Add mode='a-': Do not overwrite coordinates when appending to Zarr with append_dim

xarray/backends/api.py

@@ -38,6 +38,7 @@
 from xarray.core.dataset import Dataset, _get_chunk, _maybe_chunk
 from xarray.core.indexes import Index
 from xarray.core.parallelcompat import guess_chunkmanager
+from xarray.core.types import ZarrWriteModes
 from xarray.core.utils import is_remote_uri
 
 if TYPE_CHECKING:
@@ -68,7 +69,6 @@
         "NETCDF4", "NETCDF4_CLASSIC", "NETCDF3_64BIT", "NETCDF3_CLASSIC"
     ]
 
-
 DATAARRAY_NAME = "__xarray_dataarray_name__"
 DATAARRAY_VARIABLE = "__xarray_dataarray_variable__"
 
@@ -1524,7 +1524,7 @@ def to_zarr(
     dataset: Dataset,
     store: MutableMapping | str | os.PathLike[str] | None = None,
     chunk_store: MutableMapping | str | os.PathLike | None = None,
-    mode: Literal["w", "w-", "a", "r+", None] = None,
+    mode: ZarrWriteModes | None = None,
     synchronizer=None,
     group: str | None = None,
     encoding: Mapping | None = None,
@@ -1548,7 +1548,7 @@ def to_zarr(
     dataset: Dataset,
     store: MutableMapping | str | os.PathLike[str] | None = None,
     chunk_store: MutableMapping | str | os.PathLike | None = None,
-    mode: Literal["w", "w-", "a", "r+", None] = None,
+    mode: ZarrWriteModes | None = None,
     synchronizer=None,
     group: str | None = None,
     encoding: Mapping | None = None,
@@ -1570,7 +1570,7 @@ def to_zarr(
     dataset: Dataset,
     store: MutableMapping | str | os.PathLike[str] | None = None,
     chunk_store: MutableMapping | str | os.PathLike | None = None,
-    mode: Literal["w", "w-", "a", "r+", None] = None,
+    mode: ZarrWriteModes | None = None,
     synchronizer=None,
     group: str | None = None,
     encoding: Mapping | None = None,
@@ -1627,16 +1627,18 @@ def to_zarr(
         else:
             mode = "w-"
 
-    if mode != "a" and append_dim is not None:
+    if mode not in ["a", "a-"] and append_dim is not None:
         raise ValueError("cannot set append_dim unless mode='a' or mode=None")
 
-    if mode not in ["a", "r+"] and region is not None:
-        raise ValueError("cannot set region unless mode='a', mode='r+' or mode=None")
+    if mode not in ["a", "a-", "r+"] and region is not None:
+        raise ValueError(
+            "cannot set region unless mode='a', mode='a-', mode='r+' or mode=None"
+        )
 
-    if mode not in ["w", "w-", "a", "r+"]:
+    if mode not in ["w", "w-", "a", "a-", "r+"]:
         raise ValueError(
             "The only supported options for mode are 'w', "
-            f"'w-', 'a' and 'r+', but mode={mode!r}"
+            f"'w-', 'a', 'a-', and 'r+', but mode={mode!r}"
         )
 
     # validate Dataset keys, DataArray names
@@ -1679,7 +1681,7 @@ def to_zarr(
         write_empty=write_empty_chunks,
     )
 
-    if mode in ["a", "r+"]:
+    if mode in ["a", "a-", "r+"]:
         _validate_datatypes_for_zarr_append(zstore, dataset)
         if append_dim is not None:
             existing_dims = zstore.get_dimensions()

xarray/backends/zarr.py

@@ -21,6 +21,7 @@
 from xarray.core import indexing
 from xarray.core.parallelcompat import guess_chunkmanager
 from xarray.core.pycompat import integer_types
+from xarray.core.types import ZarrWriteModes
 from xarray.core.utils import (
     FrozenDict,
     HiddenKeyDict,
@@ -377,7 +378,7 @@ class ZarrStore(AbstractWritableDataStore):
     def open_group(
         cls,
         store,
-        mode="r",
+        mode: ZarrWriteModes = "r",
         synchronizer=None,
         group=None,
         consolidated=False,
@@ -402,7 +403,8 @@ def open_group(
             zarr_version = getattr(store, "_store_version", 2)
 
         open_kwargs = dict(
-            mode=mode,
+            # mode='a-' is a handcrafted xarray specialty
+            mode="a" if mode == "a-" else mode,
             synchronizer=synchronizer,
             path=group,
         )
@@ -628,8 +630,21 @@ def store(
             self.set_attributes(attributes)
             self.set_dimensions(variables_encoded, unlimited_dims=unlimited_dims)
 
+        # if we are appending to an append_dim, only write either
+        # - new variables not already present, OR
+        # - variables with the append_dim in their dimensions
+        # We do NOT overwrite other variables.
+        if self._mode == "a-" and self._append_dim is not None:
+            variables_to_set = {
+                k: v
+                for k, v in variables_encoded.items()
+                if (k not in existing_variable_names) or (self._append_dim in v.dims)
+            }
+        else:
+            variables_to_set = variables_encoded
+
         self.set_variables(
-            variables_encoded, check_encoding_set, writer, unlimited_dims=unlimited_dims
+            variables_to_set, check_encoding_set, writer, unlimited_dims=unlimited_dims
         )
         if self._consolidate_on_close:
             zarr.consolidate_metadata(self.zarr_group.store)

xarray/core/dataarray.py

@@ -49,7 +49,12 @@
 from xarray.core.indexing import is_fancy_indexer, map_index_queries
 from xarray.core.merge import PANDAS_TYPES, MergeError
 from xarray.core.options import OPTIONS, _get_keep_attrs
-from xarray.core.types import DaCompatible, T_DataArray, T_DataArrayOrSet
+from xarray.core.types import (
+    DaCompatible,
+    T_DataArray,
+    T_DataArrayOrSet,
+    ZarrWriteModes,
+)
 from xarray.core.utils import (
     Default,
     HybridMappingProxy,
@@ -4064,7 +4069,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         *,
@@ -4085,7 +4090,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         encoding: Mapping | None = None,
@@ -4104,7 +4109,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         encoding: Mapping | None = None,
@@ -4140,10 +4145,11 @@ def to_zarr(
         chunk_store : MutableMapping, str or path-like, optional
             Store or path to directory in local or remote file system only for Zarr
             array chunks. Requires zarr-python v2.4.0 or later.
-        mode : {"w", "w-", "a", "r+", None}, optional
+        mode : {"w", "w-", "a", "a-", r+", None}, optional
             Persistence mode: "w" means create (overwrite if exists);
             "w-" means create (fail if exists);
-            "a" means override existing variables (create if does not exist);
+            "a" means override all existing variables including dimension coordinates (create if does not exist);
+            "a-" means only append those variables that have ``append_dim``.
             "r+" means modify existing array *values* only (raise an error if
             any metadata or shapes would change).
             The default mode is "a" if ``append_dim`` is set. Otherwise, it is

xarray/core/dataset.py

@@ -100,6 +100,7 @@
     T_Chunks,
     T_DataArrayOrSet,
     T_Dataset,
+    ZarrWriteModes,
 )
 from xarray.core.utils import (
     Default,
@@ -2297,7 +2298,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         encoding: Mapping | None = None,
@@ -2320,7 +2321,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         encoding: Mapping | None = None,
@@ -2341,7 +2342,7 @@ def to_zarr(
         self,
         store: MutableMapping | str | PathLike[str] | None = None,
         chunk_store: MutableMapping | str | PathLike | None = None,
-        mode: Literal["w", "w-", "a", "r+", None] = None,
+        mode: ZarrWriteModes | None = None,
         synchronizer=None,
         group: str | None = None,
         encoding: Mapping | None = None,
@@ -2379,10 +2380,11 @@ def to_zarr(
         chunk_store : MutableMapping, str or path-like, optional
             Store or path to directory in local or remote file system only for Zarr
             array chunks. Requires zarr-python v2.4.0 or later.
-        mode : {"w", "w-", "a", "r+", None}, optional
+        mode : {"w", "w-", "a", "a-", r+", None}, optional
             Persistence mode: "w" means create (overwrite if exists);
             "w-" means create (fail if exists);
-            "a" means override existing variables (create if does not exist);
+            "a" means override all existing variables including dimension coordinates (create if does not exist);
+            "a-" means only append those variables that have ``append_dim``.
             "r+" means modify existing array *values* only (raise an error if
             any metadata or shapes would change).
             The default mode is "a" if ``append_dim`` is set. Otherwise, it is

xarray/core/types.py

@@ -282,3 +282,6 @@ def copy(
     "midpoint",
     "nearest",
 ]
+
+
+ZarrWriteModes = Literal["w", "w-", "a", "a-", "r+", "r"]

xarray/tests/test_backends.py

@@ -2382,6 +2382,29 @@ def test_append_with_new_variable(self) -> None:
                 xr.open_dataset(store_target, engine="zarr", **self.version_kwargs),
             )
 
+    def test_append_with_append_dim_no_overwrite(self) -> None:
+        ds, ds_to_append, _ = create_append_test_data()
+        with self.create_zarr_target() as store_target:
+            ds.to_zarr(store_target, mode="w", **self.version_kwargs)
+            original = xr.concat([ds, ds_to_append], dim="time")
+            original2 = xr.concat([original, ds_to_append], dim="time")
+
+            # overwrite a coordinate;
+            # for mode='a-', this will not get written to the store
+            # because it does not have the append_dim as a dim
+            ds_to_append.lon.data[:] = -999
+            ds_to_append.to_zarr(
+                store_target, mode="a-", append_dim="time", **self.version_kwargs
+            )
+            actual = xr.open_dataset(store_target, engine="zarr", **self.version_kwargs)
+            assert_identical(original, actual)
+
+            # by default, mode="a" will overwrite all coordinates.
+            ds_to_append.to_zarr(store_target, append_dim="time", **self.version_kwargs)
+            actual = xr.open_dataset(store_target, engine="zarr", **self.version_kwargs)
+            original2.lon.data[:] = -999
+            assert_identical(original2, actual)
+
     @requires_dask
     def test_to_zarr_compute_false_roundtrip(self) -> None:
         from dask.delayed import Delayed
@@ -2578,7 +2601,7 @@ def setup_and_verify_store(expected=data):
             with pytest.raises(
                 ValueError,
                 match=re.escape(
-                    "cannot set region unless mode='a', mode='r+' or mode=None"
+                    "cannot set region unless mode='a', mode='a-', mode='r+' or mode=None"
                 ),
             ):
                 data.to_zarr(