pyproject.toml

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

[project]
name = "interscript-ml-tools"
version = "0.1.0"
description = "Unified training framework for Interscript ML models (rababa + secryst)"
readme = "README.md"
license = { text = "BSD-3-Clause" }
requires-python = ">=3.10"
authors = [{ name = "Interscript Project" }]
keywords = ["nlp", "transliteration", "diacritization", "onnx", "distillation"]

dependencies = [
  "numpy>=1.26",
  "pyyaml>=6.0",
  "tqdm>=4.66",
  "pydantic>=2.5",
]

[project.optional-dependencies]
train = [
  "torch>=2.2",
  "transformers>=4.42",
  "datasets>=2.18",
  "accelerate>=0.27",
  "peft>=0.10",
  "sentencepiece>=0.2",
]
export = [
  "onnx>=1.16",
  "onnxruntime>=1.17",
]
publish = [
  "huggingface_hub>=0.23",
  "omegaconf>=2.3",
  "pyarrow>=15.0",
]
sadeed = [
  "pyarabic>=0.6",
  "prettytable>=3.9",
  "pandas>=2.0",
  "pyarrow>=14.0",
  "huggingface_hub>=0.23",
]
dev = [
  "pytest>=8.0",
  "pytest-cov>=5.0",
  "ruff>=0.4",
  "mypy>=1.10",
]

[project.scripts]
interscript-ml = "imf.cli:main"
interscript-sadeed-eval = "sadeedbench.cli:main"

[tool.setuptools.packages.find]
where = ["src"]
include = ["framework*", "tasks*", "imf*", "sadeedbench*"]

[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src", "."]
addopts = "-ra -q --strict-markers"
markers = [
  "slow: marks tests as slow (deselect with '-m \"not slow\"')",
  "gpu: marks tests requiring a GPU",
]

[tool.ruff]
line-length = 100
target-version = "py310"
# ADR-0001: the vendored Misraj evaluator is a provenance artifact —
# excluded, never rewritten or reformatted (same policy as rababa's copy)
extend-exclude = ["src/sadeedbench/vendored_sadeed_evaluator.py"]

[tool.ruff.lint]
select = ["E", "F", "I", "B", "UP", "SIM", "C4"]

[tool.mypy]
python_version = "3.10"
strict = true
warn_unused_configs = true