+# Install uv and hatch
+curl -LsSf https://astral.sh/uv/install.sh | sh
+pip install hatch
+
+# Clone and setup
+git clone https://github.com/vexyart/vexy-pdf-werk
+cd vexy-pdf-werk
+
+# Run tests using hatch (automatically manages environment)
+hatch run test
+
+# Run linting and formatting
+hatch run lint
+
+# Type checking
+hatch run type-check
+
+# Or run individual commands
+hatch run python -c "import vexy_pdf_werk; print(vexy_pdf_werk.__version__)"
+```
+
+## Architecture
+
+VPW follows a modular pipeline architecture:
+
+```
+PDF Input → Analysis → OCR Enhancement → Content Extraction → Format Generation → Multi-Format Output
+                          ↓
+                   Optional AI Enhancement
+```
+
+### Core Components
+
+- **PDF Processor**: Handles OCR and PDF/A conversion
+- **Content Extractors**: Multiple backends for PDF-to-Markdown
+- **Format Generators**: Creates ePub and metadata outputs
+- **AI Integrations**: Optional LLM enhancement services
+- **Configuration System**: Platform-aware settings management
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch (`git checkout -b feature/amazing-feature`)
+3. Make your changes following the code quality standards
+4. Run tests and linting
+5. Commit your changes (`git commit -m 'Add amazing feature'`)
+6. Push to the branch (`git push origin feature/amazing-feature`)
+7. Open a Pull Request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Authors
+
+- **Fontlab Ltd** - *Initial work* - [Vexy Art](https://vexy.art)
+
+## Acknowledgments
+
+- Built on proven tools: qpdf, OCRmyPDF, tesseract
+- Integration with cutting-edge AI services
+- Inspired by the need for better PDF accessibility and archival
+
+---
+
+**Project Status**: Under active development
+
+For detailed implementation specifications, see the [spec/](spec/) directory.

vexy_pdf_werk-1.1.2.dev0/pyproject.toml

@@ -0,0 +1,448 @@
+# this_file: pyproject.toml
+#==============================================================================
+# VEXY-PDF-WERK PACKAGE CONFIGURATION
+# This pyproject.toml defines the package metadata, dependencies, build system,
+# and development environment for the vexy-pdf-werk package.
+#==============================================================================
+
+#------------------------------------------------------------------------------
+# PROJECT METADATA
+# Core package information used by PyPI and package managers.
+#------------------------------------------------------------------------------
+[project]
+name = 'vexy-pdf-werk' # Package name on PyPI
+description = '' # Short description
+readme = 'README.md' # Path to README file
+requires-python = '>=3.10' # Minimum Python version
+keywords = [
+] # Keywords for PyPI search
+dynamic = ["version"] # Fields set dynamically at build time
+
+# PyPI classifiers for package categorization
+classifiers = [
+    'Development Status :: 4 - Beta', # Package maturity level
+    'Programming Language :: Python',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
+    'Programming Language :: Python :: Implementation :: CPython',
+    'Programming Language :: Python :: Implementation :: PyPy',
+    'Operating System :: OS Independent',
+    'License :: OSI Approved :: MIT License',
+    'Intended Audience :: Developers',
+]
+
+dependencies = [
+]
+
+# Author information
+[[project.authors]]
+name = 'Fontlab Ltd'
+email = 'opensource@vexy.art'
+
+# License information
+[project.license]
+text = 'MIT'
+
+# Project URLs
+[project.urls]
+Documentation = 'https://github.com/vexyart/vexy-pdf-werk#readme'
+Issues = 'https://github.com/vexyart/vexy-pdf-werk/issues'
+Source = 'https://github.com/vexyart/vexy-pdf-werk'
+
+#------------------------------------------------------------------------------
+# OPTIONAL DEPENDENCIES
+# Additional dependencies for optional features, development, and testing.
+#------------------------------------------------------------------------------
+[project.optional-dependencies]
+
+# Development tools
+dev = [
+    'pre-commit>=4.1.0', # Pre-commit hook manager - Keep pre-commit as is, update if newer pre-commit version is required
+    'ruff>=0.9.7', # Linting and formatting - Keep ruff as is, update if newer ruff version is required
+    'mypy>=1.15.0', # Type checking - Keep mypy as is, update if newer mypy version is required
+    'absolufy-imports>=0.3.1', # Convert relative imports to absolute - Keep absolufy-imports as is, update if newer absolufy-imports version is required
+    'pyupgrade>=3.19.1', # Upgrade Python syntax - Keep pyupgrade as is, update if newer pyupgrade version is required
+    'isort>=6.0.1', # Sort imports - Keep isort as is, update if newer isort version is required
+]
+
+# Testing tools and frameworks
+test = [
+    'pytest>=8.3.4', # Testing framework - Keep pytest as is, update if newer pytest version is required
+    'pytest-cov>=6.0.0', # Coverage plugin for pytest - Keep pytest-cov as is, update if newer pytest-cov version is required
+    'pytest-xdist>=3.6.1', # Parallel test execution - Keep pytest-xdist as is, update if newer pytest-xdist version is required
+    'pytest-benchmark[histogram]>=5.1.0', # Benchmarking plugin - Keep pytest-benchmark as is, update if newer pytest-benchmark version is required
+    'pytest-asyncio>=0.25.3', # Async test support - Keep pytest-asyncio as is, update if newer pytest-asyncio version is required
+    'coverage[toml]>=7.6.12',
+]
+
+docs = [
+    "sphinx>=7.2.6",
+    "sphinx-rtd-theme>=2.0.0",
+    "sphinx-autodoc-typehints>=2.0.0",
+    "myst-parser>=3.0.0", # Markdown support in Sphinx
+]
+
+# All optional dependencies combined
+all = [
+]
+
+#------------------------------------------------------------------------------
+# COMMAND-LINE SCRIPTS
+# Entry points for command-line executables installed with the package.
+#------------------------------------------------------------------------------
+[project.scripts]
+vpw = "vexy_pdf_werk.cli:main"
+
+#------------------------------------------------------------------------------
+# BUILD SYSTEM CONFIGURATION
+# Defines the tools required to build the package and the build backend.
+#------------------------------------------------------------------------------
+[build-system]
+# Hatchling is a modern build backend for Python packaging
+# hatch-vcs integrates with version control systems for versioning
+requires = [
+    'hatchling>=1.27.0', # Keep hatchling as is, update if newer hatchling version is required
+    'hatch-vcs>=0.4.0', # Keep hatch-vcs as is, update if newer hatch-vcs version is required
+]
+build-backend = 'hatchling.build' # Specifies Hatchling as the build backend
+
+
+#------------------------------------------------------------------------------
+# HATCH BUILD CONFIGURATION
+# Configures the build process, specifying which packages to include and
+# how to handle versioning.
+#------------------------------------------------------------------------------
+[tool.hatch.build]
+# Include package data files
+include = [
+    "src/vexy_pdf_werk/py.typed", # For better type checking support
+    "src/vexy_pdf_werk/data/**/*", # Include data files if any
+
+]
+exclude = ["**/__pycache__", "**/.pytest_cache", "**/.mypy_cache"]
+
+[tool.hatch.build.targets.wheel]
+only-include = ["src/vexy_pdf_werk"]
+sources = ["src"]
+reproducible = true
+
+# Version control system hook configuration
+# Automatically updates the version file from git tags
+[tool.hatch.build.hooks.vcs]
+version-file = "src/vexy_pdf_werk/_version.py"
+template = '''
+__version__ = "{version}"
+__version_tuple__ = {version_tuple}
+'''
+
+# Version source configuration
+[tool.hatch.version]
+source = 'vcs' # Get version from git tags or other VCS info
+raw-options = { local_scheme = "no-local-version" } # Clean version format without local identifiers
+
+# Metadata handling configuration
+[tool.hatch.metadata]
+allow-direct-references = true # Allow direct references in metadata (useful for local dependencies)
+
+
+#------------------------------------------------------------------------------
+# DEVELOPMENT ENVIRONMENTS
+
+[tool.hatch.envs.default]
+features = ['dev', 'test', 'all']
+installer = "uv" # Use uv for fast dependency resolution and installation
+dependencies = []
+dev-mode = true
+python = "3.12"
+
+# Commands available in the default environment
+[tool.hatch.envs.default.scripts]
+# Run tests with optional arguments
+test = 'pytest {args:tests}'
+# Run tests with coverage reporting
+test-cov = "pytest --cov-report=term-missing --cov-config=pyproject.toml --cov=src/vexy_pdf_werk --cov=tests {args:tests}"
+# Run type checking
+type-check = "mypy src/vexy_pdf_werk tests"
+# Run linting and formatting
+lint = ["ruff check src/vexy_pdf_werk tests", "ruff format --respect-gitignore src/vexy_pdf_werk tests"]
+# Format and fix style issues
+fmt = ["ruff format --respect-gitignore src/vexy_pdf_werk tests", "ruff check --fix src/vexy_pdf_werk tests"]
+fix = ["ruff check --fix --unsafe-fixes src/vexy_pdf_werk tests", "ruff format --respect-gitignore src/vexy_pdf_werk tests"]
+
+# Matrix configuration to test across multiple Python versions
+
+[[tool.hatch.envs.all.matrix]]
+python = ["3.10", "3.11", "3.12"]
+
+#------------------------------------------------------------------------------
+# SPECIALIZED ENVIRONMENTS
+# Additional environments for specific development tasks.
+#------------------------------------------------------------------------------
+
+# Dedicated environment for linting and code quality checks
+[tool.hatch.envs.lint]
+detached = true # Create a separate, isolated environment
+installer = "uv" # Use uv for fast dependency resolution
+features = ['dev'] # Use dev extras  dependencies 
+
+# Linting environment commands
+[tool.hatch.envs.lint.scripts]
+# Type checking with automatic type installation
+typing = "mypy --install-types --non-interactive {args:src/vexy_pdf_werk tests}"
+# Check style and format code
+style = ["ruff check {args:.}", "ruff format --respect-gitignore {args:.}"]
+# Format and fix style issues
+fmt = ["ruff format --respect-gitignore {args:.}", "ruff check --fix {args:.}"]
+fix = ["ruff check --fix --unsafe-fixes {args:.}", "ruff format --respect-gitignore {args:.}"]
+# Run all ops
+all = ["style", "typing", "fix"]
+
+# Dedicated environment for testing
+[tool.hatch.envs.test]
+features = ['test'] # Use test extras as dependencies
+installer = "uv" # Use uv for fast dependency resolution
+dev-mode = true
+python = "3.12"
+
+# Testing environment commands
+[tool.hatch.envs.test.scripts]
+# Run tests in parallel
+test = "python -m pytest -n auto {args:tests}"
+# Run tests with coverage in parallel
+test-cov = "python -m pytest -n auto --cov-report=term-missing --cov-config=pyproject.toml --cov=src/vexy_pdf_werk --cov=tests {args:tests}"
+# Run benchmarks
+bench = "python -m pytest -v -p no:briefcase tests/test_benchmark.py --benchmark-only"
+# Run benchmarks and save results
+bench-save = "python -m pytest -v -p no:briefcase tests/test_benchmark.py --benchmark-only --benchmark-json=benchmark/results.json"
+
+# Documentation environment
+[tool.hatch.envs.docs]
+features = ['docs']
+installer = "uv" # Use uv for fast dependency resolution
+
+# Documentation environment commands
+[tool.hatch.envs.docs.scripts]
+build = "sphinx-build -b html docs/source docs/build"
+
+# GitHub Actions workflow configuration
+[tool.hatch.envs.ci]
+features = ['test']
+installer = "uv" # Use uv for fast dependency resolution
+dev-mode = true
+python = "3.12"
+
+
+[tool.hatch.envs.ci.scripts]
+test = "pytest --cov=src/vexy_pdf_werk --cov-report=xml"
+
+
+#------------------------------------------------------------------------------
+# CODE QUALITY TOOLS
+# Configuration for linting, formatting, and code quality enforcement.
+#------------------------------------------------------------------------------
+
+#------------------------------------------------------------------------------
+# COVERAGE CONFIGURATION
+# Settings for test coverage measurement and reporting.
+#------------------------------------------------------------------------------
+
+# Path mapping for coverage in different environments
+[tool.coverage.paths]
+vexy_pdf_werk = ["src/vexy_pdf_werk", "*/vexy-pdf-werk/src/vexy_pdf_werk"]
+tests = ["tests", "*/vexy-pdf-werk/tests"]
+
+# Coverage report configuration
+[tool.coverage.report]
+# Lines to exclude from coverage reporting
+exclude_lines = [
+    'no cov', # Custom marker to skip coverage
+    'if __name__ == .__main__.:', # Script execution guard
+    'if TYPE_CHECKING:', # Type checking imports and code
+    'pass', # Empty pass statements
+    'raise NotImplementedError', # Unimplemented method placeholders
+    'raise ImportError', # Import error handling
+    'except ImportError', # Import error handling
+    'except KeyError', # Common error handling
+    'except AttributeError', # Common error handling
+    'except NotImplementedError', # Common error handling
+]
+
+[tool.coverage.run]
+source_pkgs = ["vexy_pdf_werk", "tests"]
+branch = true # Measure branch coverage (if/else statements)
+parallel = true # Support parallel test execution
+omit = [
+    "src/vexy_pdf_werk/_version.py",
+]
+
+#------------------------------------------------------------------------------
+# MYPY CONFIGURATION
+# Configuration for type checking with mypy.
+#------------------------------------------------------------------------------
+
+[tool.mypy]
+python_version = "3.10"
+strict = true # Enable all strict checks
+warn_return_any = true
+warn_unused_configs = true
+warn_redundant_casts = true
+warn_unused_ignores = true
+warn_no_return = true
+warn_unreachable = true
+show_error_codes = true
+enable_error_code = ["ignore-without-code", "redundant-expr", "truthy-bool"]
+
+[[tool.mypy.overrides]]
+module = ["tests.*"]
+disallow_untyped_defs = false
+disallow_incomplete_defs = false
+
+#------------------------------------------------------------------------------
+# PYTEST CONFIGURATION
+# Configuration for pytest, including markers, options, and benchmark settings.
+#------------------------------------------------------------------------------
+
+[tool.pytest.ini_options]
+addopts = "-v --durations=10 -p no:briefcase"
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+console_output_style = "progress"
+filterwarnings = ["ignore::DeprecationWarning", "ignore::UserWarning"]
+log_cli = true
+log_cli_level = "INFO"
+markers = [
+    "benchmark: marks tests as benchmarks (select with '-m benchmark')",
+    "unit: mark a test as a unit test",
+    "integration: mark a test as an integration test",
+    "permutation: tests for permutation functionality", 
+    "parameter: tests for parameter parsing",
+    "prompt: tests for prompt parsing",
+]
+norecursedirs = [
+    ".*",
+    "build",
+    "dist", 
+    "venv",
+    "__pycache__",
+    "*.egg-info",
+    "_private",
+]
+python_classes = ["Test*"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]
+testpaths = ["tests"]
+pythonpath = ["src"]
+
+[tool.pytest-benchmark]
+min_rounds = 100
+min_time = 0.1
+histogram = true
+storage = "file"
+save-data = true
+compare = [
+    "min",    # Minimum time
+    "max",    # Maximum time
+    "mean",   # Mean time
+    "stddev", # Standard deviation
+    "median", # Median time
+    "iqr",    # Inter-quartile range
+    "ops",    # Operations per second
+    "rounds", # Number of rounds
+]
+
+#------------------------------------------------------------------------------
+# RUFF CONFIGURATION
+# Configuration for Ruff, including linter and formatter settings.
+#------------------------------------------------------------------------------ 
+
+# Ruff linter and formatter configuration
+[tool.ruff]
+target-version = "py310"
+line-length = 120
+
+# Linting rules configuration
+[tool.ruff.lint]
+# Rule sets to enable, organized by category
+select = [
+    # flake8 plugins and extensions
+    'A', # flake8-builtins: checks for shadowed builtins
+    'ARG', # flake8-unused-arguments: checks for unused function arguments
+    'ASYNC', # flake8-async: checks for async/await issues
+    'B', # flake8-bugbear: finds likely bugs and design problems
+    'C', # flake8-comprehensions: helps write better list/dict comprehensions
+    'DTZ', # flake8-datetimez: checks for datetime timezone issues
+    'E', # pycodestyle errors: PEP 8 style guide errors
+    'EM', # flake8-errmsg: checks for better error messages
+    'F', # pyflakes: detects various errors
+    'FBT', # flake8-boolean-trap: checks for boolean traps in function signatures
+    'I', # isort: sorts imports
+    'ICN', # flake8-import-conventions: checks for import conventions
+    'ISC', # flake8-implicit-str-concat: checks for implicit string concatenation
+    'LOG', # flake8-logging: checks for logging issues
+    'N', # pep8-naming: checks naming conventions
+    'PLC', # pylint convention: checks for convention issues
+    'PLE', # pylint error: checks for errors
+    'PLR', # pylint refactor: suggests refactors
+    'PLW', # pylint warning: checks for suspicious code
+    'PT', # flake8-pytest-style: checks pytest-specific style
+    'PTH', # flake8-use-pathlib: checks for stdlib path usage vs pathlib
+    'PYI', # flake8-pyi: checks stub files
+    'RET', # flake8-return: checks return statement consistency
+    'RSE', # flake8-raise: checks raise statements
+    'RUF', # Ruff-specific rules
+    'S', # flake8-bandit: checks for security issues
+    'SIM', # flake8-simplify: checks for code simplification opportunities
+    'T', # flake8-print: checks for print statements
+    'TCH', # flake8-type-checking: helps with type-checking
+    'TID', # flake8-tidy-imports: checks for tidy import statements
+    'UP', # pyupgrade: checks for opportunities to use newer Python features
+    'W', # pycodestyle warnings: PEP 8 style guide warnings
+    'YTT', # flake8-2020: checks for misuse of sys.version or sys.version_info
+
+]
+# Rules to ignore (with reasons)
+ignore = [
+    'B027', # Empty method in abstract base class - sometimes needed for interfaces
+    'C901', # Function is too complex - sometimes complexity is necessary
+    'FBT003', # Boolean positional argument in function definition - sometimes unavoidable
+    'PLR0911', # Too many return statements - sometimes needed for readability
+    'PLR0912', # Too many branches - sometimes needed for complex logic
+    'PLR0913', # Too many arguments - sometimes needed in APIs
+    'PLR0915', # Too many statements - sometimes needed for comprehensive functions
+    'PLR1714', # Consider merging multiple comparisons - sometimes less readable
+    'PLW0603', # Using the global statement - sometimes necessary
+    'PT013', # Pytest explicit test parameter - sometimes clearer
+    'PTH123', # Path traversal - sometimes needed
+    'PYI056', # Calling open() in pyi file - sometimes needed in type stubs
+    'S105', # Possible hardcoded password - often false positives
+    'S106', # Possible hardcoded password - often false positives
+    'S107', # Possible hardcoded password - often false positives
+    'S110', # try-except-pass - sometimes valid for suppressing exceptions
+    'SIM102', # Nested if statements - sometimes more readable than combined conditions
+]
+# Rules that should not be automatically fixed
+unfixable = [
+    'F401', # Don't automatically remove unused imports - may be needed later
+
+]
+# Configure exclude to ignore specific directories
+exclude = [".git", ".venv", "venv", "dist", "build"]
+
+# isort configuration within Ruff
+[tool.ruff.lint.isort]
+known-first-party = ['vexy_pdf_werk'] # Treat as first-party imports for sorting
+
+# flake8-tidy-imports configuration within Ruff
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = 'all' # Ban all relative imports for consistency
+
+# Per-file rule exceptions
+[tool.ruff.lint.per-file-ignores]
+# Tests can use magic values, assertions, and relative imports
+'tests/**/*' = [
+    'PLR2004', # Allow magic values in tests for readability
+    'S101', # Allow assertions in tests
+    'TID252'
+    # Allow relative imports in tests for convenience
+]

vexy_pdf_werk-1.1.2.dev0/src/vexy_pdf_werk/_version.py

@@ -0,0 +1,2 @@
+__version__ = "1.1.2.dev0"
+__version_tuple__ = (1, 1, 2, 'dev0')