Add snapshot-loading-mode option to RESTCatalog

mkdocs/docs/configuration.md

@@ -332,6 +332,7 @@ catalog:
 | rest.signing-region | us-east-1                        | The region to use when SigV4 signing a request                                                     |
 | rest.signing-name   | execute-api                      | The service signing name to use when SigV4 signing a request                                       |
 | oauth2-server-uri   | <https://auth-service/cc>          | Authentication URL to use for client credentials authentication (default: uri + 'v1/oauth/tokens') |
+| snapshot-loading-mode | refs                             | The snapshots to return in the body of the metadata. Setting the value to `all` would return the full set of snapshots currently valid for the table. Setting the value to `refs` would load all snapshots referenced by branches or tags. |
 
 <!-- markdown-link-check-enable-->
 

pyiceberg/catalog/rest/__init__.py

@@ -138,6 +138,7 @@ class IdentifierKind(Enum):
 SIGV4_REGION = "rest.signing-region"
 SIGV4_SERVICE = "rest.signing-name"
 OAUTH2_SERVER_URI = "oauth2-server-uri"
+SNAPSHOT_LOADING_MODE = "snapshot-loading-mode"
 
 NAMESPACE_SEPARATOR = b"\x1f".decode(UTF8)
 
@@ -678,7 +679,16 @@ def list_tables(self, namespace: Union[str, Identifier]) -> List[Identifier]:
 
     @retry(**_RETRY_ARGS)
     def load_table(self, identifier: Union[str, Identifier]) -> Table:
-        response = self._session.get(self.url(Endpoints.load_table, prefixed=True, **self._split_identifier_for_path(identifier)))
+        params = {}
+        if mode := self.properties.get(SNAPSHOT_LOADING_MODE):
+            if mode in {"all", "refs"}:
+                params["snapshots"] = mode
+            else:
+                raise ValueError("Invalid snapshot-loading-mode: {}")
+
+        response = self._session.get(
+            self.url(Endpoints.load_table, prefixed=True, **self._split_identifier_for_path(identifier)), params=params
+        )
         try:
             response.raise_for_status()
         except HTTPError as exc:

tests/catalog/test_rest.py

@@ -24,7 +24,7 @@
 
 import pyiceberg
 from pyiceberg.catalog import PropertiesUpdateSummary, load_catalog
-from pyiceberg.catalog.rest import OAUTH2_SERVER_URI, RestCatalog
+from pyiceberg.catalog.rest import OAUTH2_SERVER_URI, SNAPSHOT_LOADING_MODE, RestCatalog
 from pyiceberg.exceptions import (
     AuthorizationExpiredError,
     NamespaceAlreadyExistsError,
@@ -853,6 +853,29 @@ def test_load_table_200(rest_mock: Mocker, example_table_metadata_with_snapshot_
     assert actual == expected
 
 
+def test_load_table_200_loading_mode(
+    rest_mock: Mocker, example_table_metadata_with_snapshot_v1_rest_json: Dict[str, Any]
+) -> None:
+    rest_mock.get(
+        f"{TEST_URI}v1/namespaces/fokko/tables/table?snapshots=refs",
+        json=example_table_metadata_with_snapshot_v1_rest_json,
+        status_code=200,
+        request_headers=TEST_HEADERS,
+    )
+    catalog = RestCatalog("rest", uri=TEST_URI, token=TEST_TOKEN, **{SNAPSHOT_LOADING_MODE: "refs"})
+    actual = catalog.load_table(("fokko", "table"))
+    expected = Table(
+        identifier=("fokko", "table"),
+        metadata_location=example_table_metadata_with_snapshot_v1_rest_json["metadata-location"],
+        metadata=TableMetadataV1(**example_table_metadata_with_snapshot_v1_rest_json["metadata"]),
+        io=load_file_io(),
+        catalog=catalog,
+    )
+    # First compare the dicts
+    assert actual.metadata.model_dump() == expected.metadata.model_dump()
+    assert actual == expected
+
+
 def test_load_table_honor_access_delegation(
     rest_mock: Mocker, example_table_metadata_with_snapshot_v1_rest_json: Dict[str, Any]
 ) -> None: