GitHub Actions

.github/workflows/python-ci.yml

@@ -0,0 +1,27 @@
+name: Python CI
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v5
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: "0.9.6"
+
+      - name: Set up Python
+        run: uv python install
+
+      - name: Install dependencies
+        run: make update
+
+      - name: Run tests
+        run: make test
+
+      - name: Lint check
+        run: make lint-check

Makefile

@@ -0,0 +1,107 @@
+# Default target
+.DEFAULT_GOAL := help
+
+# Colors for output
+BLUE := \033[36m
+GREEN := \033[32m
+YELLOW := \033[33m
+RED := \033[31m
+RESET := \033[0m
+
+# Configuration
+VENV_NAME := .venv
+TEST_PATH := tests/
+SRC_PATH := src/
+
+# Command shortcuts
+UV := uv
+RUFF := uv run ruff
+TY := uv run ty
+PYTEST := uv run pytest
+
+
+.PHONY: help
+help: ## Show this help message
+	@echo "$(BLUE)MDVerse Grodecoder$(RESET)"
+	@echo "Available targets:"
+	@awk 'BEGIN {FS = ":.*?## "} /^[a-zA-Z_-]+:.*?## / {printf "  $(GREEN)%-20s$(RESET) %s\n", $$1, $$2}' $(MAKEFILE_LIST)
+
+# Environment setup
+.PHONY: venv
+venv: ## Create a virtual environment using uv
+	@echo "$(BLUE)Creating virtual environment...$(RESET)"
+	$(UV) sync
+	@echo "$(GREEN)Virtual environment created. Activate with: source $(VENV_NAME)/bin/activate$(RESET)"
+
+.PHONY: install
+install: ## Install package dependencies
+	@echo "$(BLUE)Installing dependencies...$(RESET)"
+	$(UV) pip install -e .
+	@echo "$(GREEN)Dependencies installed$(RESET)"
+
+.PHONY: install-dev
+install-dev: ## Install package with development dependencies
+	@echo "$(BLUE)Installing development dependencies...$(RESET)"
+	$(UV) pip install -e ".[test,dev]"
+	@echo "$(GREEN)Development dependencies installed$(RESET)"
+
+.PHONY: deps
+deps: ## Update and sync dependencies
+	@echo "$(BLUE)Updating dependencies...$(RESET)"
+	$(UV) lock
+	$(UV) sync
+	@echo "$(GREEN)Dependencies updated$(RESET)"
+
+# Package management
+update: ## Update all dependencies to latest versions
+	@echo "$(BLUE)Updating dependencies...$(RESET)"
+	$(UV) lock --upgrade
+	$(UV) sync
+	@echo "$(GREEN)Dependencies updated$(RESET)"
+
+.PHONY: build
+build: clean ## Build the package
+	@echo "$(BLUE)Building package...$(RESET)"
+	$(UV) build
+	@echo "$(GREEN)Package built successfully$(RESET)"
+
+# Cleaning tasks
+.PHONY: clean
+clean: ## Clean build artifacts
+	@echo "$(BLUE)Cleaning build artifacts...$(RESET)"
+	rm -rf build/
+	rm -rf dist/
+	rm -rf *.egg-info/
+	rm -rf .pytest_cache/
+	rm -rf .mypy_cache/
+	rm -rf .ruff_cache/
+	find . -type d -name __pycache__ -exec rm -rf {} +
+	find . -type f -name "*.pyc" -delete
+	find . -type f -name "*.pyo" -delete
+	@echo "$(GREEN)Build artifacts cleaned$(RESET)"
+
+# Testing tasks
+.PHONY: test
+test: ## Run tests with pytest
+	@echo "$(BLUE)Running tests...$(RESET)"
+	$(PYTEST) $(TEST_PATH)
+	@echo "$(GREEN)Tests completed$(RESET)"
+
+.PHONY: test-verbose
+test-verbose: ## Run tests with verbose output
+	@echo "$(BLUE)Running tests with verbose output...$(RESET)"
+	$(PYTEST) $(TEST_PATH) -v -s --tb=long
+	@echo "$(GREEN)Tests completed$(RESET)"
+
+# Code quality tasks
+lint-check: ## Check if code is properly formatted
+	@echo "$(BLUE)Running linter...$(RESET)"
+	$(RUFF) check $(SRC_PATH) $(TEST_PATH)
+	$(TY) check $(SRC_PATH)
+	@echo "$(GREEN)Linting completed$(RESET)"
+
+lint-format: ## Format code with ruff
+	@echo "$(BLUE)Formatting code...$(RESET)"
+	$(RUFF) format $(SRC_PATH) $(TEST_PATH)
+	$(RUFF) check $(SRC_PATH) $(TEST_PATH) --fix
+	@echo "$(GREEN)Code formatted$(RESET)"

pyproject.toml

@@ -22,7 +22,6 @@ grodecoder = "grodecoder.cli:cli"
 [dependency-groups]
 dev = [
     "icecream>=2.1.4",
-    "mypy>=1.17.1",
     "pytest>=8.3.5",
     "ruff>=0.11.2",
     "types-requests>=2.32.4.20250809",
@@ -32,6 +31,7 @@ dev = [
     "requests>=2.32.3",
     "streamlit>=1.44.0",
     "watchdog>=6.0.0",
+    "ty==0.0.1a26",
 ]
 
 [tool.ruff]

src/grodecoder/identifier.py

@@ -34,6 +34,7 @@ def identify_small_molecule(
 
 def identify(universe: UniverseLike, bond_threshold: float = 5.0) -> Inventory:
     """Identifies the molecules in a structure file."""
+    assert universe.atoms is not None  # avoids ty error "Expect Sized"
     timer_start = time.perf_counter()  # do not include structure reading time in the performance measurement
     inventory = _identify(universe, bond_threshold)
     elapsed = time.perf_counter() - timer_start

src/grodecoder/toputils.py

@@ -23,7 +23,9 @@ def formula(molecule: UniverseLike, elements: Iterable[str] = ("C", "H", "O", "N
 
     The formula is based on the first residue alone.
     """
-    atoms = molecule.atoms.residues[0].atoms
+    residues = getattr(molecule.atoms, "residues", [])
+    assert len(residues) > 0
+    atoms = residues[0].atoms
     count = collections.Counter(_first_alpha(atom.name) for atom in atoms)
     formula = "".join(
         f"{element}{count[element]}" if count[element] > 1 else element
@@ -37,7 +39,7 @@ def sequence(atoms: UniverseLike) -> str:
     """Returns the protein sequence from a set of atoms."""
     residue_names = get_amino_acid_name_map()
     residue_names.update(get_nucleotide_name_map())
-    return "".join(residue_names.get(residue.resname, "X") for residue in atoms.residues)
+    return "".join(residue_names.get(residue.resname, "X") for residue in getattr(atoms, "residues", []))
 
 
 def has_bonds(residue: Residue, cutoff: float = 2.0):
@@ -102,13 +104,15 @@ def end_of_chain():
 
     segments = []
 
+    assert (residues := getattr(universe, "residues", [])) and len(residues) > 0
+
     start_current_chain = 0
-    for i, current_residue in enumerate(universe.residues[:-1]):
-        next_residue = universe.residues[i + 1]
+    for i, current_residue in enumerate(residues[:-1]):
+        next_residue = residues[i + 1]
         if end_of_chain():
             segments.append((start_current_chain, i))
             start_current_chain = i + 1
-    segments.append((start_current_chain, len(universe.residues) - 1))
+    segments.append((start_current_chain, len(residues) - 1))
 
     return segments
 
@@ -123,7 +127,8 @@ def guess_resolution(universe: UniverseLike) -> MolecularResolution:
     If none of the first five residues have bonds, the resolution is considered coarse-grained.
     """
     # Select the first five residues with at least two atoms.
-    residues = [residue for residue in universe.residues if len(residue.atoms) >= 2][:5]
+    assert (residues := getattr(universe, "residues", [])) and len(residues) > 0
+    residues = [residue for residue in residues if len(residue.atoms) >= 2][:5]
     for residue in residues:
         if has_bonds(residue, cutoff=2.0):
             return MolecularResolution.ALL_ATOM