feat: add load_view to REST catalog

Author: spr0els

pyiceberg/catalog/__init__.py

@@ -644,6 +644,23 @@ def list_views(self, namespace: str | Identifier) -> list[Identifier]:
             NoSuchNamespaceError: If a namespace with the given name does not exist.
         """
 
+    @abstractmethod
+    def load_view(self, identifier: str | Identifier) -> View:
+        """Load the view's metadata and returns the view instance.
+
+        You can also use this method to check for view existence using 'try catalog.load_view() except NoSuchViewError'.
+        Note: This method doesn't scan data stored in the view.
+
+        Args:
+            identifier (str | Identifier): View identifier.
+
+        Returns:
+            View: the view instance with its metadata.
+
+        Raises:
+            NoSuchViewError: If a view with the name does not exist.
+        """
+
     @abstractmethod
     def load_namespace_properties(self, namespace: str | Identifier) -> Properties:
         """Get properties for a namespace.

pyiceberg/catalog/bigquery_metastore.py

@@ -41,6 +41,7 @@
 from pyiceberg.table.update import TableRequirement, TableUpdate
 from pyiceberg.typedef import EMPTY_DICT, Identifier, Properties
 from pyiceberg.utils.config import Config
+from pyiceberg.view import View
 
 if TYPE_CHECKING:
     import pyarrow as pa
@@ -310,6 +311,9 @@ def drop_view(self, identifier: str | Identifier) -> None:
     def view_exists(self, identifier: str | Identifier) -> bool:
         raise NotImplementedError
 
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError
+
     def load_namespace_properties(self, namespace: str | Identifier) -> Properties:
         dataset_name = self.identifier_to_database(namespace)
 

pyiceberg/catalog/dynamodb.py

@@ -558,6 +558,9 @@ def drop_view(self, identifier: str | Identifier) -> None:
     def view_exists(self, identifier: str | Identifier) -> bool:
         raise NotImplementedError
 
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError
+
     def _get_iceberg_table_item(self, database_name: str, table_name: str) -> dict[str, Any]:
         try:
             return self._get_dynamo_item(identifier=f"{database_name}.{table_name}", namespace=database_name)

pyiceberg/catalog/glue.py

@@ -972,6 +972,9 @@ def drop_view(self, identifier: str | Identifier) -> None:
     def view_exists(self, identifier: str | Identifier) -> bool:
         raise NotImplementedError
 
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError
+
     @staticmethod
     def __is_iceberg_table(table: "TableTypeDef") -> bool:
         return table.get("Parameters", {}).get(TABLE_TYPE, "").lower() == ICEBERG

pyiceberg/catalog/hive.py

@@ -482,6 +482,9 @@ def list_views(self, namespace: str | Identifier) -> list[Identifier]:
     def view_exists(self, identifier: str | Identifier) -> bool:
         raise NotImplementedError
 
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError
+
     def _create_lock_request(self, database_name: str, table_name: str) -> LockRequest:
         lock_component: LockComponent = LockComponent(
             level=LockLevel.TABLE, type=LockType.EXCLUSIVE, dbname=database_name, tablename=table_name, isTransactional=True

pyiceberg/catalog/noop.py

@@ -143,3 +143,6 @@ def create_view(
         properties: Properties = EMPTY_DICT,
     ) -> View:
         raise NotImplementedError
+
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError

pyiceberg/catalog/rest/__init__.py

@@ -152,6 +152,7 @@ class Endpoints:
     get_token: str = "oauth/tokens"
     rename_table: str = "tables/rename"
     list_views: str = "namespaces/{namespace}/views"
+    load_view: str = "namespaces/{namespace}/views/{view}"
     create_view: str = "namespaces/{namespace}/views"
     drop_view: str = "namespaces/{namespace}/views/{view}"
     view_exists: str = "namespaces/{namespace}/views/{view}"
@@ -180,6 +181,7 @@ class Capability:
     V1_REGISTER_TABLE = Endpoint(http_method=HttpMethod.POST, path=f"{API_PREFIX}/{Endpoints.register_table}")
 
     V1_LIST_VIEWS = Endpoint(http_method=HttpMethod.GET, path=f"{API_PREFIX}/{Endpoints.list_views}")
+    V1_LOAD_VIEW = Endpoint(http_method=HttpMethod.GET, path=f"{API_PREFIX}/{Endpoints.load_view}")
     V1_VIEW_EXISTS = Endpoint(http_method=HttpMethod.HEAD, path=f"{API_PREFIX}/{Endpoints.view_exists}")
     V1_DELETE_VIEW = Endpoint(http_method=HttpMethod.DELETE, path=f"{API_PREFIX}/{Endpoints.drop_view}")
     V1_SUBMIT_TABLE_SCAN_PLAN = Endpoint(http_method=HttpMethod.POST, path=f"{API_PREFIX}/{Endpoints.plan_table_scan}")
@@ -209,6 +211,7 @@ class Capability:
 VIEW_ENDPOINTS: frozenset[Endpoint] = frozenset(
     (
         Capability.V1_LIST_VIEWS,
+        Capability.V1_LOAD_VIEW,
         Capability.V1_DELETE_VIEW,
     )
 )
@@ -1099,6 +1102,21 @@ def list_views(self, namespace: str | Identifier) -> list[Identifier]:
             _handle_non_200_response(exc, {404: NoSuchNamespaceError})
         return [(*view.namespace, view.name) for view in ListViewsResponse.model_validate_json(response.text).identifiers]
 
+    @retry(**_RETRY_ARGS)
+    def load_view(self, identifier: str | Identifier) -> View:
+        self._check_endpoint(Capability.V1_LOAD_VIEW)
+        response = self._session.get(
+            self.url(Endpoints.load_view, prefixed=True, **self._split_identifier_for_path(identifier, IdentifierKind.VIEW)),
+            params={},
+        )
+        try:
+            response.raise_for_status()
+        except HTTPError as exc:
+            _handle_non_200_response(exc, {404: NoSuchViewError})
+
+        view_response = ViewResponse.model_validate_json(response.text)
+        return self._response_to_view(self.identifier_to_tuple(identifier), view_response)
+
     @retry(**_RETRY_ARGS)
     def commit_table(
         self, table: Table, requirements: tuple[TableRequirement, ...], updates: tuple[TableUpdate, ...]

pyiceberg/catalog/sql.py

@@ -744,6 +744,9 @@ def view_exists(self, identifier: str | Identifier) -> bool:
     def drop_view(self, identifier: str | Identifier) -> None:
         raise NotImplementedError
 
+    def load_view(self, identifier: str | Identifier) -> View:
+        raise NotImplementedError
+
     def close(self) -> None:
         """Close the catalog and release database connections.
 

tests/catalog/test_rest.py

@@ -103,6 +103,7 @@
     Capability.V1_RENAME_TABLE,
     Capability.V1_REGISTER_TABLE,
     Capability.V1_LIST_VIEWS,
+    Capability.V1_LOAD_VIEW,
     Capability.V1_VIEW_EXISTS,
     Capability.V1_DELETE_VIEW,
     Capability.V1_SUBMIT_TABLE_SCAN_PLAN,
@@ -1416,6 +1417,38 @@ def test_create_view_409(
     assert "View already exists" in str(e.value)
 
 
+def test_load_view_200(rest_mock: Mocker, example_view_metadata_rest_json: dict[str, Any]) -> None:
+    rest_mock.get(
+        f"{TEST_URI}v1/namespaces/fokko/views/view",
+        json=example_view_metadata_rest_json,
+        status_code=200,
+        request_headers=TEST_HEADERS,
+    )
+    catalog = RestCatalog("rest", uri=TEST_URI, token=TEST_TOKEN)
+    actual = catalog.load_view(("fokko", "view"))
+    expected = View(identifier=("fokko", "view"), metadata=ViewMetadata(**example_view_metadata_rest_json["metadata"]))
+    assert actual == expected
+
+
+def test_load_view_404(rest_mock: Mocker) -> None:
+    rest_mock.get(
+        f"{TEST_URI}v1/namespaces/fokko/views/non_existent_view",
+        json={
+            "error": {
+                "message": "View does not exist: examples.non_existent_view in warehouse 8bcb0838-50fc-472d-9ddb-8feb89ef5f1e",
+                "type": "NoSuchNamespaceErrorException",
+                "code": 404,
+            }
+        },
+        status_code=404,
+        request_headers=TEST_HEADERS,
+    )
+
+    with pytest.raises(NoSuchViewError) as e:
+        RestCatalog("rest", uri=TEST_URI, token=TEST_TOKEN).load_view(("fokko", "non_existent_view"))
+    assert "View does not exist" in str(e.value)
+
+
 def test_create_table_if_not_exists_200(
     rest_mock: Mocker, table_schema_simple: Schema, example_table_metadata_no_snapshot_v1_rest_json: dict[str, Any]
 ) -> None: