fix: deprecate Lake Formation Governed Tables (BREAKING CHANGE) (#2692)

Author: jaidisido

CONTRIBUTING.md

@@ -224,7 +224,7 @@ To run all database MySQL tests (Using 8 parallel processes):
 
 ``pytest -n 8 tests/unit/test_mysql.py``
 
-To run all tests for all python versions (assuming Amazon QuickSight is activated and the optional stacks deployed):
+To run all tests for all python versions (assuming Amazon QuickSight is activated and the optional stack deployed):
 
 ``./test.sh``
 

README.md

@@ -153,7 +153,6 @@ The quickest way to get started is to use AWS Glue with Ray. Read our [docs](htt
   - [029 - S3 Select](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/029%20-%20S3%20Select.ipynb)
   - [030 - Data Api](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/030%20-%20Data%20Api.ipynb)
   - [031 - OpenSearch](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/031%20-%20OpenSearch.ipynb)
-  - [032 - Lake Formation Governed Tables](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/032%20-%20Lake%20Formation%20Governed%20Tables.ipynb)
   - [033 - Amazon Neptune](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/033%20-%20Amazon%20Neptune.ipynb)
   - [034 - Distributing Calls Using Ray](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/034%20-%20Distributing%20Calls%20using%20Ray.ipynb)
   - [035 - Distributing Calls on Ray Remote Cluster](https://github.com/aws/aws-sdk-pandas/blob/main/tutorials/035%20-%20Distributing%20Calls%20on%20Ray%20Remote%20Cluster.ipynb)
@@ -167,7 +166,6 @@ The quickest way to get started is to use AWS Glue with Ray. Read our [docs](htt
   - [Amazon S3](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#amazon-s3)
   - [AWS Glue Catalog](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#aws-glue-catalog)
   - [Amazon Athena](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#amazon-athena)
-  - [AWS Lake Formation](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#aws-lake-formation)
   - [Amazon Redshift](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#amazon-redshift)
   - [PostgreSQL](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#postgresql)
   - [MySQL](https://aws-sdk-pandas.readthedocs.io/en/3.6.0/api.html#mysql)

awswrangler/__init__.py

@@ -19,7 +19,6 @@
     emr,
     emr_serverless,
     exceptions,
-    lakeformation,
     mysql,
     neptune,
     opensearch,
@@ -58,7 +57,6 @@
     "s3",
     "sts",
     "redshift",
-    "lakeformation",
     "mysql",
     "neptune",
     "postgresql",

awswrangler/_config.py

@@ -44,7 +44,6 @@ class _ConfigArg(NamedTuple):
     "max_local_cache_entries": _ConfigArg(dtype=int, nullable=False, parent_parameter_key="athena_cache_settings"),
     "athena_query_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
     "cloudwatch_query_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
-    "lakeformation_query_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
     "neptune_load_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
     "timestream_batch_load_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
     "emr_serverless_job_wait_polling_delay": _ConfigArg(dtype=float, nullable=False),
@@ -61,7 +60,6 @@ class _ConfigArg(NamedTuple):
     "redshift_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
     "kms_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
     "emr_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
-    "lakeformation_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
     "dynamodb_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
     "secretsmanager_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
     "timestream_query_endpoint_url": _ConfigArg(dtype=str, nullable=True, enforced=True, loaded=True),
@@ -353,15 +351,6 @@ def cloudwatch_query_wait_polling_delay(self) -> float:
     def cloudwatch_query_wait_polling_delay(self, value: float) -> None:
         self._set_config_value(key="cloudwatch_query_wait_polling_delay", value=value)
 
-    @property
-    def lakeformation_query_wait_polling_delay(self) -> float:
-        """Property lakeformation_query_wait_polling_delay."""
-        return cast(float, self["lakeformation_query_wait_polling_delay"])
-
-    @lakeformation_query_wait_polling_delay.setter
-    def lakeformation_query_wait_polling_delay(self, value: float) -> None:
-        self._set_config_value(key="lakeformation_query_wait_polling_delay", value=value)
-
     @property
     def neptune_load_wait_polling_delay(self) -> float:
         """Property neptune_load_wait_polling_delay."""
@@ -497,15 +486,6 @@ def emr_endpoint_url(self) -> str | None:
     def emr_endpoint_url(self, value: str | None) -> None:
         self._set_config_value(key="emr_endpoint_url", value=value)
 
-    @property
-    def lakeformation_endpoint_url(self) -> str | None:
-        """Property lakeformation_endpoint_url."""
-        return cast(Optional[str], self["lakeformation_endpoint_url"])
-
-    @lakeformation_endpoint_url.setter
-    def lakeformation_endpoint_url(self, value: str | None) -> None:
-        self._set_config_value(key="lakeformation_endpoint_url", value=value)
-
     @property
     def dynamodb_endpoint_url(self) -> str | None:
         """Property dynamodb_endpoint_url."""

awswrangler/_utils.py

@@ -51,7 +51,6 @@
     from mypy_boto3_emr_serverless import EMRServerlessClient
     from mypy_boto3_glue import GlueClient
     from mypy_boto3_kms.client import KMSClient
-    from mypy_boto3_lakeformation.client import LakeFormationClient
     from mypy_boto3_logs.client import CloudWatchLogsClient
     from mypy_boto3_opensearch.client import OpenSearchServiceClient
     from mypy_boto3_opensearchserverless.client import OpenSearchServiceServerlessClient
@@ -75,7 +74,6 @@
         "emr-serverless",
         "glue",
         "kms",
-        "lakeformation",
         "logs",
         "opensearch",
         "opensearchserverless",
@@ -267,8 +265,6 @@ def _get_endpoint_url(service_name: str) -> str | None:
         endpoint_url = _config.config.kms_endpoint_url
     elif service_name == "emr" and _config.config.emr_endpoint_url is not None:
         endpoint_url = _config.config.emr_endpoint_url
-    elif service_name == "lakeformation" and _config.config.lakeformation_endpoint_url is not None:
-        endpoint_url = _config.config.lakeformation_endpoint_url
     elif service_name == "dynamodb" and _config.config.dynamodb_endpoint_url is not None:
         endpoint_url = _config.config.dynamodb_endpoint_url
     elif service_name == "secretsmanager" and _config.config.secretsmanager_endpoint_url is not None:
@@ -301,16 +297,6 @@ def client(
     ...
 
 
-@overload
-def client(
-    service_name: 'Literal["lakeformation"]',
-    session: boto3.Session | None = None,
-    botocore_config: Config | None = None,
-    verify: str | bool | None = None,
-) -> "LakeFormationClient":
-    ...
-
-
 @overload
 def client(
     service_name: 'Literal["logs"]',

awswrangler/athena/_utils.py

@@ -30,7 +30,7 @@
 from awswrangler import _data_types, _utils, catalog, exceptions, s3, sts, typing
 from awswrangler._config import apply_configs
 from awswrangler._sql_formatter import _process_sql_params
-from awswrangler.catalog._utils import _catalog_id, _transaction_id
+from awswrangler.catalog._utils import _catalog_id
 
 from . import _executions
 from ._cache import _cache_manager, _LocalMetadataCacheManager
@@ -935,8 +935,6 @@ def show_create_table(
 def generate_create_query(
     table: str,
     database: str | None = None,
-    transaction_id: str | None = None,
-    query_as_of_time: str | None = None,
     catalog_id: str | None = None,
     boto3_session: boto3.Session | None = None,
 ) -> str:
@@ -950,11 +948,6 @@ def generate_create_query(
         Table name.
     database : str
         Database name.
-    transaction_id: str, optional
-        The ID of the transaction.
-    query_as_of_time: str, optional
-        The time as of when to read the table contents. Must be a valid Unix epoch timestamp.
-        Cannot be specified alongside transaction_id.
     catalog_id : str, optional
         The ID of the Data Catalog from which to retrieve Databases.
         If none is provided, the AWS account ID is used by default.
@@ -992,14 +985,9 @@ def parse_properties(parameters: dict[str, str]) -> str:
         return ", \n".join(properties_str)
 
     client_glue = _utils.client(service_name="glue", session=boto3_session)
-    table_detail = client_glue.get_table(
-        **_catalog_id(
-            catalog_id=catalog_id,
-            **_transaction_id(
-                transaction_id=transaction_id, query_as_of_time=query_as_of_time, DatabaseName=database, Name=table
-            ),
-        )
-    )["Table"]
+    table_detail = client_glue.get_table(**_catalog_id(catalog_id=catalog_id, DatabaseName=database, Name=table))[
+        "Table"
+    ]
     if table_detail["TableType"] == "VIRTUAL_VIEW":
         glue_base64_query: str = table_detail["ViewOriginalText"].replace("/* Presto View: ", "").replace(" */", "")
         glue_query: str = json.loads(base64.b64decode(glue_base64_query))["originalSql"]

awswrangler/catalog/_add.py

@@ -17,7 +17,7 @@
     _parquet_partition_definition,
     _update_table_definition,
 )
-from awswrangler.catalog._utils import _catalog_id, _transaction_id, sanitize_table_name
+from awswrangler.catalog._utils import _catalog_id, sanitize_table_name
 
 _logger: logging.Logger = logging.getLogger(__name__)
 
@@ -382,7 +382,6 @@ def add_column(
     column_name: str,
     column_type: str = "string",
     column_comment: str | None = None,
-    transaction_id: str | None = None,
     boto3_session: boto3.Session | None = None,
     catalog_id: str | None = None,
 ) -> None:
@@ -400,8 +399,6 @@ def add_column(
         Column type.
     column_comment : str
         Column Comment
-    transaction_id: str, optional
-        The ID of the transaction (i.e. used with GOVERNED tables).
     boto3_session : boto3.Session(), optional
         Boto3 Session. The default boto3 session will be used if boto3_session receive None.
     catalog_id : str, optional
@@ -425,21 +422,13 @@ def add_column(
     """
     if _check_column_type(column_type):
         client_glue = _utils.client(service_name="glue", session=boto3_session)
-        table_res = client_glue.get_table(
-            **_catalog_id(
-                catalog_id=catalog_id,
-                **_transaction_id(transaction_id=transaction_id, DatabaseName=database, Name=table),
-            )
-        )
+        table_res = client_glue.get_table(**_catalog_id(catalog_id=catalog_id, DatabaseName=database, Name=table))
         table_input: dict[str, Any] = _update_table_definition(table_res)
         table_input["StorageDescriptor"]["Columns"].append(
             {"Name": column_name, "Type": column_type, "Comment": column_comment}
         )
         res: dict[str, Any] = client_glue.update_table(
-            **_catalog_id(
-                catalog_id=catalog_id,
-                **_transaction_id(transaction_id=transaction_id, DatabaseName=database, TableInput=table_input),
-            )
+            **_catalog_id(catalog_id=catalog_id, DatabaseName=database, TableInput=table_input)
         )
         if ("Errors" in res) and res["Errors"]:
             for error in res["Errors"]: