heidi-anonymizer/pyproject.toml at main · stackabletech/heidi-anonymizer · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "heidi-anonymizer"
version = "0.1.0"
description = "Service for redaction and anonymization of structured data using Microsoft Presidio"
readme = "README.md"
# Pin to 3.13 because spacy doesn't support 3.14
requires-python = "==3.13.*"
dependencies = [
    # Core PII detection and anonymization
    "presidio-analyzer>=2.2.0",
    "presidio-anonymizer>=2.2.0",

    # NLP engine for Presidio
    "spacy>=3.0.0",

    # File format extraction
    "pdfminer.six>=20221105",
    "python-docx>=0.8.11",
    "Pillow>=9.0.0",

    # OCR for images
    # Note: pytesseract requires the system package 'tesseract-ocr' to be installed
    # Install via: sudo apt install tesseract-ocr (Linux) or brew install tesseract (macOS)
    "pytesseract>=0.3.10",

    # Synthetic data generation for anonymization
    "faker>=8.0.0",

    # Configuration and output formatting
    "pyyaml>=6.0",

    # CLI framework
    "click>=8.0.0",

    # HTTP client for Jira API
    "requests>=2.28.0",
]

[project.optional-dependencies]
dev = [
    "ruff>=0.1.0",
    "black>=23.0.0",
    "mypy>=1.0.0",
    "pytest>=7.0.0",
    "pytest-cov>=4.0.0",
]

[project.scripts]
heidi-anonymizer = "heidi_anonymizer.cli:main"
heidi-jira-fetch = "heidi_anonymizer.jira_cli:main"

[tool.setuptools.packages.find]
where = ["src"]

[tool.black]
# Needs to match the requires-python config above
target-version = ["py313"]