Remove invalid dict entries from hashes.pkl

If the data in a hashes.pkl is corrupted but still de-serialized without
errors, it will mess up the replication and gets never fixed. This
happens for example if one of the keys is a NULL byte.

This patch checks if the dict keys in hashes.pkl are valid strings and
invalidates it if not.

Closes-Bug: 1830881
Change-Id: I84b062d062ff49935feed0aee3e1963bb72eb5ea
(cherry picked from commit c9e78d15e1)

swift/obj/diskfile.py

@@ -354,6 +354,12 @@ def read_hashes(partition_dir):
             # given invalid input depending on the way in which the
             # input is invalid.
             pass
+
+    # Check for corrupted data that could break os.listdir()
+    for suffix in hashes.keys():
+        if not suffix.isalnum():
+            return {'valid': False}
+
     # hashes.pkl w/o valid updated key is "valid" but "forever old"
     hashes.setdefault('valid', True)
     hashes.setdefault('updated', -1)

test/unit/obj/test_diskfile.py

@@ -8337,6 +8337,11 @@ class TestHashesHelpers(unittest.TestCase):
         # with the exactly the same value mutation from write_hashes
         self.assertEqual(hashes, result)
 
+    def test_ignore_corrupted_hashes(self):
+        corrupted_hashes = {u'\x00\x00\x00': False, 'valid': True}
+        diskfile.write_hashes(self.testdir, corrupted_hashes)
+        result = diskfile.read_hashes(self.testdir)
+        self.assertFalse(result['valid'])
 
 if __name__ == '__main__':
     unittest.main()