Backport PR #2048: (chore): Re-introduce strict warnings (#2055)

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

Author: meeseeksmachine

.github/workflows/test-cpu.yml

@@ -38,7 +38,7 @@ jobs:
           ENVS_JSON=$(NO_COLOR=1 uvx hatch env show --json | jq -c 'to_entries
             | map(
               select(.key | startswith("hatch-test"))
-              | { name: .key, python: .value.python }
+              | { name: .key, python: .value.python, args: (.value."extra-args" // [] | join(" ")) }
             )')
           echo "envs=${ENVS_JSON}" | tee $GITHUB_OUTPUT
   test:
@@ -71,7 +71,7 @@ jobs:
         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}}"
+        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 coverage data
         uses: codecov/codecov-action@v5

hatch.toml

@@ -36,6 +36,7 @@ overrides.matrix.deps.python = [
 overrides.matrix.deps.features = [
     { if = [ "stable", "pre" ], value = "test" },
 ]
+overrides.matrix.deps.extra-args = { if = [ "stable", "pre" ], value = [ "--strict-warnings" ] }
 
 [[envs.hatch-test.matrix]]
 deps = [ "stable", "pre", "min" ]

pyproject.toml

@@ -146,6 +146,7 @@ addopts = [
 filterwarnings = [
     "ignore::anndata._warnings.OldFormatWarning",
     "ignore::anndata._warnings.ExperimentalFeatureWarning",
+    "ignore:.*first_column_names:FutureWarning:scanpy",     # scanpy 1.10.x
 ]
 # When `--strict-warnings` is used, all warnings are treated as errors, except those:
 filterwarnings_when_strict = [
@@ -158,6 +159,8 @@ filterwarnings_when_strict = [
     "default:The codec `vlen-utf8:UserWarning",
     "default:The dtype `StringDType():UserWarning",
     "default:Consolidated metadata is:UserWarning",
+    "default:.*Structured:zarr.core.dtype.common.UnstableSpecificationWarning",
+    "default:.*FixedLengthUTF32:zarr.core.dtype.common.UnstableSpecificationWarning",
 ]
 python_files = "test_*.py"
 testpaths = [

src/anndata/_io/read.py

@@ -48,7 +48,9 @@ def read_csv(
     dtype
         Numpy data type.
     """
-    return read_text(filename, delimiter, first_column_names, dtype)
+    return read_text(
+        filename, delimiter, first_column_names=first_column_names, dtype=dtype
+    )
 
 
 def read_excel(
@@ -360,18 +362,26 @@ def read_text(
         Numpy data type.
     """
     if not isinstance(filename, PathLike | str | bytes):
-        return _read_text(filename, delimiter, first_column_names, dtype)
+        return _read_text(
+            filename, delimiter, first_column_names=first_column_names, dtype=dtype
+        )
 
     filename = Path(filename)
     if filename.suffix == ".gz":
         with gzip.open(str(filename), mode="rt") as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
     elif filename.suffix == ".bz2":
         with bz2.open(str(filename), mode="rt") as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
     else:
         with filename.open() as f:
-            return _read_text(f, delimiter, first_column_names, dtype)
+            return _read_text(
+                f, delimiter, first_column_names=first_column_names, dtype=dtype
+            )
 
 
 def _iter_lines(file_like: Iterable[str]) -> Generator[str, None, None]:
@@ -385,7 +395,8 @@ def _iter_lines(file_like: Iterable[str]) -> Generator[str, None, None]:
 def _read_text(  # noqa: PLR0912, PLR0915
     f: Iterator[str],
     delimiter: str | None,
-    first_column_names: bool | None,  # noqa: FBT001
+    *,
+    first_column_names: bool | None,
     dtype: str,
 ) -> AnnData:
     comments = []

src/anndata/_io/specs/methods.py

@@ -695,12 +695,11 @@ def write_recarray_zarr(
     from anndata.compat import _to_fixed_length_strings
 
     elem = _to_fixed_length_strings(elem)
-    if isinstance(f, H5Group) or is_zarr_v2():
+    if is_zarr_v2():
         f.create_dataset(k, data=elem, shape=elem.shape, **dataset_kwargs)
     else:
         dataset_kwargs = dataset_kwargs.copy()
         dataset_kwargs = zarr_v3_compressor_compat(dataset_kwargs)
-        # TODO: zarr’s on-disk format v3 doesn’t support this dtype
         f.create_array(k, shape=elem.shape, dtype=elem.dtype, **dataset_kwargs)
         f[k][...] = elem
 

tests/test_readwrite.py

@@ -844,7 +844,10 @@ def test_scanpy_krumsiek11(tmp_path, diskfmt, roundtrip):
         import scanpy as sc
 
     # TODO: this should be fixed in scanpy instead
-    with pytest.warns(UserWarning, match=r"Observation names are not unique"):
+    with pytest.warns(UserWarning, match=r"Observation names are not unique"):  # noqa: PT031
+        warnings.filterwarnings(
+            "ignore", r".*first_column_names.*no longer positional", FutureWarning
+        )
         orig = sc.datasets.krumsiek11()
     del orig.uns["highlights"]  # Can’t write int keys
     # Can’t write "string" dtype: https://github.com/scverse/anndata/issues/679

tests/test_structured_arrays.py

@@ -1,12 +1,14 @@
 from __future__ import annotations
 
+import warnings
 from itertools import combinations, product
 from typing import TYPE_CHECKING
 
 import numpy as np
 
 import anndata as ad
 from anndata import AnnData
+from anndata.compat import is_zarr_v2
 from anndata.tests.helpers import gen_vstr_recarray
 
 if TYPE_CHECKING:
@@ -27,7 +29,14 @@ def assert_str_contents_equal(A, B):
 
 def test_io(
     tmp_path, diskfmt: Literal["zarr", "h5ad"], diskfmt2: Literal["zarr", "h5ad"]
-):
+) -> None:
+    if not is_zarr_v2():
+        from zarr.core.dtype.common import UnstableSpecificationWarning
+
+        warnings.filterwarnings(  # raised by “S10” dtype in the recarray below
+            "default", r".*NullTerminatedBytes", UnstableSpecificationWarning
+        )
+
     read1 = lambda pth: getattr(ad, f"read_{diskfmt}")(pth)
     write1 = lambda adata, pth: getattr(adata, f"write_{diskfmt}")(pth)
     read2 = lambda pth: getattr(ad, f"read_{diskfmt2}")(pth)