pyproject.toml

[build-system]
requires = ["flit_core>=3.8.0"]
build-backend = "flit_core.buildapi"
  
# Project metadata and dependencies via PEP 621 for uv package manager
[project]
name = "pdf-ocr-pipeline"
version = "0.1.0"
requires-python = ">=3.8"
description = "A tool to extract text from PDF documents using OCR"
readme = "README.md"
readme-content-type = "text/markdown"
authors = [ { name = "PDF OCR Pipeline Contributors", email = "your.email@example.com" } ]
license = { text = "MIT" }
keywords = ["pdf", "ocr", "tesseract", "poppler", "openai", "gpt-4"]
classifiers = [
  "Development Status :: 3 - Alpha",
  "Intended Audience :: Developers",
  "License :: OSI Approved :: MIT License",
  "Programming Language :: Python :: 3",
  "Programming Language :: Python :: 3.8",
  "Programming Language :: Python :: 3.9",
  "Programming Language :: Python :: 3.10",
  "Topic :: Text Processing :: OCR",
  "Topic :: Utilities",
]
dependencies = ["openai>=1.75.0", "pydantic>=2.0"]
  
[project.scripts]
pdf-ocr = "pdf_ocr_pipeline.cli:main"
pdf-ocr-summarize = "pdf_ocr_pipeline.summarize:main"
pdf-ocr-segment = "pdf_ocr_pipeline.segment_cli:main"
  
[project.optional-dependencies]
dev = [
  "pytest>=7.0.0",
  "pytest-cov>=3.0.0",
  "black>=22.1.0",
  # Ruff replaces Flake8 for linting
  "ruff>=0.4.4",
  "mypy>=0.931",
  "tox>=3.24.5",
  "build>=0.7.0",
  "twine>=4.0.0",
  # Pin to <3.6 so we retain Python 3.8 compatibility (pre‑commit 3.6+
  # requires Python >=3.9)
  "pre-commit>=3.5.0,<3.6",
]
[tool.black]
line-length = 88
target-version = ['py36', 'py37', 'py38', 'py39']
include = '\.pyi?$'

[tool.mypy]
python_version = "3.8"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
files = ["src/pdf_ocr_pipeline"]
ignore_missing_imports = true

[tool.flake8]
max-line-length = 88
# Ignore E203 (black compatibility) and E501 (line length) because
# our default prompt string intentionally includes long lines and
# black's formatting keeps them as-is.
extend-ignore = "E203,E501"