Initial Open-SWE-Traces cleanup pipeline

pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=70", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "swe-data-processing"
+version = "0.1.0"
+description = "Static quality control and repair planning for Open-SWE-Traces."
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "MIT"}
+authors = [
+  {name = "TIGER Lab"}
+]
+dependencies = [
+  "httpx>=0.27,<1",
+  "jsonschema>=4.23,<5",
+  "pyarrow>=16,<26"
+]
+
+[project.optional-dependencies]
+dev = [
+  "pytest>=8,<10",
+  "ruff>=0.9,<1"
+]
+
+[project.scripts]
+swe-qc = "swe_data_processing.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+swe_data_processing = [
+  "prompts/*.md",
+  "schemas/*.json"
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"
+
+[tool.ruff]
+line-length = 110
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B"]