Merge branch 'main' into cosmx_reader

Author: LucaMarconato

.flake8

@@ -4,6 +4,7 @@ changelog:
             - release-ignore
         authors:
             - pre-commit-ci
+            - pre-commit-ci[bot]
     categories:
         - title: Added
           labels:

.github/release.yml

@@ -4,7 +4,8 @@ on:
     schedule:
         - cron: "0 0 1 * *" # run once a month to prevent artifact expiration
     workflow_dispatch:
-# uncomment and adjust the branch name if you need to add new datasets to the artifact
+    # Uncomment and adjust the branch name if you need to add new datasets to the artifact.
+    # It needs to be a branch in the spatialdata-io origin repository, not from a fork.
 #    push:
 #        branches:
 #            - main
@@ -14,13 +15,17 @@ jobs:
         runs-on: ubuntu-latest
 
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
 
             - name: Download test datasets
               run: |
                   mkdir -p ./data
                   cd ./data
 
+                  # -------
+                  # the Xenium datasets are licensed as CC BY 4.0, as shown here
+                  # https://www.10xgenomics.com/support/software/xenium-onboard-analysis/latest/resources/xenium-example-data
+
                   # 10x Genomics Xenium 2.0.0
                   curl -O https://cf.10xgenomics.com/samples/xenium/2.0.0/Xenium_V1_human_Breast_2fov/Xenium_V1_human_Breast_2fov_outs.zip
                   curl -O https://cf.10xgenomics.com/samples/xenium/2.0.0/Xenium_V1_human_Lung_2fov/Xenium_V1_human_Lung_2fov_outs.zip
@@ -32,9 +37,35 @@ jobs:
                   # 10x Genomics Xenium 3.0.0 (5K) Mouse ileum, nuclear expansion
                   curl -O https://cf.10xgenomics.com/samples/xenium/3.0.0/Xenium_Prime_Mouse_Ileum_tiny/Xenium_Prime_Mouse_Ileum_tiny_outs.zip
 
+                  # 10x Genomics Xenium 4.0.0 (v1) Human ovary, nuclear expansion
+                  curl -O https://cf.10xgenomics.com/samples/xenium/4.0.0/Xenium_V1_Human_Ovary_tiny/Xenium_V1_Human_Ovary_tiny_outs.zip
+
+                  # 10x Genomics Xenium 4.0.0 (v1) Human ovary, multimodal cell segmentation
+                  curl -O https://cf.10xgenomics.com/samples/xenium/4.0.0/Xenium_V1_MultiCellSeg_Human_Ovary_tiny/Xenium_V1_MultiCellSeg_Human_Ovary_tiny_outs.zip
+
+                  # 10x Genomics Xenium 4.0.0 (v1+Protein) Human kidney, multimodal cell segmentation
+                  curl -O https://cf.10xgenomics.com/samples/xenium/4.0.0/Xenium_V1_Protein_Human_Kidney_tiny/Xenium_V1_Protein_Human_Kidney_tiny_outs.zip
+
+                  # -------
+                  # the Visium HD dataset is licensed as CC BY 4.0, as shown here
+                  # https://www.10xgenomics.com/support/software/space-ranger/latest/resources/visium-hd-example-data
+
+                  # 10x Genomics Visium HD 4.0.1 3' Mouse Brain Chunk
+                  curl -O https://cf.10xgenomics.com/samples/spatial-exp/4.0.1/Visium_HD_Tiny_3prime_Dataset/Visium_HD_Tiny_3prime_Dataset_outs.zip
+
+                  # -------
+                  # we received written permission to make the following dataset public and integrate it in the CI system of spatialdata-io
                   # Spatial Genomics seqFISH v2
                   curl -O https://s3.embl.de/spatialdata/raw_data/seqfish-2-test-dataset.zip
 
+                  # -------
+                  # MACSima OMAP datasets are licensed as CC BY 4.0
+                  # OMAP23 for format v1.x.x
+                  curl -o OMAP23_small.zip "https://zenodo.org/api/records/18196452/files-archive"
+
+                  # OMAP10 for format v0.x.x
+                  curl -o OMAP10_small.zip "https://zenodo.org/api/records/18196366/files-archive"
+
             - name: Unzip files
               run: |
                   cd ./data

.github/workflows/prepare_test_data.yaml

@@ -9,11 +9,11 @@ jobs:
         runs-on: ubuntu-latest
         if: startsWith(github.ref, 'refs/tags/v')
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
             - name: Set up Python 3.12
-              uses: actions/setup-python@v4
+              uses: actions/setup-python@v5
               with:
-                  python-version: "3.12"
+                  python-version: "3.13"
                   cache: pip
             - name: Install build dependencies
               run: python -m pip install --upgrade pip wheel twine build

.github/workflows/release.yaml

@@ -18,17 +18,17 @@ jobs:
         strategy:
             fail-fast: false
             matrix:
-                python: ["3.10", "3.12"]
+                python: ["3.11", "3.12", "3.13"]
                 os: [ubuntu-latest]
 
         env:
             OS: ${{ matrix.os }}
             PYTHON: ${{ matrix.python }}
 
         steps:
-            - uses: actions/checkout@v2
+            - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python }}
-              uses: actions/setup-python@v4
+              uses: actions/setup-python@v5
               with:
                   python-version: ${{ matrix.python }}
 
@@ -37,7 +37,7 @@ jobs:
               run: |
                   echo "::set-output name=dir::$(pip cache dir)"
             - name: Restore pip cache
-              uses: actions/cache@v3
+              uses: actions/cache@v4
               with:
                   path: ${{ steps.pip-cache-dir.outputs.dir }}
                   key: pip-${{ runner.os }}-${{ env.pythonLocation }}-${{ hashFiles('**/pyproject.toml') }}
@@ -52,7 +52,7 @@ jobs:
                   pip install --pre -e ".[dev,test]"
 
             - name: Download artifact of test data
-              if: matrix.python == '3.12'
+              if: matrix.python == '3.13'
               uses: dawidd6/action-download-artifact@v9
               with:
                   workflow: prepare_test_data.yaml

.github/workflows/test.yaml

@@ -6,6 +6,7 @@ temp/
 
 # Compiled files
 __pycache__/
+.ipynb_checkpoints/
 
 # Distribution / packaging
 /build/
@@ -35,6 +36,17 @@ _version.py
 node_modules/
 .code-workspace
 
+# memray report
+*.bin
+
+# speedscope report
+profile.speedscope.json
+
 # test datasets (e.g. Xenium ones)
+# symlinks
+data
+# data folder
 data/
 tests/data
+uv.lock
+.asv/

.gitignore

@@ -1,6 +1,5 @@
 [mypy]
 python_version = 3.10
-plugins = numpy.typing.mypy_plugin
 
 ignore_errors = False
 warn_redundant_casts = True

.mypy.ini

@@ -6,41 +6,24 @@ default_stages:
     - pre-push
 minimum_pre_commit_version: 2.16.0
 repos:
-    - repo: https://github.com/psf/black
-      rev: 25.1.0
-      hooks:
-          - id: black
     - repo: https://github.com/rbubley/mirrors-prettier
-      rev: v3.5.1
+      rev: v3.8.1
       hooks:
           - id: prettier
-    - repo: https://github.com/asottile/blacken-docs
-      rev: 1.19.1
-      hooks:
-          - id: blacken-docs
-    - repo: https://github.com/PyCQA/isort
-      rev: 6.0.0
+    - repo: https://github.com/astral-sh/ruff-pre-commit
+      rev: v0.15.2
       hooks:
-          - id: isort
+          - id: ruff
+            args: [--fix, --exit-non-zero-on-fix, --unsafe-fixes]
+          - id: ruff-format
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.15.0
+      rev: v1.19.1
       hooks:
           - id: mypy
             additional_dependencies: [numpy, types-PyYAML]
             exclude: docs/
-    - repo: https://github.com/asottile/yesqa
-      rev: v1.5.0
-      hooks:
-          - id: yesqa
-            additional_dependencies:
-                - flake8-tidy-imports
-                - flake8-docstrings
-                - flake8-rst-docstrings
-                - flake8-comprehensions
-                - flake8-bugbear
-                - flake8-blind-except
     - repo: https://github.com/pre-commit/pre-commit-hooks
-      rev: v5.0.0
+      rev: v6.0.0
       hooks:
           - id: detect-private-key
           - id: check-ast
@@ -49,31 +32,6 @@ repos:
             args: [--fix=lf]
           - id: trailing-whitespace
           - id: check-case-conflict
-    - repo: https://github.com/PyCQA/autoflake
-      rev: v2.3.1
-      hooks:
-          - id: autoflake
-            args:
-                - --in-place
-                - --remove-all-unused-imports
-                - --remove-unused-variable
-                - --ignore-init-module-imports
-    - repo: https://github.com/PyCQA/flake8
-      rev: 7.1.2
-      hooks:
-          - id: flake8
-            additional_dependencies:
-                - flake8-tidy-imports
-                - flake8-docstrings
-                - flake8-rst-docstrings
-                - flake8-comprehensions
-                - flake8-bugbear
-                - flake8-blind-except
-    - repo: https://github.com/asottile/pyupgrade
-      rev: v3.19.1
-      hooks:
-          - id: pyupgrade
-            args: [--py3-plus, --py310-plus, --keep-runtime-typing]
     - repo: local
       hooks:
           - id: forbid-to-commit
@@ -83,7 +41,3 @@ repos:
                 Fix the merge conflicts manually and remove the .rej files.
             language: fail
             files: '.*\.rej$'
-    - repo: https://github.com/PyCQA/doc8
-      rev: v1.1.2
-      hooks:
-          - id: doc8

.pre-commit-config.yaml

@@ -1,9 +1,8 @@
-# https://docs.readthedocs.io/en/stable/config-file/v2.html
 version: 2
 build:
-    os: ubuntu-20.04
+    os: ubuntu-24.04
     tools:
-        python: "3.10"
+        python: "3.12"
 sphinx:
     configuration: docs/conf.py
     fail_on_warning: true

.readthedocs.yaml

@@ -14,6 +14,8 @@
 [badge-pypi]: https://badge.fury.io/py/spatialdata-io.svg
 [link-pypi]: https://pypi.org/project/spatialdata-io/
 
+_We encourage contributions from the community and from developers of spatial technologies. Please see the "How to Contribute" section below._
+
 This package contains reader functions to load common spatial omics formats into SpatialData. Currently, we provide support for:
 
 - 10x Genomics Visium®
@@ -32,6 +34,8 @@ This package contains reader functions to load common spatial omics formats into
 
 Note: all mentioned technologies are registered trademarks of their respective companies.
 
+Please refer to the list of [open Pull Requests](https://github.com/scverse/spatialdata-io/pulls?q=sort%3Aupdated-desc+is%3Apr+is%3Aopen) for readers that are currently being developed.
+
 ## Known limitations
 
 Contributions for addressing the below limitations are very welcomed.
@@ -42,9 +46,7 @@ Contributions for addressing the below limitations are very welcomed.
 
 1. **Open a GitHub Issue**: Start by opening a new issue or commenting on an existing one in the repository. Clearly describe the problem and your proposed changes to avoid overlapping efforts with others.
 
-2. **Submit a Pull Request (PR)**: Once the issue is discussed, submit a PR to the `spatialdata-io` repository. Ensure your PR includes information about a suitable dataset for testing the reader, ideally no larger than 10 GB. Include clear instructions for accessing the data, preferably with a `curl` or `wget` command for easy downloading.
-
-3. **Optional Enhancements**: To facilitate reproducibility and ease of data access, consider adding a folder in the [spatialdata-sandbox](https://github.com/giovp/spatialdata-sandbox) repository. Include a `download.py` and `to_zarr.py` script (refer to examples in the repository) to enable others to reproduce your reader by simply running these scripts sequentially.
+2. **Submit a Pull Request (PR)**: Once the issue is discussed, submit a PR to the `spatialdata-io` repository. If you are contributing a new reader, or extending the reader for a new versions of a technologies, please consult our [contribution guide](https://spatialdata.scverse.org/projects/io/en/latest/contributing.html), which describes the steps to ensure that the pull request can be tested on suitable example data and reviewed efficiently.
 
 ## Getting started