chore: sync v3 with main branch

google/cloud/bigquery/dataset.py

@@ -17,6 +17,7 @@
 from __future__ import absolute_import
 
 import copy
+from typing import Dict, Any
 
 import google.cloud._helpers  # type: ignore
 
@@ -77,28 +78,29 @@ def _get_routine_reference(self, routine_id):
 class AccessEntry(object):
     """Represents grant of an access role to an entity.
 
-    An entry must have exactly one of the allowed :attr:`ENTITY_TYPES`. If
-    anything but ``view`` or ``routine`` are set, a ``role`` is also required.
-    ``role`` is omitted for ``view`` and ``routine``, because they are always
-    read-only.
+    An entry must have exactly one of the allowed
+    :class:`google.cloud.bigquery.enums.EntityTypes`. If anything but ``view``, ``routine``,
+    or ``dataset`` are set, a ``role`` is also required. ``role`` is omitted for ``view``,
+    ``routine``, ``dataset``, because they are always read-only.
 
     See https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets.
 
     Args:
         role (str):
             Role granted to the entity. The following string values are
             supported: `'READER'`, `'WRITER'`, `'OWNER'`. It may also be
-            :data:`None` if the ``entity_type`` is ``view`` or ``routine``.
+            :data:`None` if the ``entity_type`` is ``view``, ``routine``, or ``dataset``.
 
         entity_type (str):
-            Type of entity being granted the role. One of :attr:`ENTITY_TYPES`.
+            Type of entity being granted the role. See
+            :class:`google.cloud.bigquery.enums.EntityTypes` for supported types.
 
         entity_id (Union[str, Dict[str, str]]):
-            If the ``entity_type`` is not 'view' or 'routine', the ``entity_id``
-            is the ``str`` ID of the entity being granted the role. If the
-            ``entity_type`` is 'view' or 'routine', the ``entity_id`` is a ``dict``
-            representing the view  or routine from a different dataset to grant
-            access to in the following format for views::
+            If the ``entity_type`` is not 'view', 'routine', or 'dataset', the
+            ``entity_id`` is the ``str`` ID of the entity being granted the role. If
+            the ``entity_type`` is 'view' or 'routine', the ``entity_id`` is a ``dict``
+            representing the view or routine from a different dataset to grant access
+            to in the following format for views::
 
                 {
                     'projectId': string,
@@ -114,11 +116,22 @@ class AccessEntry(object):
                     'routineId': string
                 }
 
+            If the ``entity_type`` is 'dataset', the ``entity_id`` is a ``dict`` that includes
+            a 'dataset' field with a ``dict`` representing the dataset and a 'target_types'
+            field with a ``str`` value of the dataset's resource type::
+
+                {
+                    'dataset': {
+                        'projectId': string,
+                        'datasetId': string,
+                    },
+                    'target_types: 'VIEWS'
+                }
+
     Raises:
         ValueError:
-            If the ``entity_type`` is not among :attr:`ENTITY_TYPES`, or if a
-            ``view`` or a ``routine`` has ``role`` set, or a non ``view`` and
-            non ``routine`` **does not** have a ``role`` set.
+            If a ``view``, ``routine``, or ``dataset`` has ``role`` set, or a non ``view``,
+            non ``routine``, and non ``dataset`` **does not** have a ``role`` set.
 
     Examples:
         >>> entry = AccessEntry('OWNER', 'userByEmail', '[email protected]')
@@ -131,27 +144,9 @@ class AccessEntry(object):
         >>> entry = AccessEntry(None, 'view', view)
     """
 
-    ENTITY_TYPES = frozenset(
-        [
-            "userByEmail",
-            "groupByEmail",
-            "domain",
-            "specialGroup",
-            "view",
-            "iamMember",
-            "routine",
-        ]
-    )
-    """Allowed entity types."""
-
-    def __init__(self, role, entity_type, entity_id) -> None:
-        if entity_type not in self.ENTITY_TYPES:
-            message = "Entity type %r not among: %s" % (
-                entity_type,
-                ", ".join(self.ENTITY_TYPES),
-            )
-            raise ValueError(message)
-        if entity_type in ("view", "routine"):
+    def __init__(self, role=None, entity_type=None, entity_id=None) -> None:
+        self._properties: Dict[str, Any] = {}
+        if entity_type in ("view", "routine", "dataset"):
             if role is not None:
                 raise ValueError(
                     "Role must be None for a %r. Received "
@@ -162,7 +157,6 @@ def __init__(self, role, entity_type, entity_id) -> None:
                 raise ValueError(
                     "Role must be set for entity " "type %r" % (entity_type,)
                 )
-
         self._role = role
         self._entity_type = entity_type
         self._entity_id = entity_id
@@ -214,7 +208,8 @@ def to_api_repr(self):
         Returns:
             Dict[str, object]: Access entry represented as an API resource
         """
-        resource = {self._entity_type: self._entity_id}
+        resource = copy.deepcopy(self._properties)
+        resource[self._entity_type] = self._entity_id
         if self._role is not None:
             resource["role"] = self._role
         return resource
@@ -241,7 +236,10 @@ def from_api_repr(cls, resource: dict) -> "AccessEntry":
         entity_type, entity_id = entry.popitem()
         if len(entry) != 0:
             raise ValueError("Entry has unexpected keys remaining.", entry)
-        return cls(role, entity_type, entity_id)
+
+        config = cls(role, entity_type, entity_id)
+        config._properties = copy.deepcopy(resource)
+        return config
 
 
 class DatasetReference(object):

google/cloud/bigquery/enums.py

@@ -236,6 +236,19 @@ def _generate_next_value_(name, start, count, last_values):
     STRUCT = enum.auto()
 
 
+class EntityTypes(str, enum.Enum):
+    """Enum of allowed entity type names in AccessEntry"""
+
+    USER_BY_EMAIL = "userByEmail"
+    GROUP_BY_EMAIL = "groupByEmail"
+    DOMAIN = "domain"
+    DATASET = "dataset"
+    SPECIAL_GROUP = "specialGroup"
+    VIEW = "view"
+    IAM_MEMBER = "iamMember"
+    ROUTINE = "routine"
+
+
 # See also: https://cloud.google.com/bigquery/data-types#legacy_sql_data_types
 # and https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types
 class SqlTypeNames(str, enum.Enum):

samples/geography/requirements.txt

@@ -1,50 +1,51 @@
 attrs==21.2.0
 cachetools==4.2.4
-certifi==2021.5.30
-cffi==1.14.6
-charset-normalizer==2.0.6
-click==8.0.1
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.9
+click==8.0.3
 click-plugins==1.1.1
 cligj==0.7.2
 dataclasses==0.6; python_version < '3.7'
 db-dtypes==0.3.0
 Fiona==1.8.20
 geojson==2.5.0
-geopandas==0.9.0
-google-api-core==2.0.1
-google-auth==2.2.1
-google-cloud-bigquery==2.27.1
-google-cloud-bigquery-storage==2.9.0
-google-cloud-core==2.0.0
-google-crc32c==1.2.0
-google-resumable-media==2.0.3
-googleapis-common-protos==1.53.0
-grpcio==1.41.0
-idna==3.2
-importlib-metadata==4.8.1
-libcst==0.3.21
+geopandas==0.9.0; python_version < '3.7'
+geopandas==0.10.2; python_version >= '3.7'
+google-api-core==2.3.0
+google-auth==2.3.3
+google-cloud-bigquery==2.31.0
+google-cloud-bigquery-storage==2.10.1
+google-cloud-core==2.2.1
+google-crc32c==1.3.0
+google-resumable-media==2.1.0
+googleapis-common-protos==1.54.0
+grpcio==1.42.0
+idna==3.3
+importlib-metadata==4.8.2
+libcst==0.3.23
 munch==2.5.0
 mypy-extensions==0.4.3
-packaging==21.0
+packaging==21.3
 pandas==1.1.5; python_version < '3.7'
 pandas==1.3.4; python_version >= '3.7'
-proto-plus==1.19.2
-protobuf==3.18.0
-pyarrow==6.0.0
+proto-plus==1.19.8
+protobuf==3.19.1
+pyarrow==6.0.1
 pyasn1==0.4.8
 pyasn1-modules==0.2.8
-pycparser==2.20
-pyparsing==2.4.7
+pycparser==2.21
+pyparsing==3.0.6
 pyproj==3.0.1; python_version < "3.7"
 pyproj==3.1.0; python_version > "3.6"
 python-dateutil==2.8.2
-pytz==2021.1
-PyYAML==5.4.1
+pytz==2021.3
+PyYAML==6.0
 requests==2.26.0
-rsa==4.7.2
+rsa==4.8
 Shapely==1.8.0
 six==1.16.0
-typing-extensions==3.10.0.2
+typing-extensions==4.0.1
 typing-inspect==0.7.1
 urllib3==1.26.7
 zipp==3.6.0

samples/magics/requirements-test.txt

@@ -1,3 +1,3 @@
-google-cloud-testutils==1.1.0
+google-cloud-testutils==1.3.1
 pytest==6.2.5
 mock==4.0.3

samples/magics/requirements.txt

@@ -1,13 +1,13 @@
-db-dtypes==0.3.0
-google-cloud-bigquery-storage==2.9.0
+db-dtypes==0.3.1
+google-cloud-bigquery-storage==2.10.1
 google-auth-oauthlib==0.4.6
-grpcio==1.41.0
+grpcio==1.42.0
 ipython==7.16.1; python_version < '3.7'
 ipython==7.29.0; python_version >= '3.7'
 matplotlib==3.3.4; python_version < '3.7'
 matplotlib==3.5.0rc1; python_version >= '3.7'
 pandas==1.1.5; python_version < '3.7'
 pandas==1.3.4; python_version >= '3.7'
-pyarrow==6.0.0
-pytz==2021.1
+pyarrow==6.0.1
+pytz==2021.3
 typing-extensions==3.10.0.2

samples/snippets/authorized_view_tutorial.py

@@ -31,6 +31,7 @@ def run_authorized_view_tutorial(
     # Create a source dataset
     # [START bigquery_avt_create_source_dataset]
     from google.cloud import bigquery
+    from google.cloud.bigquery.enums import EntityTypes
 
     client = bigquery.Client()
     source_dataset_id = "github_source_data"
@@ -113,7 +114,7 @@ def run_authorized_view_tutorial(
     # analyst_group_email = '[email protected]'
     access_entries = shared_dataset.access_entries
     access_entries.append(
-        bigquery.AccessEntry("READER", "groupByEmail", analyst_group_email)
+        bigquery.AccessEntry("READER", EntityTypes.GROUP_BY_EMAIL, analyst_group_email)
     )
     shared_dataset.access_entries = access_entries
     shared_dataset = client.update_dataset(
@@ -125,7 +126,7 @@ def run_authorized_view_tutorial(
     # [START bigquery_avt_source_dataset_access]
     access_entries = source_dataset.access_entries
     access_entries.append(
-        bigquery.AccessEntry(None, "view", view.reference.to_api_repr())
+        bigquery.AccessEntry(None, EntityTypes.VIEW, view.reference.to_api_repr())
     )
     source_dataset.access_entries = access_entries
     source_dataset = client.update_dataset(

samples/snippets/requirements-test.txt

@@ -1,3 +1,3 @@
-google-cloud-testutils==1.1.0
+google-cloud-testutils==1.3.1
 pytest==6.2.5
 mock==4.0.3

samples/snippets/requirements.txt

@@ -1,13 +1,13 @@
-db-dtypes==0.3.0
-google-cloud-bigquery-storage==2.9.0
+db-dtypes==0.3.1
+google-cloud-bigquery-storage==2.10.1
 google-auth-oauthlib==0.4.6
-grpcio==1.41.0
+grpcio==1.42.0
 ipython==7.16.1; python_version < '3.7'
 ipython==7.29.0; python_version >= '3.7'
 matplotlib==3.3.4; python_version < '3.7'
 matplotlib==3.4.1; python_version >= '3.7'
 pandas==1.1.5; python_version < '3.7'
 pandas==1.3.4; python_version >= '3.7'
-pyarrow==6.0.0
-pytz==2021.1
+pyarrow==6.0.1
+pytz==2021.3
 typing-extensions==3.10.0.2

samples/snippets/update_dataset_access.py

@@ -27,6 +27,8 @@ def update_dataset_access(dataset_id: str, entity_id: str) -> None:
     # of the entity, such as a view's table reference.
     entity_id = "[email protected]"
 
+    from google.cloud.bigquery.enums import EntityTypes
+
     # TODO(developer): Set entity_type to the type of entity you are granting access to.
     # Common types include:
     #
@@ -37,7 +39,7 @@ def update_dataset_access(dataset_id: str, entity_id: str) -> None:
     #
     # For a complete reference, see the REST API reference documentation:
     # https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets#Dataset.FIELDS.access
-    entity_type = "groupByEmail"
+    entity_type = EntityTypes.GROUP_BY_EMAIL
 
     # TODO(developer): Set role to a one of the "Basic roles for datasets"
     # described here:

samples/tests/test_copy_table.py

@@ -14,10 +14,11 @@
 
 import typing
 
+import pytest
+
 from .. import copy_table
 
 if typing.TYPE_CHECKING:
-    import pytest
     from google.cloud import bigquery
 
 
@@ -27,6 +28,7 @@ def test_copy_table(
     random_table_id: str,
     client: "bigquery.Client",
 ) -> None:
+    pytest.skip("b/210907595: copy fails for shakespeare table")
 
     copy_table.copy_table(table_with_data_id, random_table_id)
     out, err = capsys.readouterr()

samples/tests/test_copy_table_cmek.py

@@ -12,20 +12,18 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import typing
+import pytest
 
 from .. import copy_table_cmek
 
-if typing.TYPE_CHECKING:
-    import pytest
-
 
 def test_copy_table_cmek(
     capsys: "pytest.CaptureFixture[str]",
     random_table_id: str,
     table_with_data_id: str,
     kms_key_name: str,
 ) -> None:
+    pytest.skip("b/210907595: copy fails for shakespeare table")
 
     copy_table_cmek.copy_table_cmek(random_table_id, table_with_data_id, kms_key_name)
     out, err = capsys.readouterr()

tests/system/test_client.py

@@ -1137,6 +1137,8 @@ def test_extract_table(self):
         self.assertIn("Bharney Rhubble", got)
 
     def test_copy_table(self):
+        pytest.skip("b/210907595: copy fails for shakespeare table")
+
         # If we create a new table to copy from, the test won't work
         # because the new rows will be stored in the streaming buffer,
         # and copy jobs don't read the streaming buffer.