Merge branch 'main' into feature/concat_hdf5_virtual_datasets

ilan-gold · web-flow · commit 729c0f10d222 · 2025-08-28T15:33:59.000+02:00
diff --git a/.github/dependabot.yml b/.github/dependabot.yml
@@ -0,0 +1,9 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    labels:
+      - no milestone
+      - skip-gpu-ci
diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
@@ -11,7 +11,10 @@ env:
 
 defaults:
   run:
-    shell: bash -el {0}
+    # Add `-l` to GitHub’s default bash options to activate mamba environments
+    # https://docs.github.com/en/actions/reference/workflows-and-actions/workflow-syntax#exit-codes-and-error-action-preference
+    # https://github.com/mamba-org/setup-micromamba/#readme
+    shell: bash -elo pipefail {0}
 
 jobs:
   benchmark:
@@ -29,9 +32,10 @@ jobs:
       ASV_DIR: "./benchmarks"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
+          # no blob filter so asv can checkout other commits
 
       - run: git fetch origin main:main
         if: ${{ github.ref_name != 'main' }}
diff --git a/.github/workflows/check-pr.yml b/.github/workflows/check-pr.yml
@@ -24,7 +24,7 @@ env:
 
 jobs:
   check-milestone:
-    name: "Triage: Check Milestone"
+    name: "Triage: Check PR title, milestone, and labels"
     runs-on: ubuntu-latest
     steps:
       - name: Check if merging isn’t blocked
@@ -35,3 +35,7 @@ jobs:
         uses: flying-sheep/check@v1
         with:
           success: ${{ github.event.pull_request.user.login == 'pre-commit-ci[bot]' || github.event.pull_request.milestone != null || contains(env.LABELS, 'no milestone') }}
+      - name: Check if PR title is valid
+        uses: amannn/action-semantic-pull-request@v6
+        env: # Needs repo options: “Squash and merge” with commit message set to “PR title”
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
diff --git a/.github/workflows/close-stale.yml b/.github/workflows/close-stale.yml
@@ -8,7 +8,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v5
+      - uses: actions/stale@v9
         with:
           days-before-issue-stale: -1 # We don't want to mark issues as stale in this action
           days-before-issue-close: 14
diff --git a/.github/workflows/label-stale.yml b/.github/workflows/label-stale.yml
@@ -8,7 +8,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v5
+      - uses: actions/stale@v9
         with:
           days-before-issue-stale: 60
           days-before-pr-stale: -1 # We don't want to mark PRs as stale
diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
@@ -11,7 +11,7 @@ jobs:
     permissions:
       id-token: write # to authenticate as Trusted Publisher to pypi.org
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none
diff --git a/.github/workflows/test-cpu.yml b/.github/workflows/test-cpu.yml
@@ -10,12 +10,7 @@ on:
 env:
   FORCE_COLOR: "1"
 
-defaults:
-  run:
-    shell: bash -el {0}
-
-# Cancel the job if new commits are pushed
-# https://stackoverflow.com/questions/66335225/how-to-cancel-previous-runs-in-the-pr-when-you-push-new-commitsupdate-the-curre
+# Cancel the job if new commits are pushed: https://stackoverflow.com/q/66335225/247482
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -26,11 +21,11 @@ jobs:
     outputs:
       envs: ${{ steps.get-envs.outputs.envs }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           filter: blob:none
           fetch-depth: 0
-      - uses: astral-sh/setup-uv@v5
+      - uses: astral-sh/setup-uv@v6
         with:
           enable-cache: false
       - id: get-envs
@@ -41,6 +36,7 @@ jobs:
               | { name: .key, python: .value.python, args: (.value."extra-args" // [] | join(" ")) }
             )')
           echo "envs=${ENVS_JSON}" | tee $GITHUB_OUTPUT
+
   test:
     needs: get-environments
     runs-on: ubuntu-latest
@@ -51,31 +47,35 @@ jobs:
     env:  # environment variable for use in codecov’s env_vars tagging
       ENV_NAME: ${{ matrix.env.name }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none
 
       - name: Install system dependencies
         run: sudo apt install -y hdf5-tools
 
-      - name: Set up Python ${{ matrix.env.python }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.env.python }}
-
       - name: Install UV
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           enable-cache: true
-          cache-dependency-glob: pyproject.toml
+          python-version: ${{ matrix.env.python }}
 
       - name: Install dependencies
         run: uvx hatch -v env create ${{ matrix.env.name }}
 
       - name: Run tests
         run: uvx hatch run ${{ matrix.env.name }}:run-cov -v --color=yes -n auto --cov --cov-report=xml --junitxml=test-data/test-results.xml -m "${{ matrix.io_mark }}" ${{ matrix.env.args }}
 
+      - name: Upload test results
+        if: ${{ !cancelled() }}
+        uses: codecov/test-results-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          env_vars: ENV_NAME
+          fail_ci_if_error: true
+          file: test-data/test-results.xml
+
       - name: Upload coverage data
         uses: codecov/codecov-action@v5
         with:
@@ -85,17 +85,18 @@ jobs:
           files: test-data/coverage.xml
 
   build:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
           filter: blob:none
 
-      - name: Set up Python 3.13
+      - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.13'
+          python-version: '3.x'
+          cache: pip
 
       - name: Install build tools and requirements
         run: |
@@ -123,6 +124,6 @@ jobs:
       - build
     runs-on: ubuntu-latest
     steps:
-        - uses: re-actors/alls-green@release/v1
-          with:
-            jobs: ${{ toJSON(needs) }}
+      - uses: re-actors/alls-green@release/v1
+        with:
+          jobs: ${{ toJSON(needs) }}
diff --git a/.github/workflows/test-gpu.yml b/.github/workflows/test-gpu.yml
@@ -13,10 +13,6 @@ env:
   PYTEST_ADDOPTS: "-v --color=yes"
   FORCE_COLOR: "1"
 
-defaults:
-  run:
-    shell: bash -el {0}
-
 # Cancel the job if new commits are pushed
 # https://stackoverflow.com/questions/66335225/how-to-cancel-previous-runs-in-the-pr-when-you-push-new-commitsupdate-the-curre
 concurrency:
@@ -48,7 +44,7 @@ jobs:
     timeout-minutes: 30
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v4 # TODO: upgrade once cirun image supports node 24
         with:
           fetch-depth: 0
           filter: blob:none
@@ -66,28 +62,24 @@ jobs:
           max_version=$(echo "$classifiers" | sort -V | tail -1)
           echo "max_python_version=$max_version" >> $GITHUB_ENV
 
-      - name: Install Python
-        uses: actions/setup-python@v5
-        with:
-          # https://github.com/cupy/cupy/issues/8651 cupy does not support python3.13 yet
-          python-version: "3.12"
-
       - name: Install UV
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
         with:
           enable-cache: true
-          cache-dependency-glob: pyproject.toml
+          python-version: ${{ env.max_python_version }}
 
       - name: Install AnnData
-        run: uv pip install --system -e ".[dev,test,cu12]" -c ci/constraints.txt
+        run: |
+          uv venv
+          uv pip install -e ".[dev,test,cu12]" -c ci/constraints.txt
 
       - name: Env list
-        run: pip list
+        run: uv pip list
 
       - name: Run test
-        run: coverage run -m pytest -m gpu -n auto --cov --cov-report=xml
+        run: uv run coverage run -m pytest -m gpu -n auto --cov --cov-report=xml
 
-      - uses: codecov/codecov-action@v4
+      - uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           fail_ci_if_error: true
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.9
+    rev: v0.12.10
     hooks:
       - id: ruff
         args: ["--fix"]
@@ -10,7 +10,7 @@ repos:
         id: ruff
         args: ["--preview", "--select=PLR0917"]
   - repo: https://github.com/biomejs/pre-commit
-    rev: v2.2.0
+    rev: v2.2.2
     hooks:
       - id: biome-format
   - repo: https://github.com/ComPWA/taplo-pre-commit
diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -1,6 +1,6 @@
 version: 2
 build:
-  os: ubuntu-20.04
+  os: ubuntu-24.04
   tools:
     python: "3.13"
   jobs:
diff --git a/docs/release-notes/2084.fix.md b/docs/release-notes/2084.fix.md
diff --git a/docs/release-notes/2087.feature.md b/docs/release-notes/2087.feature.md
@@ -0,0 +1 @@
+Add support for Dask {class}`dask.array.Array`s containing {class}`~scipy.sparse.sparray`s {user}`flying-sheep`
diff --git a/pyproject.toml b/pyproject.toml
@@ -101,7 +101,7 @@ test-min = [
     "pyarrow<21",        # https://github.com/scikit-hep/awkward/issues/3579
     "anndata[dask]",
 ]
-test = [ "anndata[test-min,lazy]" ]
+test = [ "anndata[test-min,lazy]", "fast-array-utils>=1.2.3" ]
 gpu = [ "cupy" ]
 cu12 = [ "cupy-cuda12x" ]
 cu11 = [ "cupy-cuda11x" ]
@@ -250,10 +250,13 @@ single_file = false
 package_dir = "src"
 issue_format = "{{pr}}`{issue}`"
 title_format = "(v{version})=\n### {version} {{small}}`{project_date}`"
-fragment.bugfix.name = "Bug fixes"
-fragment.doc.name = "Documentation"
-fragment.feature.name = "Features"
-fragment.misc.name = "Miscellaneous improvements"
-fragment.performance.name = "Performance"
-fragment.breaking.name = "Breaking changes"
-fragment.dev.name = "Development Process"
+# Valid fragments should be a subset of conventional commit types (except for `breaking`):
+# https://github.com/commitizen/conventional-commit-types/blob/master/index.json
+# style, refactor, test, build, ci: should not go into changelog
+fragment.feat.name = "Features"
+fragment.fix.name = "Bug fixes"
+fragment.docs.name = "Documentation"
+fragment.perf.name = "Performance"
+fragment.chore.name = "Miscellaneous changes"
+fragment.revert.name = "Revert"
+fragment.breaking.name = "Breaking changes"   # add `!` to commit type (e.g. “feature!:”)
diff --git a/src/anndata/_core/merge.py b/src/anndata/_core/merge.py
@@ -146,7 +146,7 @@ def equal_dask_array(a, b) -> bool:
         return False
     if isinstance(b, DaskArray) and tokenize(a) == tokenize(b):
         return True
-    if isinstance(a._meta, CSMatrix):
+    if isinstance(a._meta, CSMatrix | CSArray):
         # TODO: Maybe also do this in the other case?
         return da.map_blocks(equal, a, b, drop_axis=(0, 1)).all()
     else:
diff --git a/src/anndata/_io/specs/methods.py b/src/anndata/_io/specs/methods.py
@@ -876,6 +876,8 @@ def chunk_slice(start: int, stop: int) -> tuple[slice | None, slice | None]:
     for scipy_sparse_type, spec in [
         (sparse.csr_matrix, IOSpec("csr_matrix", "0.1.0")),
         (sparse.csc_matrix, IOSpec("csc_matrix", "0.1.0")),
+        (sparse.csr_array, IOSpec("csr_matrix", "0.1.0")),
+        (sparse.csc_array, IOSpec("csc_matrix", "0.1.0")),
     ]:
         _REGISTRY.register_write(group_type, (array_type, scipy_sparse_type), spec)(
             write_dask_sparse
diff --git a/src/anndata/compat/__init__.py b/src/anndata/compat/__init__.py
@@ -11,7 +11,7 @@
 import h5py
 import numpy as np
 import pandas as pd
-import scipy
+import scipy.sparse
 from numpy.typing import NDArray
 from packaging.version import Version
 from zarr import Array as ZarrArray  # noqa: F401
diff --git a/src/anndata/tests/helpers.py b/src/anndata/tests/helpers.py
diff --git a/tests/test_dask.py b/tests/test_dask.py
diff --git a/tests/test_io_elementwise.py b/tests/test_io_elementwise.py
