Adds support for creating a GlueCatalog with own client (#1920)

Closes #1910 

# Rationale for this change

When working with the GlueCatalog, I may already have a GlueClient that
I've instantiated from elsewhere, and perhaps wish to keep. This allows
passing our client to the GlueCatalog constructor so that we aren't
forced into getting a new client.

This is slightly interesting because it's the only catalog that now has
a different constructor signature. Also it may be odd for users to pass
a client, but then none of their properties (which may have retry
configs) are applied.

An alternative to consider is having a `from_client` or `with_client`
staticmethod, but I did not see precedence elsewhere. I will leave it to
the maintainers to decide which they prefer and will update accordingly.
Similarly, I can do the same for dynamodb 🙂

I've also skipped the event_handler for a user-provided client because I
wouldn't want to impede on their existing events, also the param is
optional. Something to consider is using the [unique_id
arg](https://github.com/boto/botocore/blob/aaa6690e45c8dabcde3a8d2d1aa34b5fd399fba7/botocore/hooks.py#L89)
when registering an event.

> If a ``unique_id`` is given, the handler will not be registered
> if a handler with the ``unique_id`` has already been registered.


# Are these changes tested?

Basic unit test to assert the client passed is the client used.

# Are there any user-facing changes?

I believe so since this is an addition to the public API.

Author: rchowell

pyiceberg/catalog/glue.py

@@ -303,32 +303,46 @@ def add_glue_catalog_id(params: Dict[str, str], **kwargs: Any) -> None:
 
 
 class GlueCatalog(MetastoreCatalog):
-    def __init__(self, name: str, **properties: Any):
-        super().__init__(name, **properties)
+    glue: GlueClient
 
-        retry_mode_prop_value = get_first_property_value(properties, GLUE_RETRY_MODE)
+    def __init__(self, name: str, client: Optional[GlueClient] = None, **properties: Any):
+        """Glue Catalog.
 
-        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,
-                }
-            ),
-        )
+        You either need to provide a boto3 glue client, or one will be constructed from the properties.
+
+        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
+        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"]

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