Merge 74c40c1 into d423263

Author: timtreis

.github/workflows/execute.yaml

@@ -2,7 +2,7 @@ name: Execute notebooks
 
 on:
   schedule:
-    # Weekly: Mondays 04:00 UTC — re-executes ALL notebooks against latest releases.
+    # Weekly: Mondays 04:00 UTC; re-executes ALL notebooks against latest releases.
     - cron: "0 4 * * 1"
   pull_request:
     branches: [main]
@@ -22,36 +22,45 @@ jobs:
     timeout-minutes: 60
     steps:
       - uses: actions/checkout@v5
-        with:
-          # Need full history so we can diff PR HEAD against the merge base.
-          fetch-depth: 0
 
       - uses: actions/setup-python@v5
         with:
           python-version: "3.13"
+          cache: pip
+          cache-dependency-path: pyproject.toml
 
       - name: Cache pooch datasets
         uses: actions/cache@v4
         with:
           path: ~/.cache/pooch
-          key: pooch-${{ runner.os }}-${{ hashFiles('**/*.ipynb') }}
+          # Datasets are pinned by URL inside notebook code, not by the
+          # notebook's surrounding markdown — bump the v* suffix when an
+          # actually-new dataset URL lands.
+          key: pooch-${{ runner.os }}-v1
           restore-keys: |
             pooch-${{ runner.os }}-
 
       - name: Install execution environment
         run: |
           pip install --upgrade pip
-          pip install -e ".[exec]" nbdime
+          pip install -e ".[exec]"
+
+      - name: Detect changed notebooks (PR only)
+        if: github.event_name == 'pull_request'
+        id: changed
+        uses: tj-actions/changed-files@v45
+        with:
+          files: |
+            tutorials/**/*.ipynb
+            examples/**/*.ipynb
 
       - name: Determine notebooks to execute
         id: pick
         run: |
-          # On the weekly schedule and manual dispatch, run all notebooks.
-          # On PR, run only notebooks the PR touched, to keep CI fast as the
-          # gallery grows. (sklearn does the same.)
           if [ "${{ github.event_name }}" = "pull_request" ]; then
-            base="${{ github.event.pull_request.base.sha }}"
-            nbs=$(git diff --name-only --diff-filter=AMR "$base"...HEAD -- '*.ipynb' | grep -E '^(tutorials|examples)/' || true)
+            nbs="${{ steps.changed.outputs.all_changed_files }}"
+            # tj-actions emits space-separated; one-per-line for the loop below.
+            nbs=$(printf '%s\n' $nbs)
           else
             nbs=$(find tutorials examples -name "*.ipynb" -not -path "*/.ipynb_checkpoints/*" 2>/dev/null || true)
           fi
@@ -75,15 +84,3 @@ jobs:
             echo "Executing $nb"
             jupyter nbconvert --to notebook --execute --inplace "$nb"
           done <<< "${{ steps.pick.outputs.files }}"
-
-      - name: Diff outputs against committed
-        if: steps.pick.outputs.files != ''
-        run: |
-          # If outputs drift from what's committed, fail the job. Authors are
-          # expected to commit re-executed notebooks; CI catches drift between
-          # commits (e.g., upstream lib changes).
-          if ! git diff --quiet -- '*.ipynb'; then
-            echo "Notebook outputs drifted from committed state:"
-            nbdime diff
-            exit 1
-          fi

.github/workflows/preview.yaml

@@ -33,7 +33,6 @@ jobs:
         with:
           repository: scverse/spatialdata-plot
           path: lib
-          fetch-depth: 0
 
       - name: Mount PR notebooks into lib's submodule path
         run: |
@@ -69,7 +68,10 @@ jobs:
             const pr = context.issue.number;
             const owner = context.repo.owner;
             const repo = context.repo.repo;
-            const url = `https://${owner}.github.io/${repo}/pr-${pr}/gallery.html`;
+            // Use the canonical scverse.org URL directly. The github.io URL
+            // 301-redirects there because of the org-wide CNAME, which makes
+            // the displayed link confusingly different from the destination.
+            const url = `https://scverse.org/${repo}/pr-${pr}/gallery.html`;
             const marker = '<!-- preview-link -->';
             const body = `${marker}\n📖 **Docs preview**: ${url}\n\n_Built from ${context.sha.substring(0, 7)}; redeployed on every push._`;
             const { data: comments } = await github.rest.issues.listComments({ owner, repo, issue_number: pr });

.pre-commit-config.yaml

@@ -1,11 +1,27 @@
+# pre-commit config. Auto-run on PRs by pre-commit.ci (see ci: block below);
+# run locally with `pre-commit run --all-files` after `pip install pre-commit`.
+
+ci:
+  # Auto-fix PRs where possible; tag the commit so it's clearly bot-authored.
+  autofix_commit_msg: |
+    [pre-commit.ci] auto fixes from pre-commit.com hooks
+
+    for more information, see https://pre-commit.ci
+  autofix_prs: true
+  autoupdate_branch: ""
+  autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
+  autoupdate_schedule: monthly
+  skip: []
+  submodules: false
+
 fail_fast: false
 default_language_version:
   python: python3
 minimum_pre_commit_version: 3.0.0
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: check-yaml
       - id: check-toml
@@ -20,14 +36,26 @@ repos:
         exclude: \.ipynb$
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.4
+    rev: v0.15.12
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: [--fix]
       - id: ruff-format
+        # Notebook cells use a chained fluent API; ruff-format collapses
+        # short chains onto one line which hurts readability. Lint notebooks
+        # via nbqa-ruff (below) instead.
+        exclude: \.ipynb$
 
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.9.0
+    rev: 1.9.1
     hooks:
       - id: nbqa-ruff
         args: [--fix]
+
+  - repo: local
+    hooks:
+      - id: strip-widget-metadata
+        name: Strip Jupyter widget metadata from notebooks
+        entry: python scripts/strip_widget_metadata.py
+        language: system
+        files: \.ipynb$

pyproject.toml

@@ -20,6 +20,7 @@ exec = [
     "squidpy",
     "jupyter",
     "ipykernel",
+    "watermark",
 ]
 dev = [
     "pre-commit>=3.0",

scripts/strip_widget_metadata.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""Strip Jupyter widget metadata + outputs from .ipynb files.
+
+Anything using `tqdm.notebook` (pooch downloads, scanpy progress bars in a
+Jupyter kernel) emits widget output blobs whose UUIDs regenerate on every
+execution. Stripping them keeps committed notebooks small and produces
+clean PR diffs that reflect real source changes only.
+
+Usage: strip_widget_metadata.py <notebook> [<notebook> ...]
+Exits 0 if no changes, 1 if files were modified (so pre-commit reports the
+fix the way other auto-fixers do).
+"""
+
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+
+WIDGET_MIME = "application/vnd.jupyter.widget-view+json"
+
+
+def strip(path: Path) -> bool:
+    nb = json.loads(path.read_text())
+    changed = False
+
+    if "widgets" in nb.get("metadata", {}):
+        nb["metadata"].pop("widgets")
+        changed = True
+
+    for cell in nb.get("cells", []):
+        for output in cell.get("outputs", []):
+            data = output.get("data", {})
+            if WIDGET_MIME in data:
+                data.pop(WIDGET_MIME)
+                changed = True
+
+    if changed:
+        path.write_text(json.dumps(nb, indent=1) + "\n")
+    return changed
+
+
+def main() -> int:
+    if len(sys.argv) < 2:
+        print("usage: strip_widget_metadata.py <notebook> [<notebook> ...]", file=sys.stderr)
+        return 2
+    any_changed = False
+    for arg in sys.argv[1:]:
+        if strip(Path(arg)):
+            print(f"stripped widgets: {arg}")
+            any_changed = True
+    return 1 if any_changed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

tutorials/getting_started.ipynb

@@ -8,4 +8,5 @@ spatial elements, and styling a publication-ready figure.
 :maxdepth: 1
 
 getting_started
+visium_mouse_brain
 ```