Refactor apiv2.open_dataset (#4642)

* in apiv2: rename ds in backend_ds and ds2 in ds

* add function _chunks_ds to simplify dataset_from_backend_dataset

* add small function _get_mtime to simplify _chunks_ds

* make resolve_decoders_kwargs and dataset_from_backend_dataset private

Author: aurghs

xarray/backends/apiv2.py

@@ -11,37 +11,33 @@
 )
 
 
-def dataset_from_backend_dataset(
-    ds,
+def _get_mtime(filename_or_obj):
+    # if passed an actual file path, augment the token with
+    # the file modification time
+    if isinstance(filename_or_obj, str) and not is_remote_uri(filename_or_obj):
+        mtime = os.path.getmtime(filename_or_obj)
+    else:
+        mtime = None
+    return mtime
+
+
+def _chunk_ds(
+    backend_ds,
     filename_or_obj,
     engine,
     chunks,
-    cache,
     overwrite_encoded_chunks,
     **extra_tokens,
 ):
-    if not (isinstance(chunks, (int, dict)) or chunks is None):
-        if chunks != "auto":
-            raise ValueError(
-                "chunks must be an int, dict, 'auto', or None. "
-                "Instead found %s. " % chunks
-            )
-
-    _protect_dataset_variables_inplace(ds, cache)
-    if chunks is not None and engine != "zarr":
+    if engine != "zarr":
         from dask.base import tokenize
 
-        # if passed an actual file path, augment the token with
-        # the file modification time
-        if isinstance(filename_or_obj, str) and not is_remote_uri(filename_or_obj):
-            mtime = os.path.getmtime(filename_or_obj)
-        else:
-            mtime = None
+        mtime = _get_mtime(filename_or_obj)
         token = tokenize(filename_or_obj, mtime, engine, chunks, **extra_tokens)
         name_prefix = "open_dataset-%s" % token
-        ds2 = ds.chunk(chunks, name_prefix=name_prefix, token=token)
+        ds = backend_ds.chunk(chunks, name_prefix=name_prefix, token=token)
 
-    elif engine == "zarr":
+    else:
 
         if chunks == "auto":
             try:
@@ -50,35 +46,64 @@ def dataset_from_backend_dataset(
                 chunks = None
 
         if chunks is None:
-            return ds
+            return backend_ds
 
         if isinstance(chunks, int):
-            chunks = dict.fromkeys(ds.dims, chunks)
+            chunks = dict.fromkeys(backend_ds.dims, chunks)
 
         variables = {}
-        for k, v in ds.variables.items():
+        for k, v in backend_ds.variables.items():
             var_chunks = _get_chunk(k, v, chunks)
             variables[k] = _maybe_chunk(
                 k,
                 v,
                 var_chunks,
                 overwrite_encoded_chunks=overwrite_encoded_chunks,
             )
-        ds2 = ds._replace(variables)
+        ds = backend_ds._replace(variables)
+    return ds
+
+
+def _dataset_from_backend_dataset(
+    backend_ds,
+    filename_or_obj,
+    engine,
+    chunks,
+    cache,
+    overwrite_encoded_chunks,
+    **extra_tokens,
+):
+    if not (isinstance(chunks, (int, dict)) or chunks is None):
+        if chunks != "auto":
+            raise ValueError(
+                "chunks must be an int, dict, 'auto', or None. "
+                "Instead found %s. " % chunks
+            )
 
+    _protect_dataset_variables_inplace(backend_ds, cache)
+    if chunks is None:
+        ds = backend_ds
     else:
-        ds2 = ds
-    ds2._file_obj = ds._file_obj
+        ds = _chunk_ds(
+            backend_ds,
+            filename_or_obj,
+            engine,
+            chunks,
+            overwrite_encoded_chunks,
+            **extra_tokens,
+        )
+
+    ds._file_obj = backend_ds._file_obj
 
     # Ensure source filename always stored in dataset object (GH issue #2550)
     if "source" not in ds.encoding:
         if isinstance(filename_or_obj, str):
-            ds2.encoding["source"] = filename_or_obj
+            ds.encoding["source"] = filename_or_obj
 
-    return ds2
+    return ds
 
 
-def resolve_decoders_kwargs(decode_cf, engine, **decoders):
+def _resolve_decoders_kwargs(decode_cf, engine, **decoders):
     signature = plugins.ENGINES[engine]["signature"]
     if decode_cf is False:
         for d in decoders:
@@ -225,7 +250,7 @@ def open_dataset(
     if engine is None:
         engine = _autodetect_engine(filename_or_obj)
 
-    decoders = resolve_decoders_kwargs(
+    decoders = _resolve_decoders_kwargs(
         decode_cf,
         engine=engine,
         mask_and_scale=mask_and_scale,
@@ -249,7 +274,7 @@ def open_dataset(
         **backend_kwargs,
         **{k: v for k, v in kwargs.items() if v is not None},
     )
-    ds = dataset_from_backend_dataset(
+    ds = _dataset_from_backend_dataset(
         backend_ds,
         filename_or_obj,
         engine,