Cache netCDF attributes

lib/iris/fileformats/cf.py

@@ -63,16 +63,23 @@ class CFVariable(object):
     '''Name of the netCDF variable attribute that identifies this CF-netCDF variable'''
 
     def __init__(self, name, data):
-        if not isinstance(data, netCDF4.Variable):
-            raise TypeError('%s expects a netCDF4 Variable data instance' % self.__class__.__name__)
+        # Accessing the list of netCDF attributes is surprisingly slow.
+        # Since it's used repeatedly, caching the list makes things
+        # quite a bit faster.
+        self._nc_attrs = data.ncattrs()
+
         self.cf_name = name
         '''NetCDF variable name'''
+
         self.cf_data = data
         '''NetCDF4 Variable data instance'''
+
         self.cf_group = None
         '''Collection of CF-netCDF variables associated with this variable'''
+
         self.cf_terms_by_root = {}
         '''CF-netCDF formula terms that his variable participates in'''
+
         self.cf_attrs_reset()
 
     @staticmethod
@@ -125,9 +132,14 @@ def __ne__(self, other):
         return self.cf_name != other.cf_name
 
     def __getattr__(self, name):
-        if name in self.cf_data.ncattrs():
+        # Accessing netCDF attributes is surprisingly slow. Since
+        # they're often read repeatedly, caching the values makes things
+        # quite a bit faster.
+        if name in self._nc_attrs:
             self._cf_attrs.add(name)
-        return getattr(self.cf_data, name)
+        value = getattr(self.cf_data, name)
+        setattr(self, name, value)
+        return value
 
     def __getitem__(self, key):
         return self.cf_data.__getitem__(key)
@@ -140,19 +152,23 @@ def __repr__(self):
 
     def cf_attrs(self):
         """Return a list of all attribute name and value pairs of the CF-netCDF variable."""
-        return tuple([(attr, self.getncattr(attr)) for attr in sorted(self.ncattrs())])
+        return tuple((attr, self.getncattr(attr))
+                        for attr in sorted(self._nc_attrs))
 
     def cf_attrs_ignored(self):
         """Return a list of all ignored attribute name and value pairs of the CF-netCDF variable."""
-        return tuple([(attr, self.getncattr(attr)) for attr in sorted(set(self.ncattrs()) & _CF_ATTRS_IGNORE)])
+        return tuple((attr, self.getncattr(attr)) for attr in
+                        sorted(set(self._nc_attrs) & _CF_ATTRS_IGNORE))
 
     def cf_attrs_used(self):
         """Return a list of all accessed attribute name and value pairs of the CF-netCDF variable."""
-        return tuple([(attr, self.getncattr(attr)) for attr in sorted(self._cf_attrs)])
+        return tuple((attr, self.getncattr(attr)) for attr in
+                        sorted(self._cf_attrs))
 
     def cf_attrs_unused(self):
         """Return a list of all non-accessed attribute name and value pairs of the CF-netCDF variable."""
-        return tuple([(attr, self.getncattr(attr)) for attr in sorted(set(self.ncattrs()) - self._cf_attrs)])
+        return tuple((attr, self.getncattr(attr)) for attr in
+                        sorted(set(self._nc_attrs) - self._cf_attrs))
 
     def cf_attrs_reset(self):
         """Reset the history of accessed attribute names of the CF-netCDF variable."""

lib/iris/tests/test_cf.py

@@ -21,10 +21,45 @@
 # import iris tests first so that some things can be initialised before importing anything else
 import iris.tests as tests
 
+import unittest
+
+import mock
+
 import iris
 import iris.fileformats.cf as cf
 
 
+class TestCaching(unittest.TestCase):
+    def test_cached(self):
+        # Make sure attribute access to the underlying netCDF4.Variable
+        # is cached.
+        name = 'foo'
+        nc_var = mock.MagicMock()
+        cf_var = cf.CFAncillaryDataVariable(name, nc_var)
+        self.assertEqual(nc_var.ncattrs.call_count, 1)
+
+        # Accessing a netCDF attribute should result in no further calls
+        # to nc_var.ncattrs() and the creation of an attribute on the
+        # cf_var.
+        # NB. Can't use hasattr() because that triggers the attribute
+        # to be created!
+        self.assertTrue('coordinates' not in cf_var.__dict__)
+        _ = cf_var.coordinates
+        self.assertEqual(nc_var.ncattrs.call_count, 1)
+        self.assertTrue('coordinates' in cf_var.__dict__)
+
+        # Trying again results in no change.
+        _ = cf_var.coordinates
+        self.assertEqual(nc_var.ncattrs.call_count, 1)
+        self.assertTrue('coordinates' in cf_var.__dict__)
+
+        # Trying another attribute results in just a new attribute.
+        self.assertTrue('standard_name' not in cf_var.__dict__)
+        _ = cf_var.standard_name
+        self.assertEqual(nc_var.ncattrs.call_count, 1)
+        self.assertTrue('standard_name' in cf_var.__dict__)
+
+
 @iris.tests.skip_data
 class TestCFReader(tests.IrisTest):
     def setUp(self):