P0: project setup (packaging, CI, licences, data/oracle scripts)

- pyproject (uv/hatch, ruff, mypy strict, pytest markers), MIT LICENSE, THIRD_PARTY_NOTICES with verbatim BSD-2 (BeadArrayFiles) and MIT (gtc2vcf) - CI workflow for Gitea/GitHub Actions: lint, type check, unit tests - fetch_data.sh p0 now fetches the GSA v4 PGx demo IDATs (the GDA "Demo 36" bundle is a GenomeStudio project), unpacks archives, fixes pipefail bug - make_oracle_gtcs.sh builds bcftools + gtc2vcf and writes oracle GTCs - plan §17: corrected P0 dataset table Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
2026-09-27 16:56:39 +01:00
1 parent 0861b27c2b
commit f10c651f0f
@@ -0,0 +1,64 @@
+[build-system]
+requires = ["hatchling>=1.24"]
+build-backend = "hatchling.build"
+
+[project]
+name = "simurg"
+description = "SimurgArray: open research toolkit for Illumina Infinium genotyping BeadChip data"
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.12"
+authors = [{ name = "Kemal Yaylali" }]
+dynamic = ["version"]
+dependencies = [
+    "numpy>=1.26",   # all numerics
+    "typer>=0.12",   # CLI
+    "rich>=13",      # progress / human-readable output
+    "pyyaml>=6",     # --config files
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8",
+    "pytest-benchmark>=4",
+    "hypothesis>=6.100",
+    "ruff>=0.6",
+    "mypy>=1.11",
+    "types-PyYAML",
+]
+
+[project.scripts]
+simurg = "simurg.cli.main:app"
+
+[tool.hatch.version]
+path = "src/simurg/__init__.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/simurg"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q --strict-markers"
+markers = [
+    "data: needs downloaded datasets under data/ (skipped when absent)",
+    "oracle: compares against a reference implementation under refs/ (skipped when absent)",
+    "slow: long-running test",
+]
+
+[tool.ruff]
+line-length = 120
+target-version = "py312"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "B", "UP", "N", "SIM", "RUF"]
+ignore = ["N802", "N806", "RUF001", "RUF002", "RUF003"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["E501"]
+
+[tool.mypy]
+python_version = "3.12"
+strict = true
+files = ["src/simurg"]
+ignore_missing_imports = true