BUG: io.netcdf: do not close mmap if there are references left to it

Fixes scipygh-3630

scipy/io/netcdf.py

@@ -32,6 +32,8 @@
 __all__ = ['netcdf_file']
 
 
+import warnings
+import weakref
 from operator import mul
 import mmap as mm
 
@@ -243,9 +245,23 @@ def close(self):
             try:
                 self.flush()
             finally:
-                self._mm_buf = None
-                if self._mm is not None:
-                    self._mm.close()
+                self.variables = {}
+                if self._mm_buf is not None:
+                    ref = weakref.ref(self._mm_buf)
+                    self._mm_buf = None
+                    if ref() is None:
+                        # self._mm_buf is gc'd, and we can close the mmap
+                        self._mm.close()
+                    else:
+                        # we cannot close self._mm, since self._mm_buf is
+                        # alive and there may still be arrays referring to it
+                        warnings.warn((
+                            "Cannot close a netcdf_file opened with mmap=True, when "
+                            "netcdf_variables or arrays referring to its data still exist. "
+                            "All data arrays obtained from such files refer directly to "
+                            "data on disk, and must be copied before the file can be cleanly "
+                            "closed. (See netcdf_file docstring for more information on mmap.)"
+                        ), category=RuntimeWarning)
                 self._mm = None
                 self.fp.close()
     __del__ = close

scipy/io/tests/test_netcdf.py

@@ -5,12 +5,13 @@
 from os.path import join as pjoin, dirname
 import shutil
 import tempfile
+import warnings
 from io import BytesIO
 from glob import glob
 from contextlib import contextmanager
 
 import numpy as np
-from numpy.testing import assert_, assert_allclose
+from numpy.testing import assert_, assert_allclose, assert_warns
 
 from scipy.io.netcdf import netcdf_file
 
@@ -232,10 +233,34 @@ def test_mmaps_closed():
     vars = []
     for i in range(1100):
         f = netcdf_file(filename, mmap=True)
-        vars.append(f.variables['lat'])
+        vars.append(f.variables['lat'][:].copy())
         f.close()
 
 
+def test_mmaps_segfault():
+    filename = pjoin(TEST_DATA_PATH, 'example_1.nc')
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
+        with netcdf_file(filename, mmap=True) as f:
+            x = f.variables['lat'][:]
+            # should not raise warnings
+            del x
+
+    def doit():
+        with netcdf_file(filename, mmap=True) as f:
+            return f.variables['lat'][:]
+
+    # should raise a warning
+    assert_warns(RuntimeWarning, doit)
+
+    # should not crash
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+        x = doit()
+        x.sum()
+
+
 def test_zero_dimensional_var():
     io = BytesIO()
     with make_simple(io, 'w') as f: