pyproject.toml

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "doc_redaction"
version = "1.1.0"
description = "Redact PDF/image-based documents, or CSV/XLSX files using a Gradio-based GUI interface"
readme = "README.md"
requires-python = ">=3.10"

dependencies = [
    "pdfminer.six==20250506",
    "pdf2image==1.17.0",
    "pymupdf==1.26.3",
    "opencv-python==4.12.0.88",
    "presidio_analyzer==2.2.359",
    "presidio_anonymizer==2.2.359",
    "presidio-image-redactor==0.0.57",
    "pikepdf==9.10.2",
    "pandas==2.3.1",
    "scikit-learn==1.7.1",
    "spacy==3.8.7",
    # Direct URL dependency for spacy model
    "en_core_web_lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.8.0/en_core_web_lg-3.8.0.tar.gz",
    "gradio==5.46.1",
    "boto3==1.40.31",
    "pyarrow==21.0.0",
    "openpyxl==3.1.5",
    "Faker==37.5.3",
    "python-levenshtein==0.27.1",
    "spaczz==0.6.1",
    # Direct URL dependency for gradio_image_annotator wheel
    "gradio_image_annotation @ https://github.com/seanpedrick-case/gradio_image_annotator/releases/download/v0.3.3/gradio_image_annotation-0.3.3-py3-none-any.whl",
    "rapidfuzz==3.13.0",
    "python-dotenv==1.0.1",
    "awslambdaric==3.1.1",
    "python-docx==1.2.0",
    "paddlepaddle==3.1.0",
    "paddleocr==3.1.1",
    "polars==1.33.1"
]

[project.urls]
Homepage = "https://seanpedrick-case.github.io/doc_redaction/"
repository = "https://github.com/seanpedrick-case/doc_redaction"

[project.optional-dependencies]
dev = ["pytest"]

# Configuration for Ruff linter:
[tool.ruff]
line-length = 88
select = ["E", "F", "I"]

# Configuration for a Black formatter:
[tool.black]
line-length = 88
target-version = ['py310']