test_vindex can sometimes fail with UnicodeDecodeError

[QuLogic]

Zarr version

3.0.1

Numcodecs version

0.14.0

Python Version

3.13.1

Operating System

Fedora Rawhide

Installation

source

Description

It appears that this tests uses some Hypothesis testing, but it isn't constrained sufficiently to not input invalid data.

Steps to reproduce

pytest -k test_vindex

Additional output

_________________________________ test_vindex __________________________________

    @given(data=st.data())
>   def test_vindex(data: st.DataObject) -> None:

tests/test_properties.py:36: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
tests/test_properties.py:38: in test_vindex
    zarray = data.draw(arrays(shapes=npst.array_shapes(max_dims=4, min_side=1)))
/usr/lib/python3.13/site-packages/hypothesis/strategies/_internal/core.py:2151: in draw
    result = self.conjecture_data.draw(strategy, observe_as=f"generate:{desc}")
/usr/lib/python3.13/site-packages/hypothesis/internal/conjecture/data.py:2509: in draw
    v = strategy.do_draw(self)
/usr/lib/python3.13/site-packages/hypothesis/strategies/_internal/lazy.py:167: in do_draw
    return data.draw(self.wrapped_strategy)
/usr/lib/python3.13/site-packages/hypothesis/internal/conjecture/data.py:2503: in draw
    return strategy.do_draw(self)
/usr/lib/python3.13/site-packages/hypothesis/strategies/_internal/core.py:1775: in do_draw
    return self.definition(data.draw, *self.args, **self.kwargs)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/testing/strategies.py:167: in arrays
    a[:] = nparray
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/array.py:2471: in __setitem__
    self.set_orthogonal_selection(pure_selection, value, fields=fields)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/_compat.py:43: in inner_f
    return f(*args, **kwargs)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/array.py:2927: in set_orthogonal_selection
    return sync(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/sync.py:142: in sync
    raise return_result
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/sync.py:98: in _runner
    return await coro
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/array.py:1361: in _set_selection
    await self.codec_pipeline.write(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/codec_pipeline.py:468: in write
    await concurrent_map(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/common.py:68: in concurrent_map
    return await asyncio.gather(*[asyncio.ensure_future(run(item)) for item in items])
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/common.py:66: in run
    return await func(*item)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/codec_pipeline.py:403: in write_batch
    chunk_bytes_batch = await self.encode_batch(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/codec_pipeline.py:210: in encode_batch
    chunk_bytes_batch = await self.array_bytes_codec.encode(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/abc/codec.py:152: in encode
    return await _batching_helper(self._encode_single, chunks_and_specs)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/abc/codec.py:407: in _batching_helper
    return await concurrent_map(
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/common.py:68: in concurrent_map
    return await asyncio.gather(*[asyncio.ensure_future(run(item)) for item in items])
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/common.py:66: in run
    return await func(*item)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/abc/codec.py:420: in wrap
    return await func(chunk, chunk_spec)
../BUILDROOT/usr/lib/python3.13/site-packages/zarr/codecs/_v2.py:88: in _encode_single
    chunk = await asyncio.to_thread(f.encode, chunk)
/usr/lib64/python3.13/asyncio/threads.py:25: in to_thread
    return await loop.run_in_executor(None, func_call)
/usr/lib64/python3.13/concurrent/futures/thread.py:59: in run
    result = self.fn(*self.args, **self.kwargs)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

>   ???
E   UnicodeEncodeError: 'utf-8' codec can't encode character '\ud800' in position 0: surrogates not allowed
E   while generating 'Draw 1' from arrays(shapes=array_shapes(max_dims=4))
E   Falsifying example: test_vindex(
E       data=data(...),
E   )
E   Explanation:
E       These lines were always and only run by failing examples:
E           /builddir/build/BUILD/python-zarr-3.0.1-build/BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/sync.py:142
E           /builddir/build/BUILD/python-zarr-3.0.1-build/BUILDROOT/usr/lib/python3.13/site-packages/zarr/core/sync.py:99
E           /usr/lib64/python3.13/asyncio/futures.py:356
E           /usr/lib64/python3.13/asyncio/tasks.py:841
E           /usr/lib64/python3.13/asyncio/tasks.py:842
E           (and 5 more with settings.verbosity >= verbose)

numcodecs/vlen.pyx:105: UnicodeEncodeError