Merge pull request #71 from scverse/mudata-0.3.0rc1

v0.3.0rc1 fixes and improvements

Author: gtca

docs/source/io/input.rst

@@ -61,8 +61,31 @@ MuData objects can be read and cached from remote locations including via HTTP(S
 A caching layer can be added in the following way:
 ::
    fname_cached = "filecache::" + fname
-   with fsspec.open(fname_cached, filecache={'cache_storage': '/tmp/'}):
+   with fsspec.open(fname_cached, filecache={'cache_storage': '/tmp/'}) as f:
       mdata = mudata.read_h5mu(f)
 
 
 For more `fsspec` usage examples see [its documentation](https://filesystem-spec.readthedocs.io/).
+
+S3
+^^
+
+MuData objects in the ``.h5mu`` format stored in an S3 bucket can be read with ``fsspec`` as well:
+::
+   storage_options = {
+      'endpoint_url': 'localhost:9000',
+      'key': 'AWS_ACCESS_KEY_ID',
+      'secret': 'AWS_SECRET_ACCESS_KEY',
+   }
+
+   with fsspec.open('s3://bucket/dataset.h5mu', **storage_options) as f:
+      mudata.read_h5mu(f)
+
+
+MuData objects stored in the ``.zarr`` format in an S3 bucket can be read from a *mapping*:
+::
+   import s3fs
+
+   s3 = s3fs.S3FileSystem(**storage_options)
+   store = s3.get_mapper('s3://bucket/dataset.zarr')
+   mdata = mudata.read_zarr(store)

src/mudata/_core/io.py

@@ -369,10 +369,13 @@ def _validate_h5mu(filename: PathLike) -> (str, Callable | None):
         # with fsspec.open("s3://bucket/file.h5mu") as f:
         #     mdata = read_h5mu(f)
         # or
-        # mdata = read_h5mu(fsspec.open("s3://bucket/file.h5mu")
+        # mdata = read_h5mu(fsspec.open("s3://bucket/file.h5mu"))
         if (
             filename.__class__.__name__ == "BufferedReader"
             or filename.__class__.__name__ == "OpenFile"
+            or filename.__class__.__name__ == "HTTPFile"
+            or filename.__class__.__name__ == "HTTPStreamFile"
+            or filename.__class__.__name__ == "S3File"
         ):
             try:
                 from fsspec.core import OpenFile

src/mudata/_core/mudata.py

@@ -544,7 +544,7 @@ def _update_attr(
         if OPTIONS["pull_on_update"] is None:
             warnings.warn(
                 "From 0.4 .update() will not pull obs/var columns from individual modalities by default anymore. "
-                "Set mudate.set_options(pull_on_update=False) to adopt the new behaviour, which will become the default. "
+                "Set mudata.set_options(pull_on_update=False) to adopt the new behaviour, which will become the default. "
                 "Use new pull_obs/pull_var and push_obs/push_var methods for more flexibility.",
                 FutureWarning,
                 stacklevel=2,