454 Multiple pickle support (#460)

* allow for roundtrips of cloudpaths through pickle serialization (#454)

This avoids an exception thrown because the _client is not serialized
into the pickled object, and thus when __getstate__ is called the second
time, there is no _client field to delete.

Closes #450

* pickle tests

---------

Co-authored-by: Aaron Taylor <[email protected]>

HISTORY.md

@@ -2,6 +2,7 @@
 
 ## UNRELEASED
 
+- Allow `CloudPath` objects to be loaded/dumped through pickle format repeatedly. (Issue [#450](https://github.com/drivendataorg/cloudpathlib/issues/450))
 - Fixes typo in `FileCacheMode` where values were being filled by envvar `CLOUPATHLIB_FILE_CACHE_MODE` instead of `CLOUDPATHLIB_FILE_CACHE_MODE`. (PR [#424](https://github.com/drivendataorg/cloudpathlib/pull/424)
 - Fix `CloudPath` cleanup via `CloudPath.__del__` when `Client` encounters an exception during initialization and does not create a `file_cache_mode` attribute. (Issue [#372](https://github.com/drivendataorg/cloudpathlib/issues/372), thanks to [@bryanwweber](https://github.com/bryanwweber)) 
 - Drop support for Python 3.7; pin minimal `boto3` version to Python 3.8+ versions. (PR [#407](https://github.com/drivendataorg/cloudpathlib/pull/407))

cloudpathlib/cloudpath.py

@@ -263,7 +263,8 @@ def __getstate__(self) -> Dict[str, Any]:
         state = self.__dict__.copy()
 
         # don't pickle client
-        del state["_client"]
+        if "_client" in state:
+            del state["_client"]
 
         return state
 

tests/test_cloudpath_file_io.py

@@ -1,7 +1,6 @@
 from datetime import datetime
 import os
 from pathlib import Path, PurePosixPath
-import pickle
 from shutil import rmtree
 import sys
 from time import sleep
@@ -454,24 +453,6 @@ def test_os_open(rig):
         assert f.readable()
 
 
-def test_pickle(rig, tmpdir):
-    p = rig.create_cloud_path("dir_0/file0_0.txt")
-
-    with (tmpdir / "test.pkl").open("wb") as f:
-        pickle.dump(p, f)
-
-    with (tmpdir / "test.pkl").open("rb") as f:
-        pickled = pickle.load(f)
-
-    # test a call to the network
-    assert pickled.exists()
-
-    # check we unpickled, and that client is the default client
-    assert str(pickled) == str(p)
-    assert pickled.client == p.client
-    assert rig.client_class._default_client == pickled.client
-
-
 def test_drive_exists(rig):
     """Tests the exists call for top level bucket/container"""
     p = rig.create_cloud_path("dir_0/file0_0.txt")

tests/test_cloudpath_serialize.py

@@ -0,0 +1,32 @@
+import pickle
+
+from cloudpathlib import CloudPath
+
+
+def test_pickle(rig, tmpdir):
+    p = rig.create_cloud_path("dir_0/file0_0.txt")
+
+    with (tmpdir / "test.pkl").open("wb") as f:
+        pickle.dump(p, f)
+
+    with (tmpdir / "test.pkl").open("rb") as f:
+        pickled = pickle.load(f)
+
+    # test a call to the network
+    assert pickled.exists()
+
+    # check we unpickled, and that client is the default client
+    assert str(pickled) == str(p)
+    assert pickled.client == p.client
+    assert rig.client_class._default_client == pickled.client
+
+
+def test_pickle_roundtrip():
+    path1 = CloudPath("s3://bucket/key")
+    pkl1 = pickle.dumps(path1)
+
+    path2 = pickle.loads(pkl1)
+    pkl2 = pickle.dumps(path2)
+
+    assert path1 == path2
+    assert pkl1 == pkl2