WIP: Add functionality to virtualize GeoTIFFs using async_tiff

pyproject.toml

@@ -48,7 +48,9 @@ hdf = [
     "imagecodecs",
     "imagecodecs-numcodecs==2024.6.1",
 ]
-
+tiff = [
+    "virtual_tiff @ git+https://github.com/virtual-zarr/virtual-tiff",
+]
 # kerchunk-based parsers
 netcdf3 = [
     "virtualizarr[remote]",
@@ -165,6 +167,9 @@ h5netcdf = ">=1.5.0,<2"
 [tool.pixi.feature.icechunk-dev.dependencies]
 rust = "*"
 
+[tool.pixi.feature.rio.dependencies]
+rioxarray = "*"
+
 [tool.pixi.feature.minimum-versions.dependencies]
 xarray = "==2025.3.0"
 numpy = "==2.0.0"
@@ -187,10 +192,10 @@ run-tests-html-cov = { cmd = "pytest -n auto --run-network-tests --verbose --cov
 [tool.pixi.environments]
 min-deps = ["dev", "test", "hdf", "hdf5-lib"] # VirtualiZarr/conftest.py using h5py, so the minimum set of dependencies for testing still includes hdf libs
 # Inherit from min-deps to get all the test commands, along with optional dependencies
-test = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib"]
-test-py311 = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "py311"] # test against python 3.11
-test-py312 = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "py312"] # test against python 3.12
-minio = ["dev", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "hdf5-lib", "py312", "minio"]
+test = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "tiff", "rio"]
+test-py311 = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "py311", "tiff", "rio"] # test against python 3.11
+test-py312 = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "py312", "tiff", "rio"] # test against python 3.12
+minio = ["dev", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "hdf5-lib", "py312", "minio", "tiff", "rio"]
 minimum-versions = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk", "kerchunk_parquet", "hdf5-lib", "minimum-versions"]
 upstream = ["dev", "test", "hdf", "hdf5-lib", "netcdf3", "upstream", "icechunk-dev"]
 all = ["dev", "test", "remote", "hdf", "netcdf3", "fits", "icechunk", "kerchunk","kerchunk_parquet", "hdf5-lib", "all_parsers", "all_writers"]

virtualizarr/tests/__init__.py

@@ -34,9 +34,10 @@ def _importorskip(
 has_s3fs, requires_s3fs = _importorskip("s3fs")
 has_lithops, requires_lithops = _importorskip("lithops")
 has_scipy, requires_scipy = _importorskip("scipy")
-has_tifffile, requires_tifffile = _importorskip("tifffile")
+has_asynctiff, requires_asynctiff = _importorskip("async_tiff")
 has_imagecodecs, requires_imagecodecs = _importorskip("imagecodecs")
 has_hdf5plugin, requires_hdf5plugin = _importorskip("hdf5plugin")
 has_zarr_python, requires_zarr_python = _importorskip("zarr")
 has_dask, requires_dask = _importorskip("dask")
 has_obstore, requires_obstore = _importorskip("obstore")
+has_rioxarray, requires_rioxarray = _importorskip("rioxarray")

virtualizarr/tests/test_parsers/conftest.py

@@ -16,6 +16,15 @@
     warnings.warn("hdf5plugin is required for HDF reader")
 
 
+@pytest.fixture
+def geotiff_file(tmp_path: Path) -> str:
+    """Create a NetCDF4 file with air temperature data."""
+    filepath = tmp_path / "air.tif"
+    with xr.tutorial.open_dataset("air_temperature") as ds:
+        ds.isel(time=0).rio.to_raster(filepath, driver="COG", COMPRESS="DEFLATE")
+    return str(filepath)
+
+
 @pytest.fixture
 def empty_chunks_hdf5_file(tmpdir):
     ds = xr.Dataset({"data": []})

virtualizarr/tests/test_parsers/test_tiff.py

@@ -0,0 +1,20 @@
+import numpy as np
+import xarray as xr
+from virtual_tiff import TIFFParser
+
+from virtualizarr.tests import requires_asynctiff, requires_rioxarray
+
+
+@requires_asynctiff
+@requires_rioxarray
+def test_read_geotiff(geotiff_file):
+    import rioxarray
+    from obstore.store import LocalStore
+
+    parser = TIFFParser(ifd=0)
+    ms = parser(file_url=f"file://{geotiff_file}", object_store=LocalStore())
+    ds = xr.open_dataset(ms, engine="zarr", consolidated=False, zarr_format=3).load()
+    assert isinstance(ds, xr.Dataset)
+    expected = rioxarray.open_rasterio(geotiff_file).data.squeeze()
+    observed = ds["0"].data.squeeze()
+    np.testing.assert_allclose(observed, expected)