From f23f20c1dc1941f9f672c0983a96e23cdaba4387 Mon Sep 17 00:00:00 2001
From: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com>
Date: Wed, 17 Jan 2024 09:39:32 -0800
Subject: [PATCH] fix: postgres destination connector serialization (#2411)

This fixes the serialization of the Elasticsearch destination connector.
Presence of the _client object breaks serialization due to TypeError:
cannot pickle '_thread.lock' object. This removes that object before
serialization.
---
 CHANGELOG.md                         |  3 ++-
 unstructured/__version__.py          |  2 +-
 unstructured/ingest/connector/sql.py | 14 ++++++++++++++
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5dc331744..252d6de0c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,4 +1,4 @@
-## 0.12.1-dev10
+## 0.12.1-dev11
 
 ### Enhancements
 
@@ -21,6 +21,7 @@
 * **Pin version of unstructured-client** Set minimum version of unstructured-client to avoid raising a TypeError when passing `api_key_auth` to `UnstructuredClient`
 * **Fix the serialization of the Pinecone destination connector.** Presence of the PineconeIndex object breaks serialization due to TypeError: cannot pickle '_thread.lock' object. This removes that object before serialization.
 * **Fix the serialization of the Elasticsearch destination connector.** Presence of the _client object breaks serialization due to TypeError: cannot pickle '_thread.lock' object. This removes that object before serialization.
+* **Fix the serialization of the Postgres destination connector.** Presence of the _client object breaks serialization due to TypeError: cannot pickle '_thread.lock' object. This removes that object before serialization.
 * **Fix documentation and sample code for Chroma.** Was pointing to wrong examples..
 
 ## 0.12.0
diff --git a/unstructured/__version__.py b/unstructured/__version__.py
index 843228d06..43ad13892 100644
--- a/unstructured/__version__.py
+++ b/unstructured/__version__.py
@@ -1 +1 @@
-__version__ = "0.12.1-dev10"  # pragma: no cover
+__version__ = "0.12.1-dev11"  # pragma: no cover
diff --git a/unstructured/ingest/connector/sql.py b/unstructured/ingest/connector/sql.py
index f63090537..4c8dafdd4 100644
--- a/unstructured/ingest/connector/sql.py
+++ b/unstructured/ingest/connector/sql.py
@@ -1,9 +1,11 @@
+import copy
 import json
 import typing as t
 import uuid
 from dataclasses import dataclass, field
 
 from unstructured.ingest.enhanced_dataclass import enhanced_field
+from unstructured.ingest.enhanced_dataclass.core import _asdict
 from unstructured.ingest.error import DestinationConnectionError
 from unstructured.ingest.interfaces import (
     AccessConfig,
@@ -68,6 +70,18 @@ class SqlDestinationConnector(BaseDestinationConnector):
     connector_config: SimpleSqlConfig
     _client: t.Optional[t.Any] = field(init=False, default=None)
 
+    def to_dict(self, **kwargs):
+        """
+        The _client variable in this dataclass breaks deepcopy due to:
+        TypeError: cannot pickle '_thread.lock' object
+        When serializing, remove it, meaning client data will need to be reinitialized
+        when deserialized
+        """
+        self_cp = copy.copy(self)
+        if hasattr(self_cp, "_client"):
+            setattr(self_cp, "_client", None)
+        return _asdict(self_cp, **kwargs)
+
     @property
     def client(self):
         if self._client is None: