build: sync with cookiecutter-scverse template, adopt mypy (#2577)

Co-authored-by: Philipp A. <flying-sheep@web.de>

Author: flying-sheep

.cruft.json

@@ -1,43 +1,44 @@
 {
-    "template": "https://github.com/scverse/cookiecutter-scverse",
-    "commit": "d383d94fadff9e4e6fdb59d77c68cb900d7cedec",
-    "checkout": "v0.6.0",
-    "context": {
-        "cookiecutter": {
-            "project_name": "anndata",
-            "package_name": "anndata",
-            "project_description": "Annotated data.",
-            "author_full_name": "Philipp Angerer",
-            "author_email": "philipp.angerer@helmholtz-munich.de",
-            "github_user": "scverse",
-            "github_repo": "anndata",
-            "license": "BSD 3-Clause License",
-            "ide_integration": true,
-            "_copy_without_render": [
-                ".github/workflows/build.yaml",
-                ".github/workflows/test.yaml",
-                "docs/_templates/autosummary/**.rst"
-            ],
-            "_exclude_on_template_update": [
-                "CHANGELOG.md",
-                "LICENSE",
-                "README.md",
-                "docs/api.md",
-                "docs/index.md",
-                "docs/notebooks/example.ipynb",
-                "docs/references.bib",
-                "docs/references.md",
-                "src/**",
-                "tests/**"
-            ],
-            "_render_devdocs": false,
-            "_jinja2_env_vars": {
-                "lstrip_blocks": true,
-                "trim_blocks": true
-            },
-            "_template": "https://github.com/scverse/cookiecutter-scverse",
-            "_commit": "d383d94fadff9e4e6fdb59d77c68cb900d7cedec"
-        }
-    },
-    "directory": null
+  "template": "https://github.com/scverse/cookiecutter-scverse",
+  "commit": "707f3faab836f9272912f92188b63b31da70c064",
+  "checkout": "main",
+  "context": {
+    "cookiecutter": {
+      "project_name": "anndata",
+      "package_name": "anndata",
+      "project_description": "Annotated data.",
+      "author_full_name": "Philipp Angerer",
+      "author_email": "philipp.angerer@helmholtz-munich.de",
+      "github_user": "scverse",
+      "github_repo": "anndata",
+      "license": "BSD 3-Clause License",
+      "ide_integration": true,
+      "issue_categorization": "issue types",
+      "_copy_without_render": [
+        ".github/workflows/build.yaml",
+        ".github/workflows/test.yaml",
+        "docs/_templates/autosummary/**.rst"
+      ],
+      "_exclude_on_template_update": [
+        "CHANGELOG.md",
+        "LICENSE",
+        "README.md",
+        "docs/api.md",
+        "docs/index.md",
+        "docs/notebooks/example.ipynb",
+        "docs/references.bib",
+        "docs/references.md",
+        "src/**",
+        "tests/**"
+      ],
+      "_render_devdocs": false,
+      "_jinja2_env_vars": {
+        "lstrip_blocks": true,
+        "trim_blocks": true
+      },
+      "_template": "https://github.com/scverse/cookiecutter-scverse",
+      "_commit": "707f3faab836f9272912f92188b63b31da70c064"
+    }
+  },
+  "directory": null
 }

.editorconfig

@@ -1,13 +1,17 @@
 root = true
 
 [*]
-charset = utf-8
+indent_style = space
+indent_size = 4
 end_of_line = lf
-insert_final_newline = true
+charset = utf-8
 trim_trailing_whitespace = true
+insert_final_newline = true
 max_line_length = 88
-indent_size = 4
-indent_style = space
 
-[*.{yml,yaml}]
+# TOML is formatted by taplo, which is configured for 4 spaces in .taplo.toml
+[{*.{yml,yaml},.cruft.json}]
 indent_size = 2
+
+[Makefile]
+indent_style = tab

.github/dependabot.yml

@@ -1,5 +1,18 @@
 version: 2
 updates:
+  - package-ecosystem: pre-commit
+    directory: /
+    schedule:
+      interval: weekly
+    labels:
+      - no milestone
+      - skip-gpu-ci
+    cooldown:
+      default-days: 7
+    groups:
+      pre-commit:
+        patterns:
+          - "*"
   - package-ecosystem: github-actions
     directory: /
     schedule:
@@ -9,3 +22,7 @@ updates:
       - skip-gpu-ci
     cooldown:
       default-days: 7
+    groups:
+      actions-deps:
+        patterns:
+          - "*"

.github/workflows/codespell.yml

@@ -130,12 +130,34 @@ jobs:
           python -m build --sdist --wheel .
           twine check dist/*
 
+  lint:
+    name: Pre-commit checks
+    runs-on: ubuntu-latest
+    permissions: {}
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          fetch-depth: 0
+          filter: blob:none
+          persist-credentials: false
+
+      - name: Install UV
+        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+        with:
+          enable-cache: true
+
+      - run: uv tool install hatch
+
+      - name: Run pre-commit hooks
+        run: uvx prek run --all-files --show-diff-on-failure --color=always
+
   check:
     if: always()
     needs:
       - get-environments
       - test
       - build
+      - lint
     permissions:
       actions: read
     runs-on: ubuntu-latest

.github/workflows/test-cpu.yml

@@ -8,6 +8,8 @@ __pycache__/
 /node_modules/
 /data/
 /venv/
+.venv/
+/uv.lock
 
 # Distribution / packaging
 /dist/

.gitignore

@@ -1,34 +1,54 @@
-ci:
-  autoupdate_commit_msg: "ci: pre-commit autoupdate"
-
+fail_fast: false
+default_stages:
+  - pre-commit
+  - pre-push
+minimum_pre_commit_version: 2.16.0
 repos:
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.16.1
-    hooks:
-      - id: ruff-check
-        args: ["--fix"]
-      - id: ruff-format
   - repo: https://github.com/biomejs/pre-commit
     rev: v2.5.6
     hooks:
       - id: biome-format
+        exclude: ^\.cruft\.json$ # inconsistent indentation with cruft - file never to be modified manually.
   - repo: https://github.com/ComPWA/taplo-pre-commit
     rev: v0.9.3
     hooks:
       - id: taplo-format
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.16.1
+    hooks:
+      - id: ruff-check
+        types_or: [python, pyi, jupyter]
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
+  - repo: local
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: hatch check types
+        language: system
+        types: [python]
+        files: ^(src|tests)/
+        require_serial: true
+        pass_filenames: false
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v6.0.0
     hooks:
-      - id: trailing-whitespace
-      - id: end-of-file-fixer
+      - id: detect-private-key
+      - id: check-ast
       - id: check-added-large-files
-      - id: check-case-conflict
       - id: check-toml
       - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: [--fix=lf]
+      - id: trailing-whitespace
+      - id: check-case-conflict
+      # Check that there are no merge conflicts (could be generated by template sync)
       - id: check-merge-conflict
-      - id: detect-private-key
+        args: [--assume-in-merge]
       - id: no-commit-to-branch
-        args: ["--branch=main"]
+        args: [--branch=main]
   - repo: https://github.com/codespell-project/codespell
     rev: v2.4.3
     hooks:
@@ -39,3 +59,4 @@ repos:
     rev: v1.29.0
     hooks:
       - id: zizmor
+        args: [--no-progress, --fix]

.pre-commit-config.yaml

@@ -70,6 +70,8 @@ def setup(
             if store_type == "h5ad"
             else zarr.open(f"data_{array_type}.zarr")
         )
+        assert isinstance(self.store, h5py.File | zarr.Group), self.store
+        assert isinstance(self.store["df"], h5py.Group | zarr.Group), self.store["df"]
         self.ds = ad.experimental.read_elem_lazy(self.store["df"], chunks=chunks)
         self.n_obs = self.ds.shape[0]
 

benchmarks/benchmarks/dataset2d.py

@@ -59,6 +59,8 @@ def setup_cache(self):
 
     def setup(self, index: str, use_dask: bool):  # noqa: FBT001
         g = zarr.open(self.filepath)
+        assert isinstance(g, zarr.Group), g
+        assert isinstance(g["X"], zarr.Group), g["X"]
         self.x = read_elem_lazy(g["X"]) if use_dask else sparse_dataset(g["X"])
         self.adata = AnnData(self.x)
         self.index = self._indexers[index]

benchmarks/benchmarks/sparse_dataset.py

@@ -1,5 +1,6 @@
 {
-    "$schema": "https://biomejs.dev/schemas/2.1.1/schema.json",
+    "$schema": "https://biomejs.dev/schemas/2.2.0/schema.json",
+    "vcs": { "enabled": true, "clientKind": "git", "useIgnoreFile": true },
     "formatter": { "useEditorconfig": true },
     "overrides": [
         {