From 4b9ce05520ad5dac8de6104faa28666190957294 Mon Sep 17 00:00:00 2001
From: "R. Conner Howell" <robert@eventualcomputing.com>
Date: Tue, 15 Apr 2025 15:07:24 -0700
Subject: [PATCH 1/2] Adds support for creating a GlueCatalog with own client

---
 pyiceberg/catalog/glue.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/pyiceberg/catalog/glue.py b/pyiceberg/catalog/glue.py
index 4f0a9061df..a71b6d6e71 100644
--- a/pyiceberg/catalog/glue.py
+++ b/pyiceberg/catalog/glue.py
@@ -303,11 +303,17 @@ def add_glue_catalog_id(params: Dict[str, str], **kwargs: Any) -> None:
 
 
 class GlueCatalog(MetastoreCatalog):
-    def __init__(self, name: str, **properties: Any):
+    glue: GlueClient
+
+    def __init__(self, name: str, client: GlueClient | None = None, **properties: Any):
         super().__init__(name, **properties)
 
         retry_mode_prop_value = get_first_property_value(properties, GLUE_RETRY_MODE)
 
+        if client:
+            self.glue = client
+            return
+
         session = boto3.Session(
             profile_name=properties.get(GLUE_PROFILE_NAME),
             region_name=get_first_property_value(properties, GLUE_REGION, AWS_REGION),

From b0fd88b3dfbd7ccc82567c363f68410d003d3601 Mon Sep 17 00:00:00 2001
From: "R. Conner Howell" <robert@eventualcomputing.com>
Date: Fri, 18 Apr 2025 09:06:55 -0700
Subject: [PATCH 2/2] Adds doc comment and refactor if..else block

---
 pyiceberg/catalog/glue.py  | 58 ++++++++++++++++++++++----------------
 tests/catalog/test_glue.py |  8 ++++++
 2 files changed, 41 insertions(+), 25 deletions(-)

diff --git a/pyiceberg/catalog/glue.py b/pyiceberg/catalog/glue.py
index a71b6d6e71..01bb0e9b05 100644
--- a/pyiceberg/catalog/glue.py
+++ b/pyiceberg/catalog/glue.py
@@ -305,36 +305,44 @@ def add_glue_catalog_id(params: Dict[str, str], **kwargs: Any) -> None:
 class GlueCatalog(MetastoreCatalog):
     glue: GlueClient
 
-    def __init__(self, name: str, client: GlueClient | None = None, **properties: Any):
-        super().__init__(name, **properties)
+    def __init__(self, name: str, client: Optional[GlueClient] = None, **properties: Any):
+        """Glue Catalog.
+
+        You either need to provide a boto3 glue client, or one will be constructed from the properties.
 
-        retry_mode_prop_value = get_first_property_value(properties, GLUE_RETRY_MODE)
+        Args:
+            name: Name to identify the catalog.
+            client: An optional boto3 glue client.
+            properties: Properties for glue client construction and configuration.
+        """
+        super().__init__(name, **properties)
 
         if client:
             self.glue = client
-            return
-
-        session = boto3.Session(
-            profile_name=properties.get(GLUE_PROFILE_NAME),
-            region_name=get_first_property_value(properties, GLUE_REGION, AWS_REGION),
-            botocore_session=properties.get(BOTOCORE_SESSION),
-            aws_access_key_id=get_first_property_value(properties, GLUE_ACCESS_KEY_ID, AWS_ACCESS_KEY_ID),
-            aws_secret_access_key=get_first_property_value(properties, GLUE_SECRET_ACCESS_KEY, AWS_SECRET_ACCESS_KEY),
-            aws_session_token=get_first_property_value(properties, GLUE_SESSION_TOKEN, AWS_SESSION_TOKEN),
-        )
-        self.glue: GlueClient = session.client(
-            "glue",
-            endpoint_url=properties.get(GLUE_CATALOG_ENDPOINT),
-            config=Config(
-                retries={
-                    "max_attempts": properties.get(GLUE_MAX_RETRIES, MAX_RETRIES),
-                    "mode": retry_mode_prop_value if retry_mode_prop_value in EXISTING_RETRY_MODES else STANDARD_RETRY_MODE,
-                }
-            ),
-        )
+        else:
+            retry_mode_prop_value = get_first_property_value(properties, GLUE_RETRY_MODE)
+
+            session = boto3.Session(
+                profile_name=properties.get(GLUE_PROFILE_NAME),
+                region_name=get_first_property_value(properties, GLUE_REGION, AWS_REGION),
+                botocore_session=properties.get(BOTOCORE_SESSION),
+                aws_access_key_id=get_first_property_value(properties, GLUE_ACCESS_KEY_ID, AWS_ACCESS_KEY_ID),
+                aws_secret_access_key=get_first_property_value(properties, GLUE_SECRET_ACCESS_KEY, AWS_SECRET_ACCESS_KEY),
+                aws_session_token=get_first_property_value(properties, GLUE_SESSION_TOKEN, AWS_SESSION_TOKEN),
+            )
+            self.glue: GlueClient = session.client(
+                "glue",
+                endpoint_url=properties.get(GLUE_CATALOG_ENDPOINT),
+                config=Config(
+                    retries={
+                        "max_attempts": properties.get(GLUE_MAX_RETRIES, MAX_RETRIES),
+                        "mode": retry_mode_prop_value if retry_mode_prop_value in EXISTING_RETRY_MODES else STANDARD_RETRY_MODE,
+                    }
+                ),
+            )
 
-        if glue_catalog_id := properties.get(GLUE_ID):
-            _register_glue_catalog_id_with_glue_client(self.glue, glue_catalog_id)
+            if glue_catalog_id := properties.get(GLUE_ID):
+                _register_glue_catalog_id_with_glue_client(self.glue, glue_catalog_id)
 
     def _convert_glue_to_iceberg(self, glue_table: TableTypeDef) -> Table:
         properties: Properties = glue_table["Parameters"]
diff --git a/tests/catalog/test_glue.py b/tests/catalog/test_glue.py
index eabbffb378..df1734eb68 100644
--- a/tests/catalog/test_glue.py
+++ b/tests/catalog/test_glue.py
@@ -932,3 +932,11 @@ def test_glue_endpoint_override(_bucket_initialize: None, moto_endpoint_url: str
         catalog_name, **{"s3.endpoint": moto_endpoint_url, "warehouse": f"s3://{BUCKET_NAME}", "glue.endpoint": test_endpoint}
     )
     assert test_catalog.glue.meta.endpoint_url == test_endpoint
+
+
+@mock_aws
+def test_glue_client_override() -> None:
+    catalog_name = "glue"
+    test_client = boto3.client("glue", region_name="us-west-2")
+    test_catalog = GlueCatalog(catalog_name, test_client)
+    assert test_catalog.glue is test_client