anndata 0.12.6__tar.gz → 0.12.8__tar.gz

anndata-0.12.8/.cruft.json

@@ -0,0 +1,43 @@
+{
+    "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
+}

{anndata-0.12.6 → anndata-0.12.8}/.github/workflows/test-cpu.yml

@@ -44,6 +44,8 @@ jobs:
       matrix:
         env: ${{ fromJSON(needs.get-environments.outputs.envs) }}
         io_mark: ["zarr_io", "not zarr_io", "dask_distributed"] # dask_distributed should not be run with -n auto as it uses a client with processes
+    permissions:
+      id-token: write  # for codecov OIDC
     env:  # environment variables for use in codecov’s env_vars tagging
       ENV_NAME: ${{ matrix.env.name }}
       IO_MARK: ${{ matrix.io_mark }}
@@ -64,34 +66,33 @@ jobs:
 
       - name: Install dependencies
         run: |
-          # https://github.com/pallets/click/issues/3066
-          uv tool install --with='click!=8.3.0' hatch
+          uv tool install hatch
           hatch -v env create ${{ matrix.env.name }}
 
       - name: Run tests
-        env:
-          COVERAGE_PROCESS_START: ${{ github.workspace }}/pyproject.toml
         run: |
           hatch run ${{ matrix.env.name }}:run-cov -v --color=yes ${{ matrix.io_mark != 'dask_distributed' && '-n auto' || '' }} --junitxml=test-data/test-results.xml -m "${{ matrix.io_mark }}" ${{ matrix.env.args }}
           hatch run ${{ matrix.env.name }}:cov-combine
           hatch run ${{ matrix.env.name }}:coverage xml
+          hatch run ${{ matrix.env.name }}:cov-report
 
       - name: Upload test results
         if: ${{ !cancelled() }}
-        uses: codecov/test-results-action@v1
+        uses: codecov/codecov-action@v5
         with:
-          token: ${{ secrets.CODECOV_TOKEN }}
+          report_type: test_results
           env_vars: ENV_NAME,IO_MARK
+          files: test-data/test-results.xml
+          use_oidc: true
           fail_ci_if_error: true
-          file: test-data/test-results.xml
 
       - name: Upload coverage data
         uses: codecov/codecov-action@v5
         with:
-          token: ${{ secrets.CODECOV_TOKEN }}
           env_vars: ENV_NAME,IO_MARK
-          fail_ci_if_error: true
           files: test-data/coverage.xml
+          use_oidc: true
+          fail_ci_if_error: true
 
   build:
     runs-on: ubuntu-24.04

{anndata-0.12.6 → anndata-0.12.8}/.github/workflows/test-gpu.yml

@@ -52,9 +52,10 @@ jobs:
       - name: Nvidia SMI sanity check
         run: nvidia-smi
 
-      - name: Install yq
+      - name: Install yq # https://cirun.slack.com/archives/C09SNDRB3A8/p1766512487317849?thread_ts=1766512112.938459&cid=C09SNDRB3A8
         run: |
-          sudo snap install yq
+          sudo wget -qO /usr/local/bin/yq https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64
+          sudo chmod +x /usr/local/bin/yq
 
       - name: Extract max Python version from classifiers
         run: |

{anndata-0.12.6 → anndata-0.12.8}/.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.13.0
+    rev: v0.14.7
     hooks:
       - id: ruff-check
         args: ["--fix"]
@@ -10,7 +10,7 @@ repos:
         id: ruff
         args: ["--preview", "--select=PLR0917"]
   - repo: https://github.com/biomejs/pre-commit
-    rev: v2.1.2
+    rev: v2.3.8
     hooks:
       - id: biome-format
   - repo: https://github.com/ComPWA/taplo-pre-commit

{anndata-0.12.6 → anndata-0.12.8}/.readthedocs.yml

@@ -2,7 +2,7 @@ version: 2
 build:
   os: ubuntu-24.04
   tools:
-    python: "3.13"
+    python: "3.14"
   jobs:
     post_checkout:
       # unshallow so version can be derived from tag

{anndata-0.12.6 → anndata-0.12.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anndata
-Version: 0.12.6
+Version: 0.12.8
 Summary: Annotated data.
 Project-URL: Documentation, https://anndata.readthedocs.io/
 Project-URL: Source, https://github.com/scverse/anndata
@@ -31,7 +31,7 @@ Requires-Dist: legacy-api-wrap
 Requires-Dist: natsort
 Requires-Dist: numpy>=1.26
 Requires-Dist: packaging>=24.2
-Requires-Dist: pandas!=2.1.2,>=2.1.0
+Requires-Dist: pandas!=2.1.2,<3,>=2.1.0
 Requires-Dist: scipy>=1.12
 Requires-Dist: zarr!=3.0.*,>=2.18.7
 Provides-Extra: cu11
@@ -57,7 +57,7 @@ Requires-Dist: sphinx-copybutton; extra == 'doc'
 Requires-Dist: sphinx-design>=0.5.0; extra == 'doc'
 Requires-Dist: sphinx-issues>=5.0.1; extra == 'doc'
 Requires-Dist: sphinx-toolbox>=3.8.0; extra == 'doc'
-Requires-Dist: sphinx>=8.2.1; extra == 'doc'
+Requires-Dist: sphinx<9,>=8.2.1; extra == 'doc'
 Requires-Dist: sphinxext-opengraph; extra == 'doc'
 Requires-Dist: towncrier>=24.8.0; extra == 'doc'
 Provides-Extra: gpu
@@ -74,18 +74,18 @@ Requires-Dist: boltons; extra == 'test'
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'test'
 Requires-Dist: dask[distributed]; extra == 'test'
 Requires-Dist: filelock; extra == 'test'
-Requires-Dist: httpx<1.0; extra == 'test'
 Requires-Dist: joblib; extra == 'test'
 Requires-Dist: loompy>=3.0.5; extra == 'test'
 Requires-Dist: matplotlib; extra == 'test'
 Requires-Dist: openpyxl; extra == 'test'
+Requires-Dist: pooch; extra == 'test'
 Requires-Dist: pyarrow; extra == 'test'
+Requires-Dist: pytest; extra == 'test'
 Requires-Dist: pytest-cov; extra == 'test'
 Requires-Dist: pytest-memray; extra == 'test'
 Requires-Dist: pytest-mock; extra == 'test'
 Requires-Dist: pytest-randomly; extra == 'test'
 Requires-Dist: pytest-xdist[psutil]; extra == 'test'
-Requires-Dist: pytest<8.3.4,>=8.2; extra == 'test'
 Requires-Dist: requests; extra == 'test'
 Requires-Dist: scanpy>=1.10; extra == 'test'
 Requires-Dist: scikit-learn; extra == 'test'
@@ -96,18 +96,18 @@ Requires-Dist: boltons; extra == 'test-min'
 Requires-Dist: dask[array]!=2024.8.*,!=2024.9.*,!=2025.2.*,!=2025.3.*,!=2025.4.*,!=2025.5.*,!=2025.6.*,!=2025.7.*,!=2025.8.*,>=2023.5.1; extra == 'test-min'
 Requires-Dist: dask[distributed]; extra == 'test-min'
 Requires-Dist: filelock; extra == 'test-min'
-Requires-Dist: httpx<1.0; extra == 'test-min'
 Requires-Dist: joblib; extra == 'test-min'
 Requires-Dist: loompy>=3.0.5; extra == 'test-min'
 Requires-Dist: matplotlib; extra == 'test-min'
 Requires-Dist: openpyxl; extra == 'test-min'
+Requires-Dist: pooch; extra == 'test-min'
 Requires-Dist: pyarrow; extra == 'test-min'
+Requires-Dist: pytest; extra == 'test-min'
 Requires-Dist: pytest-cov; extra == 'test-min'
 Requires-Dist: pytest-memray; extra == 'test-min'
 Requires-Dist: pytest-mock; extra == 'test-min'
 Requires-Dist: pytest-randomly; extra == 'test-min'
 Requires-Dist: pytest-xdist[psutil]; extra == 'test-min'
-Requires-Dist: pytest<8.3.4,>=8.2; extra == 'test-min'
 Requires-Dist: scanpy>=1.10; extra == 'test-min'
 Requires-Dist: scikit-learn; extra == 'test-min'
 Description-Content-Type: text/markdown

{anndata-0.12.6 → anndata-0.12.8}/benchmarks/benchmarks/dataset2d.py

@@ -18,11 +18,11 @@ class Dataset2D:
     params = (
         ("zarr", "h5ad"),
         ((-1,), None),
-        ("cat", "numeric", "string-array", "nullable-string-array"),
+        ("cat", "numeric", "string-array", "nullable-string-array", "all"),
     )
 
     def setup_cache(self):
-        n_obs = 10000
+        n_obs = 100_000
         array_types = {
             "numeric": np.arange(n_obs),
             "string-array": np.array(["a"] * n_obs),
@@ -40,17 +40,30 @@ class Dataset2D:
                 if writing_string_array_on_disk := (
                     isinstance(v, np.ndarray) and df["a"].dtype == "string"
                 ):
-                    df["a"] = df["a"].to_numpy()
+                    with pd.option_context("future.infer_string", False):  # noqa: FBT003
+                        df["a"] = df["a"].to_numpy()
                 with ad.settings.override(allow_write_nullable_strings=True):
                     ad.io.write_elem(store, "df", df)
                 if writing_string_array_on_disk:
                     assert store["df"]["a"].attrs["encoding-type"] == "string-array"
+        for store in [
+            h5py.File("data_all.h5ad", mode="w"),
+            zarr.open("data_all.zarr", mode="w", zarr_version=2),
+        ]:
+            df = pd.DataFrame(array_types, index=[f"cell{i}" for i in range(n_obs)])
+            # write a string array by triggering:
+            # https://github.com/scverse/anndata/blob/71966500949adcac4e49d2233f06e9f11f438e19/src/anndata/_io/specs/methods.py#L557-L559
+            df["string-array"] = df["string-array"].to_numpy().astype(object)
+            with ad.settings.override(allow_write_nullable_strings=True):
+                ad.io.write_elem(store, "df", df)
 
     def setup(
         self,
         store_type: Literal["zarr", "h5ad"],
         chunks: None | tuple[int],
-        array_type: Literal["cat", "numeric", "string-array", "nullable-string-array"],
+        array_type: Literal[
+            "cat", "numeric", "string-array", "nullable-string-array", "all"
+        ],
     ):
         self.store = (
             h5py.File(f"data_{array_type}.h5ad", mode="r")

{anndata-0.12.6 → anndata-0.12.8}/docs/_key_contributors.rst

@@ -1,10 +1,9 @@
 .. sidebar:: Key Contributors
 
-   * `Isaac Virshup`_: anndata >= 0.7, diverse contributions
+   * Isaac Virshup: anndata >= 0.7, diverse contributions
    * Sergei Rybakov: diverse contributions
-   * `Alex Wolf`_: initial conception/development
+   * Alex Wolf: initial conception/development
    * Philipp Angerer: initial conception/development, software quality
+   * Ilan Gold: improved cloud support, software quality
 
 .. _contributions graph: https://github.com/scverse/anndata/graphs/contributors
-.. _Isaac Virshup: https://twitter.com/ivirshup
-.. _Alex Wolf: https://twitter.com/falexwolf

{anndata-0.12.6 → anndata-0.12.8}/docs/concatenation.rst

@@ -22,14 +22,14 @@ Let's start off with an example:
     >>> from scipy import sparse
     >>> from anndata import AnnData
     >>> pbmc = sc.datasets.pbmc68k_reduced()
-    >>> pbmc
+    >>> pbmc  # doctest: +ELLIPSIS
     AnnData object with n_obs × n_vars = 700 × 765
         obs: 'bulk_labels', 'n_genes', 'percent_mito', 'n_counts', 'S_score', 'G2M_score', 'phase', 'louvain'
         var: 'n_counts', 'means', 'dispersions', 'dispersions_norm', 'highly_variable'
         uns: 'bulk_labels_colors', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups'
         obsm: 'X_pca', 'X_umap'
         varm: 'PCs'
-        obsp: 'distances', 'connectivities'
+        obsp: ...
 
 If we split this object up by clusters of observations, then stack those subsets we'll obtain the same values – just ordered differently.
 

{anndata-0.12.6 → anndata-0.12.8}/docs/conf.py

@@ -85,11 +85,13 @@ napoleon_use_rtype = True  # having a separate entry generally helps readability
 napoleon_use_param = True
 napoleon_custom_sections = [("Params", "Parameters")]
 typehints_defaults = "braces"
+always_use_bars_union = True  # use `|`, not `Union` in types even when on Python ≤3.14
 todo_include_todos = False
 nitpicky = True  # Report broken links
 nitpick_ignore = [  # APIs without an intersphinx entry
-    # This API isn’t actually documented
+    # These APIs aren’t actually documented
     ("py:class", "anndata._core.raw.Raw"),
+    ("py:class", "pandas._libs.missing.NAType"),
     # TODO: remove zappy support; the zappy repo is archived
     ("py:class", "anndata.compat.ZappyArray"),
 ]
@@ -132,10 +134,8 @@ intersphinx_mapping = dict(
     loompy=("https://linnarssonlab.org/loompy", None),
     numpy=("https://numpy.org/doc/stable", None),
     obstore=("https://developmentseed.org/obstore/latest/", None),
-    pandas=("https://pandas.pydata.org/pandas-docs/stable", None),
-    # TODO: switch to `/3` once docs are built with Python 3.14
-    # https://github.com/readthedocs/readthedocs.org/issues/12523
-    python=("https://docs.python.org/3.13", None),
+    pandas=("https://pandas.pydata.org/pandas-docs/version/2.3", None),
+    python=("https://docs.python.org/3", None),
     scipy=("https://docs.scipy.org/doc/scipy", None),
     sklearn=("https://scikit-learn.org/stable", None),
     xarray=("https://docs.xarray.dev/en/stable", None),
@@ -170,8 +170,10 @@ qualname_overrides = {
     "anndata.compat.XDataset": "xarray.Dataset",
     "awkward.highlevel.Array": "ak.Array",
     "numpy.int64": ("py:attr", "numpy.int64"),
+    "numpy.dtypes.StringDType": ("py:attr", "numpy.dtypes.StringDType"),
     "pandas.DataFrame.iloc": ("py:attr", "pandas.DataFrame.iloc"),
     "pandas.DataFrame.loc": ("py:attr", "pandas.DataFrame.loc"),
+    "pandas.core.dtypes.dtypes.BaseMaskedDtype": "pandas.api.extensions.ExtensionDtype",
     # should be fixed soon: https://github.com/tox-dev/sphinx-autodoc-typehints/pull/516
     "types.EllipsisType": ("py:data", "types.EllipsisType"),
     "pathlib._local.Path": "pathlib.Path",

{anndata-0.12.6 → anndata-0.12.8}/docs/fileformat-prose.md

@@ -7,12 +7,13 @@ but will still be read by newer versions of the library.
 ```
 
 AnnData objects are saved on disk to hierarchical array stores like [HDF5]
-(via {doc}`H5py <h5py:index>`) and {doc}`zarr:index`.
+(via {doc}`H5py <h5py:index>`) and {mod}`zarr`.
 This allows us to have very similar structures in disk and on memory.
 
 As an example we’ll look into a typical `.h5ad`/ `.zarr` object that’s been through an analysis.
 The structures are largely equivalent, though there are a few minor differences when it comes to type encoding.
 
+(elements)=
 ## Elements
 
  <!-- I’ve started using h5py since I couldn’t figure out a nice way to print attributes from bash. -->
@@ -69,12 +70,14 @@ For example, we can see that this file represents an `AnnData` object from its m
 
 Using this information, we're able to dispatch onto readers for the different element types that you'd find in an anndata.
 
+(element)=
 ### Element Specification
 
 * An element can be any object within the storage hierarchy (typically an array or group) with associated metadata
 * An element MUST have a string-valued field `"encoding-type"` in its metadata
 * An element MUST have a string-valued field `"encoding-version"` in its metadata that can be evaluated to a version
 
+(anndata)=
 ### AnnData specification (v0.1.0)
 
 * An `AnnData` object MUST be a group.
@@ -88,10 +91,11 @@ Using this information, we're able to dispatch onto readers for the different el
 * The group MAY contain a mapping `varp`. Entries in `varp` MUST be sparse or dense arrays. The entries first two dimensions MUST be of size `n_var`
 * The group MAY contain a mapping `uns`. Entries in `uns` MUST be an anndata encoded type.
 
+(dense-arrays)=
 ## Dense arrays
 
 Dense numeric arrays have the most simple representation on disk,
-as they have native equivalents in H5py {doc}`h5py:high/dataset` and Zarr {doc}`Arrays <zarr:user-guide/arrays>`.
+as they have native equivalents in H5py {doc}`h5py:high/dataset` and {class}`zarr.Array`\ s.
 We can see an example of this with dimensionality reductions stored in the `obsm` group:
 
 `````{tab-set}
@@ -129,11 +133,13 @@ X_pca                    Dataset {38410, 50}
 X_umap                   Dataset {38410, 2}
 ``` -->
 
+(array)=
 ### Dense arrays specification (v0.2.0)
 
 * Dense arrays MUST be stored in an Array object
 * Dense arrays MUST have the entries `'encoding-type': 'array'` and `'encoding-version': '0.2.0'` in their metadata
 
+(sparse-arrays)=
 ## Sparse arrays
 
 Sparse arrays don’t have a native representations in HDF5 or Zarr,
@@ -188,6 +194,8 @@ indptr <zarr.core.Array '/X/indptr' (164115,) int32 read-only>
 
 `````
 
+(csr_matrix)=
+(csc_matrix)=
 ### Sparse array specification (v0.1.0)
 
 * Each sparse array MUST be its own group
@@ -197,6 +205,7 @@ indptr <zarr.core.Array '/X/indptr' (164115,) int32 read-only>
     * `"encoding-version"`, which is set to `"0.1.0"`
     * `"shape"` which is an integer array of length 2 whose values are the sizes of the array's dimensions
 
+(dataframes)=
 ## DataFrames
 
 DataFrames are saved as a columnar format in a group, so each column of a DataFrame is saved as a separate array.
@@ -263,6 +272,7 @@ feature_is_filtered <zarr.core.Array '/var/feature_is_filtered' (40145,) bool re
 {'encoding-type': 'array', 'encoding-version': '0.2.0'}
 ```
 
+(dataframe)=
 ### Dataframe Specification (v0.2.0)
 
 * A dataframe MUST be stored as a group
@@ -274,6 +284,7 @@ feature_is_filtered <zarr.core.Array '/var/feature_is_filtered' (40145,) bool re
 * Each entry in the group MUST correspond to an array with equivalent first dimensions
 * Each entry SHOULD share chunk sizes (in the HDF5 or zarr container)
 
+(mappings)=
 ## Mappings
 
 Mappings are simply stored as `Group`s on disk.
@@ -314,13 +325,14 @@ pca/variance_ratio <zarr.core.Array '/uns/pca/variance_ratio' (50,) float64 read
 
 `````
 
-
-
+(dict)=
+(mapping)=
 ### Mapping specifications (v0.1.0)
 
 * Each mapping MUST be its own group
 * The group's metadata MUST contain the encoding metadata `"encoding-type": "dict"`, `"encoding-version": "0.1.0"`
 
+(scalars)=
 ## Scalars
 
 Zero dimensional arrays are used for scalar values (i.e. single values like strings, numbers or booleans).
@@ -363,6 +375,8 @@ random_state <zarr.core.Array '/uns/neighbors/params/random_state' () int64 read
 {'encoding-type': 'string', 'encoding-version': '0.2.0'}
 ```
 
+(numeric-scalar)=
+(string)=
 ### Scalar specification (v0.2.0)
 
 * Scalars MUST be written as a 0 dimensional array
@@ -374,6 +388,7 @@ random_state <zarr.core.Array '/uns/neighbors/params/random_state' () int64 read
     * In zarr, scalar strings MUST be stored as a fixed length unicode dtype
     * In HDF5, scalar strings MUST be stored as a variable length utf-8 encoded string dtype
 
+(categorical-arrays)=
 ## Categorical arrays
 
 ```python
@@ -414,6 +429,7 @@ codes <zarr.core.Array '/obs/development_stage/codes' (164114,) int8 read-only>
 
 `````
 
+(categorical)=
 ### Categorical array specification (v0.2.0)
 
 * Categorical arrays MUST be stored as a group
@@ -423,6 +439,7 @@ codes <zarr.core.Array '/obs/development_stage/codes' (164114,) int8 read-only>
     * The `"codes"` array MAY contain signed integer values. If so, the code `-1` denotes a missing value
 * The group MUST contain an array called `"categories"`
 
+(string-arrays)=
 ## String arrays
 
 Arrays of strings are handled differently than numeric arrays since numpy doesn't really have a good way of representing arrays of unicode strings.
@@ -457,6 +474,7 @@ Arrays of strings are handled differently than numeric arrays since numpy doesn'
 {'encoding-type': 'string-array', 'encoding-version': '0.2.0'}
 ```
 
+(string-array)=
 ### String array specifications (v0.2.0)
 
 * String arrays MUST be stored in arrays
@@ -464,9 +482,10 @@ Arrays of strings are handled differently than numeric arrays since numpy doesn'
 * In `zarr`, string arrays MUST be stored using `numcodecs`' `VLenUTF8` codec
 * In `HDF5`, string arrays MUST be stored using the variable length string data type, with a utf-8 encoding
 
-## Nullable integers and booleans
+(nullable-arrays)=
+## Nullable integers, booleans, and strings
 
-We support IO with Pandas nullable integer and boolean arrays.
+We support IO with Pandas nullable integer, boolean, and string arrays.
 We represent these on disk similar to `numpy` masked arrays, `julia` nullable arrays, or `arrow` validity bitmaps (see {issue}`504` for more discussion).
 That is, we store an indicator array (or mask) of null values alongside the array of all values.
 
@@ -523,21 +542,33 @@ nullable_integer/values <zarr.core.Array '/nullable_integer/values' (4,) int64>
 {'encoding-type': 'nullable-integer', 'encoding-version': '0.1.0'}
 ```
 
+(nullable-integer)=
 ### Nullable integer specifications (v0.1.0)
 
 * Nullable integers MUST be stored as a group
-* The group's attributes MUST have contain the encoding metadata `"encoding-type": "nullable-integer"`, `"encoding-version": "0.1.0"`
+* The group’s attributes MUST contain the encoding metadata `"encoding-type": "nullable-integer"`, `"encoding-version": "0.1.0"`
 * The group MUST contain an integer valued array under the key `"values"`
 * The group MUST contain an boolean valued array under the key `"mask"`
 
+(nullable-boolean)=
 ### Nullable boolean specifications (v0.1.0)
 
 * Nullable booleans MUST be stored as a group
-* The group's attributes MUST have contain the encoding metadata `"encoding-type": "nullable-boolean"`, `"encoding-version": "0.1.0"`
+* The group’s attributes MUST contain the encoding metadata `"encoding-type": "nullable-boolean"`, `"encoding-version": "0.1.0"`
 * The group MUST contain an boolean valued array under the key `"values"`
 * The group MUST contain an boolean valued array under the key `"mask"`
 * The `"values"` and `"mask"` arrays MUST be the same shape
 
+(nullable-string-array)=
+### Nullable string specifications (v0.1.0)
+
+* Nullable strings MUST be stored as a group
+* The group’s attributes MUST contain the encoding metadata `"encoding-type": "nullable-string-array"`, `"encoding-version": "0.1.0"`
+* The group MUST contain a string valued array under the key `"values"`
+* The group MUST contain a boolean valued array under the key `"mask"`
+* The `"values"` and `"mask"` arrays MUST be the same shape
+
+(awkward-array)=
 ## AwkwardArrays
 
 ```{warning}

anndata-0.12.8/docs/index.md

@@ -0,0 +1,21 @@
+```{include} ../README.md
+```
+
+# Latest additions
+
+See {doc}`/release-notes/index`.
+
+```{toctree}
+:hidden: true
+:maxdepth: 1
+
+tutorials/index
+api
+concatenation
+fileformat-prose
+interoperability
+benchmarks
+contributing
+release-notes/index
+references
+```

{anndata-0.12.6 → anndata-0.12.8}/docs/references.rst

@@ -1,11 +1,6 @@
 References
 ----------
 
-.. [Bredikhin22]
-   Bredikhin *et al.* (2022),
-   *MUON: multimodal omics analysis framework*,
-   Genome Biology https://doi.org/10.1186/s13059-021-02577-8.
-
 .. [Hastie09]
    Hastie *et al.* (2009),
    *The Elements of Statistical Learning*,

anndata-0.12.8/docs/release-notes/0.12.7.md

@@ -0,0 +1,12 @@
+(v0.12.7)=
+### 0.12.7 {small}`2025-12-16`
+
+#### Documentation
+
+- Add cruft config & update contributors {smaller}`zethson` ({pr}`2223`)
+
+#### Bug fixes
+
+- Handle `pandas.options.future.infer_string` {smaller}`P Angerer` {smaller}`I Gold` ({pr}`2133`)
+- Ensure there are no dangling file handles in {func}`anndata.experimental.concat_on_disk` when passing `.h5ad`-terminated strings as path inputs. {user}`ilan-gold` ({pr}`2218`)
+- Ensure {attr}`anndata.experimental.backed.Dataset2D.true_index` is carried over when subsetting by columns i.,e `ds[[col1, col2]]` {user}`ilan-gold` ({pr}`2220`)

anndata-0.12.8/docs/release-notes/0.12.8.md

@@ -0,0 +1,10 @@
+(v0.12.8)=
+### 0.12.8 {small}`2026-01-27`
+
+#### Bug fixes
+
+- Actually copy single zarr store input in {func}`anndata.experimental.concat_on_disk` {user}`ilan-gold` ({pr}`2267`)
+- Fix `compressor` kwarg handling when writing to zarr v3 {user}`ilan-gold` ({pr}`2270`)
+- Only open HDF5 file once in backed mode {user}`flying-sheep` ({pr}`2274`)
+- Fix {obj}`numpy.uint` support in {func}`anndata.experimental.read_lazy` and {func}`anndata.experimental.read_elem_lazy` {user}`flying-sheep` ({pr}`2287`)
+- `var` index is loaded into memory if it wasn't previously for {func}`anndata.concat` when {attr}`anndata.AnnData.var` is a {class}`anndata.experimental.backed.Dataset2D` {user}`ilan-gold` ({pr}`2299`)

{anndata-0.12.6 → anndata-0.12.8}/docs/tutorials/zarr-v3.md

@@ -6,7 +6,11 @@ Here is a quick guide on some of our learnings so far:
 
 ## Consolidated Metadata
 
-All `zarr` stores are now consolidated by default when written via {func}`anndata.io.write_zarr` or {meth}`anndata.AnnData.write_zarr`.  For more information on this topic, please seee {ref}`the zarr docs <zarr:user-guide-consolidated-metadata>`.  Practcally, this changes means that once a store has been written, it should be treated as immutable **unless you remove the consolidated metadata and/or rewrite after the mutating operation** i.e., if you wish to use `anndata.io.write_elem` to add a column to `obs`, a `layer` etc. to an existing store.  For example, to mutate an existing store on-disk, you may do:
+All `zarr` stores are now consolidated by default when written via {func}`anndata.io.write_zarr` or {meth}`anndata.AnnData.write_zarr`.
+For more information on this topic, please see the zarr [consolidated metadata] user guide.
+Practcally, this changes means that once a store has been written, it should be treated as immutable **unless you remove the consolidated metadata and/or rewrite after the mutating operation** i.e.,
+if you wish to use {func}`anndata.io.write_elem` to add a column to `obs`, a `layer` etc. to an existing store.
+For example, to mutate an existing store on-disk, you may do:
 
 ```python
 g = zarr.open_group(orig_path, mode="a", use_consolidated=False)
@@ -19,13 +23,14 @@ ad.io.write_elem(
 zarr.consolidate_metadata(g.store)
 ```
 
-In this example, the store was opened unconsolidated (trying to open it as a consolidated store would error out), edited, and then reconsolidated.  Alternatively, one could simple delete the file containing the consolidated metadata first at the root, `.zmetadata`.
+In this example, the store was opened unconsolidated (trying to open it as a consolidated store would error out), edited, and then reconsolidated.
+Alternatively, one could simple delete the file containing the consolidated metadata first at the root, `.zmetadata`.
 
 ## Remote data
 
 We now provide the {func}`anndata.experimental.read_lazy` feature for reading as much of the {class}`~anndata.AnnData` object as lazily as possible, using `dask` and {mod}`xarray`.
 Please note that this feature is experimental and subject to change.
-To enable this functionality in a performant and feature-complete way for remote data sources, we use {doc}`zarr:user-guide/consolidated_metadata` on the `zarr` store (written by default).
+To enable this functionality in a performant and feature-complete way for remote data sources, we use [consolidated metadata] on the `zarr` store (written by default).
 Please note that this introduces consistency issues – if you update the structure of the underlying `zarr` store i.e., remove a column from `obs`, the consolidated metadata will no longer be valid.
 Further, note that without consolidated metadata, we cannot guarantee your stored `AnnData` object will be fully readable.
 And even if it is fully readable, it will almost certainly be much slower to read.
@@ -37,7 +42,7 @@ There are two ways of opening remote `zarr` stores from the `zarr-python` packag
 
 Local data generally poses a different set of challenges.
 First, write speeds can be somewhat slow and second, the creation of many small files on a file system can slow down a filesystem.
-For the "many small files" problem, `zarr` has introduced {ref}`sharding <zarr:user-guide-sharding>` in the v3 file format.
+For the "many small files" problem, `zarr` has introduced [sharding] in the v3 file format.
 We offer {attr}`anndata.settings.auto_shard_zarr_v3` to hook into zarr's ability to automatically compute shards, which is experimental at the moment.
 Manual sharding requires knowledge of the array element you are writing (such as shape or data type), though, and therefore you will need to use {func}`anndata.experimental.write_dispatched` to use custom sharding.
 For example, you cannot shard a 1D array with `shard` sizes `(256, 256)`.
@@ -97,11 +102,13 @@ Therefore, we recommend passing in the {class}`zarr.codecs.BloscCodec` to `compr
 
 ## Dask
 
-Zarr v3 should be compatible with dask, although the default behavior is to use zarr's chunking for dask's own. With sharding, this behavior may be undesirable as shards can often contain many small chunks, thereby slowing down i/o as dask will need to index into the zarr store for every chunk.  Therefore it may be better to customize this behavior by passing `chunks=my_zarr_array.shards` as an argument to {func}`dask.array.from_zarr` or similar.
+Zarr v3 should be compatible with dask, although the default behavior is to use zarr's chunking for dask's own.
+With sharding, this behavior may be undesirable as shards can often contain many small chunks, thereby slowing down i/o as dask will need to index into the zarr store for every chunk.
+Therefore it may be better to customize this behavior by passing `chunks=my_zarr_array.shards` as an argument to {func}`dask.array.from_zarr` or similar.
 
 ## GPU i/o
 
-At the moment, it is unlikely your `anndata` i/o will work if you use {ref}`zarr.config.enable_gpu <zarr:user-guide-gpu>`.
+At the moment, it is unlikely your `anndata` i/o will work if you use [`zarr.config.enable_gpu`][GPU user guide].
 It's *possible* dense data i/o i.e., using {func}`anndata.io.read_elem` will work as expected, but this functionality is untested – sparse data, awkward arrays, and dataframes will not.
 `kvikio` currently provides a {class}`kvikio.zarr.GDSStore` although there are no working compressors at the moment exported from the `zarr-python` package (work is underway for `Zstd`: {pr}`zarr-developers/zarr-python#2863`.
 
@@ -114,5 +121,8 @@ However, `zarr-python` has a fully `async` API and provides its own event-loop s
 We anticipate providing `async` versions of {func}`anndata.io.read_elem` and {func}`anndata.experimental.read_dispatched` so that users can download data asynchronously without using the `zarr-python` event loop.
 We also would like to create an asynchronous partial reader to enable iterative streaming of a dataset.
 
+[consolidated metadata]: https://zarr.readthedocs.io/en/latest/user-guide/consolidated_metadata/
 [`obstore` claims]: https://developmentseed.org/obstore/latest/performance
+[sharding]: https://zarr.readthedocs.io/en/stable/user-guide/arrays/#sharding
 [zarr-benchmarks]: https://github.com/LDeakin/zarr_benchmarks
+[GPU user guide]: https://zarr.readthedocs.io/en/stable/user-guide/gpu/