WIP: backend interface, now it uses subclassing (#4836)

* draft

* working version

* fix: instantiate BackendEtrypoints

* rename AbstractBackendEntrypoint in BackendEntrypoint

* fix plugins tests

* style

* style

* raise NotImplemetedError if BackendEntrypoint.open_dataset is not implemented

Author: aurghs

xarray/backends/cfgrib_.py

@@ -12,7 +12,7 @@
     BackendEntrypoint,
 )
 from .locks import SerializableLock, ensure_lock
-from .store import open_backend_dataset_store
+from .store import StoreBackendEntrypoint
 
 try:
     import cfgrib
@@ -86,62 +86,58 @@ def get_encoding(self):
         return encoding
 
 
-def guess_can_open_cfgrib(store_spec):
-    try:
-        _, ext = os.path.splitext(store_spec)
-    except TypeError:
-        return False
-    return ext in {".grib", ".grib2", ".grb", ".grb2"}
-
-
-def open_backend_dataset_cfgrib(
-    filename_or_obj,
-    *,
-    mask_and_scale=True,
-    decode_times=None,
-    concat_characters=None,
-    decode_coords=None,
-    drop_variables=None,
-    use_cftime=None,
-    decode_timedelta=None,
-    lock=None,
-    indexpath="{path}.{short_hash}.idx",
-    filter_by_keys={},
-    read_keys=[],
-    encode_cf=("parameter", "time", "geography", "vertical"),
-    squeeze=True,
-    time_dims=("time", "step"),
-):
-
-    store = CfGribDataStore(
+class CfgribfBackendEntrypoint(BackendEntrypoint):
+    def guess_can_open(self, store_spec):
+        try:
+            _, ext = os.path.splitext(store_spec)
+        except TypeError:
+            return False
+        return ext in {".grib", ".grib2", ".grb", ".grb2"}
+
+    def open_dataset(
+        self,
         filename_or_obj,
-        indexpath=indexpath,
-        filter_by_keys=filter_by_keys,
-        read_keys=read_keys,
-        encode_cf=encode_cf,
-        squeeze=squeeze,
-        time_dims=time_dims,
-        lock=lock,
-    )
-
-    with close_on_error(store):
-        ds = open_backend_dataset_store(
-            store,
-            mask_and_scale=mask_and_scale,
-            decode_times=decode_times,
-            concat_characters=concat_characters,
-            decode_coords=decode_coords,
-            drop_variables=drop_variables,
-            use_cftime=use_cftime,
-            decode_timedelta=decode_timedelta,
+        *,
+        mask_and_scale=True,
+        decode_times=None,
+        concat_characters=None,
+        decode_coords=None,
+        drop_variables=None,
+        use_cftime=None,
+        decode_timedelta=None,
+        lock=None,
+        indexpath="{path}.{short_hash}.idx",
+        filter_by_keys={},
+        read_keys=[],
+        encode_cf=("parameter", "time", "geography", "vertical"),
+        squeeze=True,
+        time_dims=("time", "step"),
+    ):
+
+        store = CfGribDataStore(
+            filename_or_obj,
+            indexpath=indexpath,
+            filter_by_keys=filter_by_keys,
+            read_keys=read_keys,
+            encode_cf=encode_cf,
+            squeeze=squeeze,
+            time_dims=time_dims,
+            lock=lock,
         )
-    return ds
-
-
-cfgrib_backend = BackendEntrypoint(
-    open_dataset=open_backend_dataset_cfgrib, guess_can_open=guess_can_open_cfgrib
-)
+        store_entrypoint = StoreBackendEntrypoint()
+        with close_on_error(store):
+            ds = store_entrypoint.open_dataset(
+                store,
+                mask_and_scale=mask_and_scale,
+                decode_times=decode_times,
+                concat_characters=concat_characters,
+                decode_coords=decode_coords,
+                drop_variables=drop_variables,
+                use_cftime=use_cftime,
+                decode_timedelta=decode_timedelta,
+            )
+        return ds
 
 
 if has_cfgrib:
-    BACKEND_ENTRYPOINTS["cfgrib"] = cfgrib_backend
+    BACKEND_ENTRYPOINTS["cfgrib"] = CfgribfBackendEntrypoint

xarray/backends/common.py

@@ -1,7 +1,7 @@
 import logging
 import time
 import traceback
-from typing import Dict
+from typing import Dict, Tuple, Type, Union
 
 import numpy as np
 
@@ -344,12 +344,13 @@ def encode(self, variables, attributes):
 
 
 class BackendEntrypoint:
-    __slots__ = ("guess_can_open", "open_dataset", "open_dataset_parameters")
+    open_dataset_parameters: Union[Tuple, None] = None
 
-    def __init__(self, open_dataset, open_dataset_parameters=None, guess_can_open=None):
-        self.open_dataset = open_dataset
-        self.open_dataset_parameters = open_dataset_parameters
-        self.guess_can_open = guess_can_open
+    def open_dataset(self):
+        raise NotImplementedError
 
+    def guess_can_open(self, store_spec):
+        return False
 
-BACKEND_ENTRYPOINTS: Dict[str, BackendEntrypoint] = {}
+
+BACKEND_ENTRYPOINTS: Dict[str, Type[BackendEntrypoint]] = {}

xarray/backends/h5netcdf_.py

@@ -23,7 +23,7 @@
     _get_datatype,
     _nc4_require_group,
 )
-from .store import open_backend_dataset_store
+from .store import StoreBackendEntrypoint
 
 try:
     import h5netcdf
@@ -328,62 +328,61 @@ def close(self, **kwargs):
         self._manager.close(**kwargs)
 
 
-def guess_can_open_h5netcdf(store_spec):
-    try:
-        return read_magic_number(store_spec).startswith(b"\211HDF\r\n\032\n")
-    except TypeError:
-        pass
-
-    try:
-        _, ext = os.path.splitext(store_spec)
-    except TypeError:
-        return False
-
-    return ext in {".nc", ".nc4", ".cdf"}
-
-
-def open_backend_dataset_h5netcdf(
-    filename_or_obj,
-    *,
-    mask_and_scale=True,
-    decode_times=None,
-    concat_characters=None,
-    decode_coords=None,
-    drop_variables=None,
-    use_cftime=None,
-    decode_timedelta=None,
-    format=None,
-    group=None,
-    lock=None,
-    invalid_netcdf=None,
-    phony_dims=None,
-):
-
-    store = H5NetCDFStore.open(
+class H5netcdfBackendEntrypoint(BackendEntrypoint):
+    def guess_can_open(self, store_spec):
+        try:
+            return read_magic_number(store_spec).startswith(b"\211HDF\r\n\032\n")
+        except TypeError:
+            pass
+
+        try:
+            _, ext = os.path.splitext(store_spec)
+        except TypeError:
+            return False
+
+        return ext in {".nc", ".nc4", ".cdf"}
+
+    def open_dataset(
+        self,
         filename_or_obj,
-        format=format,
-        group=group,
-        lock=lock,
-        invalid_netcdf=invalid_netcdf,
-        phony_dims=phony_dims,
-    )
+        *,
+        mask_and_scale=True,
+        decode_times=None,
+        concat_characters=None,
+        decode_coords=None,
+        drop_variables=None,
+        use_cftime=None,
+        decode_timedelta=None,
+        format=None,
+        group=None,
+        lock=None,
+        invalid_netcdf=None,
+        phony_dims=None,
+    ):
 
-    ds = open_backend_dataset_store(
-        store,
-        mask_and_scale=mask_and_scale,
-        decode_times=decode_times,
-        concat_characters=concat_characters,
-        decode_coords=decode_coords,
-        drop_variables=drop_variables,
-        use_cftime=use_cftime,
-        decode_timedelta=decode_timedelta,
-    )
-    return ds
+        store = H5NetCDFStore.open(
+            filename_or_obj,
+            format=format,
+            group=group,
+            lock=lock,
+            invalid_netcdf=invalid_netcdf,
+            phony_dims=phony_dims,
+        )
 
+        store_entrypoint = StoreBackendEntrypoint()
+
+        ds = store_entrypoint.open_dataset(
+            store,
+            mask_and_scale=mask_and_scale,
+            decode_times=decode_times,
+            concat_characters=concat_characters,
+            decode_coords=decode_coords,
+            drop_variables=drop_variables,
+            use_cftime=use_cftime,
+            decode_timedelta=decode_timedelta,
+        )
+        return ds
 
-h5netcdf_backend = BackendEntrypoint(
-    open_dataset=open_backend_dataset_h5netcdf, guess_can_open=guess_can_open_h5netcdf
-)
 
 if has_h5netcdf:
-    BACKEND_ENTRYPOINTS["h5netcdf"] = h5netcdf_backend
+    BACKEND_ENTRYPOINTS["h5netcdf"] = H5netcdfBackendEntrypoint