Add variable/attribute names to netCDF validation errors (#4500)

* Add variable/attribute names to netCDF validation errors

This should result in a better user experience, e.g., specifically
pointing out the attribute with an invalid value.

* fix lint

Author: shoyer

xarray/backends/api.py

@@ -191,14 +191,15 @@ def check_name(name):
         if isinstance(name, str):
             if not name:
                 raise ValueError(
-                    "Invalid name for DataArray or Dataset key: "
+                    f"Invalid name {name!r} for DataArray or Dataset key: "
                     "string must be length 1 or greater for "
                     "serialization to netCDF files"
                 )
         elif name is not None:
             raise TypeError(
-                "DataArray.name or Dataset key must be either a "
-                "string or None for serialization to netCDF files"
+                f"Invalid name {name!r} for DataArray or Dataset key: "
+                "must be either a string or None for serialization to netCDF "
+                "files"
             )
 
     for k in dataset.variables:
@@ -214,22 +215,22 @@ def check_attr(name, value):
         if isinstance(name, str):
             if not name:
                 raise ValueError(
-                    "Invalid name for attr: string must be "
+                    f"Invalid name for attr {name!r}: string must be "
                     "length 1 or greater for serialization to "
                     "netCDF files"
                 )
         else:
             raise TypeError(
-                "Invalid name for attr: {} must be a string for "
-                "serialization to netCDF files".format(name)
+                f"Invalid name for attr: {name!r} must be a string for "
+                "serialization to netCDF files"
             )
 
         if not isinstance(value, (str, Number, np.ndarray, np.number, list, tuple)):
             raise TypeError(
-                "Invalid value for attr: {} must be a number, "
+                f"Invalid value for attr {name!r}: {value!r} must be a number, "
                 "a string, an ndarray or a list/tuple of "
                 "numbers/strings for serialization to netCDF "
-                "files".format(value)
+                "files"
             )
 
     # Check attrs on the dataset itself

xarray/tests/test_backends.py

@@ -907,11 +907,13 @@ def test_invalid_dataarray_names_raise(self):
         ve = (ValueError, "string must be length 1 or")
         data = np.random.random((2, 2))
         da = xr.DataArray(data)
-        for name, e in zip([0, (4, 5), True, ""], [te, te, te, ve]):
+        for name, (error, msg) in zip([0, (4, 5), True, ""], [te, te, te, ve]):
             ds = Dataset({name: da})
-            with raises_regex(*e):
+            with pytest.raises(error) as excinfo:
                 with self.roundtrip(ds):
                     pass
+            excinfo.match(msg)
+            excinfo.match(repr(name))
 
     def test_encoding_kwarg(self):
         ds = Dataset({"x": ("y", np.arange(10.0))})
@@ -4307,17 +4309,17 @@ def new_dataset_and_coord_attrs():
             ds, attrs = new_dataset_and_attrs()
 
             attrs[123] = "test"
-            with raises_regex(TypeError, "Invalid name for attr"):
+            with raises_regex(TypeError, "Invalid name for attr: 123"):
                 ds.to_netcdf("test.nc")
 
             ds, attrs = new_dataset_and_attrs()
             attrs[MiscObject()] = "test"
-            with raises_regex(TypeError, "Invalid name for attr"):
+            with raises_regex(TypeError, "Invalid name for attr: "):
                 ds.to_netcdf("test.nc")
 
             ds, attrs = new_dataset_and_attrs()
             attrs[""] = "test"
-            with raises_regex(ValueError, "Invalid name for attr"):
+            with raises_regex(ValueError, "Invalid name for attr '':"):
                 ds.to_netcdf("test.nc")
 
             # This one should work
@@ -4328,12 +4330,12 @@ def new_dataset_and_coord_attrs():
 
             ds, attrs = new_dataset_and_attrs()
             attrs["test"] = {"a": 5}
-            with raises_regex(TypeError, "Invalid value for attr"):
+            with raises_regex(TypeError, "Invalid value for attr 'test'"):
                 ds.to_netcdf("test.nc")
 
             ds, attrs = new_dataset_and_attrs()
             attrs["test"] = MiscObject()
-            with raises_regex(TypeError, "Invalid value for attr"):
+            with raises_regex(TypeError, "Invalid value for attr 'test'"):
                 ds.to_netcdf("test.nc")
 
             ds, attrs = new_dataset_and_attrs()