From 514d4477dada4b08c2be2fc6a297c43fe30282a4 Mon Sep 17 00:00:00 2001
From: Aaron Taylor <git@ataylor.io>
Date: Sat, 20 Jul 2024 19:41:35 -0700
Subject: [PATCH] allow for roundtrips of cloudpaths through pickle
 serialization

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
---
 HISTORY.md                        |  1 +
 cloudpathlib/cloudpath.py         |  3 ++-
 tests/test_cloudpath_serialize.py | 14 ++++++++++++++
 3 files changed, 17 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_cloudpath_serialize.py

diff --git a/HISTORY.md b/HISTORY.md
index 046ab12d..d7e716ca 100644
--- a/HISTORY.md
+++ b/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))
diff --git a/cloudpathlib/cloudpath.py b/cloudpathlib/cloudpath.py
index 8bad810d..e57c4af2 100644
--- a/cloudpathlib/cloudpath.py
+++ b/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
 
diff --git a/tests/test_cloudpath_serialize.py b/tests/test_cloudpath_serialize.py
new file mode 100644
index 00000000..ae8857af
--- /dev/null
+++ b/tests/test_cloudpath_serialize.py
@@ -0,0 +1,14 @@
+import pickle
+
+from cloudpathlib import CloudPath
+
+
+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