Merge pull request Unidata#1384 from RandallPittmanOrSt/disable_dataset_iteration

Disable Dataset iteration and membership operations (raise error on __iter__ and __contains__)

Author: jswhit

src/netCDF4/__init__.pyi

@@ -384,6 +384,9 @@ class Dataset:
     def has_bzip2_filter(self) -> bool: ...
     def has_szip_filter(self) -> bool: ...
     def __getitem__(self, elem: str) -> Any: ...  # should be Group | Variable, but this causes too many problems
+    # __iter__ and __contains__ always error because iteration and membership ops are not allowed
+    def __iter__(self) -> NoReturn: ...
+    def __contains__(self, key) -> NoReturn: ...
     def __setattr__(self, name: str, value: Any) -> None: ...
     def __getattr__(self, name: str) -> Any: ...
     def __delattr__(self, name: str): ...

src/netCDF4/_netCDF4.pyx

@@ -2569,6 +2569,17 @@ strings.
         else:
             raise IndexError('%s not found in %s' % (lastname,group.path))
 
+    def __iter__(self):
+        raise TypeError(
+            "Dataset is not iterable. Consider iterating on Dataset.variables."
+        )
+
+    def __contains__(self, key):
+        raise TypeError(
+            "Dataset does not support membership operations. Perhaps try 'varname in"
+            " dataset.variables' or 'dimname in dataset.dimensions'."
+        )
+
     def filepath(self,encoding=None):
         """**`filepath(self,encoding=None)`**
 
@@ -4041,7 +4052,7 @@ behavior is similar to Fortran or Matlab, but different than numpy.
         If fill_value is set to `False`, then the variable is not pre-filled.
         The default netCDF fill values can be found in the dictionary `netCDF4.default_fillvals`.
         If not set, the default fill value will be used but no `_FillValue` attribute will be created
-        (this is the default behavior of the netcdf-c library). If you want to use the 
+        (this is the default behavior of the netcdf-c library). If you want to use the
         default fill value, but have the `_FillValue` attribute set, use
         `fill_value='default'` (note - this only works for primitive data types). `Variable.get_fill_value`
         can be used to retrieve the fill value, even if the `_FillValue` attribute is not set.

test/test_no_iter_contains.py

@@ -0,0 +1,34 @@
+import os
+import tempfile
+import unittest
+
+import netCDF4
+
+FILE_NAME = tempfile.NamedTemporaryFile(suffix='.nc', delete=False).name
+
+
+class TestNoIterNoContains(unittest.TestCase):
+    def setUp(self) -> None:
+        self.file = FILE_NAME
+        with netCDF4.Dataset(self.file, "w") as dataset:
+            # just create a simple variable
+            dataset.createVariable("var1", int)
+
+    def tearDown(self) -> None:
+        os.remove(self.file)
+
+    def test_no_iter(self) -> None:
+        """Verify that iteration is explicitly not supported"""
+        with netCDF4.Dataset(self.file, "r") as dataset:
+            with self.assertRaises(TypeError):
+                for _ in dataset:  # type: ignore  # type checker catches that this doesn't work
+                    pass
+
+    def test_no_contains(self) -> None:
+        """Verify the membership operations are explicity not supported"""
+        with netCDF4.Dataset(self.file, "r") as dataset:
+            with self.assertRaises(TypeError):
+                _ = "var1" in dataset
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)