andreferraro
6a45368cb0
- Added scripts/extract_article_contents.py for batch scraping with stealth Foxcape and triple extraction (Trafilatura, Newspaper4k, Readability) - Created unit, integration, and E2E test suite in tests/test_extract_article_contents.py (90/90 passing) - Updated specs/003-article-content-extractor and README.md with usage documentation and CLI contracts - Passed ruff linting/formatting and mypy type checking cleanly
41 lines
762 B
TOML
41 lines
762 B
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "text-nlp-classifier"
|
|
version = "0.1.0"
|
|
description = "Multilingual NLP Entity Inherence Classifier (POC)"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
dependencies = []
|
|
|
|
[project.optional-dependencies]
|
|
test = [
|
|
"pytest>=7.0.0",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
pythonpath = [".", "src"]
|
|
testpaths = ["tests"]
|
|
python_files = ["test_*.py"]
|
|
python_classes = ["Test*"]
|
|
python_functions = ["test_*"]
|
|
|
|
[tool.pyright]
|
|
extraPaths = [".", "src"]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py310"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "W"]
|
|
ignore = ["E501"]
|
|
|
|
[tool.mypy]
|
|
python_version = "3.12"
|
|
ignore_missing_imports = true
|
|
check_untyped_defs = true
|
|
|