refactor

Author: sidxz

.github/workflows/ci.yml

@@ -0,0 +1,31 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Set up Python
+        run: uv python install 3.12
+
+      - name: Install dependencies
+        run: uv sync --dev
+
+      - name: Lint
+        run: uv run ruff check structflo/ tests/
+
+      - name: Format
+        run: uv run ruff format --check structflo/ tests/
+
+      - name: Test
+        run: uv run pytest -q

.github/workflows/publish.yml

@@ -0,0 +1,35 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # trusted publishing
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Set up Python
+        run: uv python install 3.12
+
+      - name: Install dependencies
+        run: uv sync --dev
+
+      - name: Lint
+        run: uv run ruff check structflo/ tests/
+
+      - name: Test
+        run: uv run pytest -q
+
+      - name: Build
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

Makefile

@@ -0,0 +1,35 @@
+.PHONY: install lint format check test clean build
+
+## Install all dependencies (including dev)
+install:
+	uv sync --dev
+
+## Run ruff linter
+lint:
+	uv run ruff check structflo/ tests/
+
+## Auto-fix lint issues
+fix:
+	uv run ruff check --fix structflo/ tests/
+
+## Format code with ruff
+format:
+	uv run ruff format structflo/ tests/
+
+## Check formatting + lint (CI-friendly, no changes)
+check:
+	uv run ruff format --check structflo/ tests/
+	uv run ruff check structflo/ tests/
+
+## Run tests
+test:
+	uv run pytest -q
+
+## Remove build artifacts
+clean:
+	rm -rf dist/ build/ *.egg-info .pytest_cache
+	find . -type d -name __pycache__ -exec rm -rf {} +
+
+## Build package
+build:
+	uv build

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "structflo-ner"
-version = "0.1.0"
+dynamic = ["version"]
 description = "Drug discovery NER wrapper around LangExtract — zero-config entity extraction for chemistry and biology."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -14,14 +14,45 @@ dataframe = ["pandas>=1.5"]
 dev = [
     "pytest>=7",
     "pytest-mock>=3",
+    "ruff>=0.8",
 ]
 
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
+[tool.hatch.version]
+path = "structflo/ner/__init__.py"
+
 [tool.hatch.build.targets.wheel]
 packages = ["structflo"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
+
+# --------------------------------------------------------------------------- #
+# Ruff
+# --------------------------------------------------------------------------- #
+[tool.ruff]
+target-version = "py310"
+line-length = 100
+
+[tool.ruff.lint]
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # pyflakes
+    "I",   # isort
+    "UP",  # pyupgrade
+    "B",   # flake8-bugbear
+    "SIM", # flake8-simplify
+]
+ignore = [
+    "E501", # line length handled by formatter
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["structflo"]
+
+[tool.ruff.format]
+quote-style = "double"

structflo/ner/__init__.py

@@ -53,6 +53,8 @@
     EntityProfile,
 )
 
+__version__ = "0.1.0"
+
 __all__ = [
     # Main class
     "NERExtractor",

structflo/ner/_entities.py

@@ -1,4 +1,5 @@
 """Typed entity dataclasses for drug discovery NER results."""
+
 from __future__ import annotations
 
 import dataclasses
@@ -124,7 +125,7 @@ def to_dict(self) -> dict:
             "unclassified": [dataclasses.asdict(e) for e in self.unclassified],
         }
 
-    def to_dataframe(self) -> "pd.DataFrame":
+    def to_dataframe(self) -> pd.DataFrame:
         """Return all entities as a flat pandas DataFrame.
 
         Requires pandas to be installed: pip install structflo-ner[dataframe]

structflo/ner/_examples.py

@@ -4,6 +4,7 @@
 designed to give the LLM strong signal about what to extract and at what
 granularity.
 """
+
 from __future__ import annotations
 
 import langextract as lx
@@ -180,7 +181,11 @@
         lx.data.Extraction(
             extraction_class="assay",
             extraction_text="A549 (human lung adenocarcinoma) cell proliferation assay",
-            attributes={"cell_line": "A549", "organism": "human", "assay_format": "cell proliferation"},
+            attributes={
+                "cell_line": "A549",
+                "organism": "human",
+                "assay_format": "cell proliferation",
+            },
         ),
         lx.data.Extraction(
             extraction_class="bioactivity",

structflo/ner/_mapping.py

@@ -1,4 +1,5 @@
 """Maps langextract Extraction objects to typed NEREntity instances."""
+
 from __future__ import annotations
 
 import langextract as lx

structflo/ner/extractor.py

@@ -1,4 +1,5 @@
 """NERExtractor: the main user-facing class for drug discovery NER."""
+
 from __future__ import annotations
 
 import langextract as lx

structflo/ner/profiles.py

@@ -16,6 +16,7 @@
     )
     extractor.extract(text, profile=my_profile)
 """
+
 from __future__ import annotations
 
 import dataclasses
@@ -42,7 +43,7 @@ class EntityProfile:
     prompt: str
     examples: list[lx.data.ExampleData]
 
-    def merge(self, other: "EntityProfile") -> "EntityProfile":
+    def merge(self, other: EntityProfile) -> EntityProfile:
         """Return a new profile combining this profile with another."""
         return EntityProfile(
             name=f"{self.name}+{other.name}",