pyproject.toml

[build-system]
requires = ["setuptools>=68", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "pdf2struct"
version = "0.2.0"
description = "pdf2struct: extract structured JSON from PDFs (text, metadata, tables, OCR, invoice key-value fields)."
readme = "README.md"
requires-python = ">=3.9"
license = {text = "MIT"}
authors = [{name="Kubenew"}]
keywords = ["pdf", "ocr", "invoice", "parser", "extract", "table", "json"]
classifiers = [
  "Programming Language :: Python :: 3",
  "License :: OSI Approved :: MIT License",
  "Intended Audience :: Developers",
  "Topic :: Text Processing",
]

dependencies = [
  "pydantic>=2.0.0",
  "pdfplumber>=0.11.0",
]

[project.optional-dependencies]
ocr = [
  "pytesseract>=0.3.10",
  "Pillow>=10.0.0"
]
dev = ["pytest>=7.0.0", "build>=1.0.0", "twine>=4.0.0"]

[project.scripts]
pdf2struct = "pdf2struct.cli:main"

[project.urls]
Homepage = "https://github.com/Kubenew/pdf2struct"
Repository = "https://github.com/Kubenew/pdf2struct"

[tool.setuptools.packages.find]
where = ["."]
include = ["pdf2struct*"]