google-cloud-bigquery 3.26.0__tar.gz → 3.28.0__tar.gz

{google_cloud_bigquery-3.26.0/google_cloud_bigquery.egg-info → google_cloud_bigquery-3.28.0}/PKG-INFO

@@ -1,12 +1,10 @@
 Metadata-Version: 2.1
 Name: google-cloud-bigquery
-Version: 3.26.0
+Version: 3.28.0
 Summary: Google BigQuery API client library
-Home-page: https://github.com/googleapis/python-bigquery
-Author: Google LLC
-Author-email: googleapis-packages@google.com
+Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache 2.0
-Platform: Posix; MacOS X; Windows
+Project-URL: Repository, https://github.com/googleapis/python-bigquery
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -21,6 +19,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Operating System :: OS Independent
 Classifier: Topic :: Internet
 Requires-Python: >=3.7
+Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: google-api-core[grpc]<3.0.0dev,>=2.11.1
 Requires-Dist: google-auth<3.0.0dev,>=2.14.1
@@ -43,7 +42,7 @@ Provides-Extra: ipywidgets
 Requires-Dist: ipywidgets>=7.7.0; extra == "ipywidgets"
 Requires-Dist: ipykernel>=6.0.0; extra == "ipywidgets"
 Provides-Extra: geopandas
-Requires-Dist: geopandas<1.0dev,>=0.9.0; extra == "geopandas"
+Requires-Dist: geopandas<2.0dev,>=0.9.0; extra == "geopandas"
 Requires-Dist: Shapely<3.0.0dev,>=1.8.4; extra == "geopandas"
 Provides-Extra: ipython
 Requires-Dist: bigquery-magics>=0.1.0; extra == "ipython"
@@ -57,25 +56,7 @@ Provides-Extra: bigquery-v2
 Requires-Dist: proto-plus<2.0.0dev,>=1.22.3; extra == "bigquery-v2"
 Requires-Dist: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.2; extra == "bigquery-v2"
 Provides-Extra: all
-Requires-Dist: google-cloud-bigquery-storage<3.0.0dev,>=2.6.0; extra == "all"
-Requires-Dist: grpcio<2.0dev,>=1.47.0; extra == "all"
-Requires-Dist: grpcio<2.0dev,>=1.49.1; python_version >= "3.11" and extra == "all"
-Requires-Dist: pyarrow>=3.0.0; extra == "all"
-Requires-Dist: pandas>=1.1.0; extra == "all"
-Requires-Dist: pyarrow>=3.0.0; extra == "all"
-Requires-Dist: db-dtypes<2.0.0dev,>=0.3.0; extra == "all"
-Requires-Dist: importlib_metadata>=1.0.0; python_version < "3.8" and extra == "all"
-Requires-Dist: ipywidgets>=7.7.0; extra == "all"
-Requires-Dist: ipykernel>=6.0.0; extra == "all"
-Requires-Dist: geopandas<1.0dev,>=0.9.0; extra == "all"
-Requires-Dist: Shapely<3.0.0dev,>=1.8.4; extra == "all"
-Requires-Dist: bigquery-magics>=0.1.0; extra == "all"
-Requires-Dist: tqdm<5.0.0dev,>=4.7.4; extra == "all"
-Requires-Dist: opentelemetry-api>=1.1.0; extra == "all"
-Requires-Dist: opentelemetry-sdk>=1.1.0; extra == "all"
-Requires-Dist: opentelemetry-instrumentation>=0.20b0; extra == "all"
-Requires-Dist: proto-plus<2.0.0dev,>=1.22.3; extra == "all"
-Requires-Dist: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.2; extra == "all"
+Requires-Dist: google-cloud-bigquery[bigquery_v2,bqstorage,geopandas,ipython,ipywidgets,opentelemetry,pandas,tqdm]; extra == "all"
 
 Python Client for Google BigQuery
 =================================

{google_cloud_bigquery-3.26.0 → google_cloud_bigquery-3.28.0}/google/cloud/bigquery/_helpers.py

@@ -22,7 +22,7 @@ import math
 import re
 import os
 import warnings
-from typing import Optional, Union
+from typing import Optional, Union, Any, Tuple, Type
 
 from dateutil import relativedelta
 from google.cloud._helpers import UTC  # type: ignore
@@ -1004,3 +1004,33 @@ def _verify_job_config_type(job_config, expected_type, param_name="job_config"):
                 job_config=job_config,
             )
         )
+
+
+def _isinstance_or_raise(
+    value: Any,
+    dtype: Union[Type, Tuple[Type, ...]],
+    none_allowed: Optional[bool] = False,
+) -> Any:
+    """Determine whether a value type matches a given datatype or None.
+    Args:
+        value (Any): Value to be checked.
+        dtype (type): Expected data type or tuple of data types.
+        none_allowed Optional(bool): whether value is allowed to be None. Default
+           is False.
+    Returns:
+        Any: Returns the input value if the type check is successful.
+    Raises:
+        TypeError: If the input value's type does not match the expected data type(s).
+    """
+    if none_allowed and value is None:
+        return value
+
+    if isinstance(value, dtype):
+        return value
+
+    or_none = ""
+    if none_allowed:
+        or_none = " (or None)"
+
+    msg = f"Pass {value} as a '{dtype}'{or_none}. Got {type(value)}."
+    raise TypeError(msg)

{google_cloud_bigquery-3.26.0 → google_cloud_bigquery-3.28.0}/google/cloud/bigquery/_pandas_helpers.py

@@ -21,13 +21,14 @@ from itertools import islice
 import logging
 import queue
 import warnings
-from typing import Any, Union
+from typing import Any, Union, Optional, Callable, Generator, List
 
 
 from google.cloud.bigquery import _pyarrow_helpers
 from google.cloud.bigquery import _versions_helpers
 from google.cloud.bigquery import schema
 
+
 try:
     import pandas  # type: ignore
 
@@ -75,7 +76,7 @@ else:
         _to_wkb = _to_wkb()
 
 try:
-    from google.cloud.bigquery_storage import ArrowSerializationOptions
+    from google.cloud.bigquery_storage_v1.types import ArrowSerializationOptions
 except ImportError:
     _ARROW_COMPRESSION_SUPPORT = False
 else:
@@ -816,18 +817,54 @@ def _nowait(futures):
 
 
 def _download_table_bqstorage(
-    project_id,
-    table,
-    bqstorage_client,
-    preserve_order=False,
-    selected_fields=None,
-    page_to_item=None,
-    max_queue_size=_MAX_QUEUE_SIZE_DEFAULT,
-):
-    """Use (faster, but billable) BQ Storage API to construct DataFrame."""
+    project_id: str,
+    table: Any,
+    bqstorage_client: Any,
+    preserve_order: bool = False,
+    selected_fields: Optional[List[Any]] = None,
+    page_to_item: Optional[Callable] = None,
+    max_queue_size: Any = _MAX_QUEUE_SIZE_DEFAULT,
+    max_stream_count: Optional[int] = None,
+) -> Generator[Any, None, None]:
+    """Downloads a BigQuery table using the BigQuery Storage API.
+
+    This method uses the faster, but potentially more expensive, BigQuery
+    Storage API to download a table as a Pandas DataFrame. It supports
+    parallel downloads and optional data transformations.
+
+    Args:
+        project_id (str): The ID of the Google Cloud project containing
+            the table.
+        table (Any): The BigQuery table to download.
+        bqstorage_client (Any): An
+            authenticated BigQuery Storage API client.
+        preserve_order (bool, optional): Whether to preserve the order
+            of the rows as they are read from BigQuery. If True this limits
+            the number of streams to one and overrides `max_stream_count`.
+            Defaults to False.
+        selected_fields (Optional[List[SchemaField]]):
+            A list of BigQuery schema fields to select for download. If None,
+            all fields are downloaded. Defaults to None.
+        page_to_item (Optional[Callable]): An optional callable
+            function that takes a page of data from the BigQuery Storage API
+        max_stream_count (Optional[int]): The maximum number of
+            concurrent streams to use for downloading data. If `preserve_order`
+            is True, the requested streams are limited to 1 regardless of the
+            `max_stream_count` value. If 0 or None, then the number of
+            requested streams will be unbounded. Defaults to None.
+
+    Yields:
+        pandas.DataFrame: Pandas DataFrames, one for each chunk of data
+            downloaded from BigQuery.
+
+    Raises:
+        ValueError: If attempting to read from a specific partition or snapshot.
+
+    Note:
+        This method requires the `google-cloud-bigquery-storage` library
+        to be installed.
+    """
 
-    # Passing a BQ Storage client in implies that the BigQuery Storage library
-    # is available and can be imported.
     from google.cloud import bigquery_storage
 
     if "$" in table.table_id:
@@ -837,10 +874,11 @@ def _download_table_bqstorage(
     if "@" in table.table_id:
         raise ValueError("Reading from a specific snapshot is not currently supported.")
 
-    requested_streams = 1 if preserve_order else 0
+    requested_streams = determine_requested_streams(preserve_order, max_stream_count)
 
-    requested_session = bigquery_storage.types.ReadSession(
-        table=table.to_bqstorage(), data_format=bigquery_storage.types.DataFormat.ARROW
+    requested_session = bigquery_storage.types.stream.ReadSession(
+        table=table.to_bqstorage(),
+        data_format=bigquery_storage.types.stream.DataFormat.ARROW,
     )
     if selected_fields is not None:
         for field in selected_fields:
@@ -848,7 +886,8 @@ def _download_table_bqstorage(
 
     if _ARROW_COMPRESSION_SUPPORT:
         requested_session.read_options.arrow_serialization_options.buffer_compression = (
-            ArrowSerializationOptions.CompressionCodec.LZ4_FRAME
+            # CompressionCodec(1) -> LZ4_FRAME
+            ArrowSerializationOptions.CompressionCodec(1)
         )
 
     session = bqstorage_client.create_read_session(
@@ -884,7 +923,7 @@ def _download_table_bqstorage(
     elif max_queue_size is None:
         max_queue_size = 0  # unbounded
 
-    worker_queue = queue.Queue(maxsize=max_queue_size)
+    worker_queue: queue.Queue[int] = queue.Queue(maxsize=max_queue_size)
 
     with concurrent.futures.ThreadPoolExecutor(max_workers=total_streams) as pool:
         try:
@@ -910,7 +949,7 @@ def _download_table_bqstorage(
                 # we want to block on the queue's get method, instead. This
                 # prevents the queue from filling up, because the main thread
                 # has smaller gaps in time between calls to the queue's get
-                # method. For a detailed explaination, see:
+                # method. For a detailed explanation, see:
                 # https://friendliness.dev/2019/06/18/python-nowait/
                 done, not_done = _nowait(not_done)
                 for future in done:
@@ -949,6 +988,7 @@ def download_arrow_bqstorage(
     preserve_order=False,
     selected_fields=None,
     max_queue_size=_MAX_QUEUE_SIZE_DEFAULT,
+    max_stream_count=None,
 ):
     return _download_table_bqstorage(
         project_id,
@@ -958,6 +998,7 @@ def download_arrow_bqstorage(
         selected_fields=selected_fields,
         page_to_item=_bqstorage_page_to_arrow,
         max_queue_size=max_queue_size,
+        max_stream_count=max_stream_count,
     )
 
 
@@ -970,6 +1011,7 @@ def download_dataframe_bqstorage(
     preserve_order=False,
     selected_fields=None,
     max_queue_size=_MAX_QUEUE_SIZE_DEFAULT,
+    max_stream_count=None,
 ):
     page_to_item = functools.partial(_bqstorage_page_to_dataframe, column_names, dtypes)
     return _download_table_bqstorage(
@@ -980,6 +1022,7 @@ def download_dataframe_bqstorage(
         selected_fields=selected_fields,
         page_to_item=page_to_item,
         max_queue_size=max_queue_size,
+        max_stream_count=max_stream_count,
     )
 
 
@@ -1024,3 +1067,40 @@ def verify_pandas_imports():
         raise ValueError(_NO_PANDAS_ERROR) from pandas_import_exception
     if db_dtypes is None:
         raise ValueError(_NO_DB_TYPES_ERROR) from db_dtypes_import_exception
+
+
+def determine_requested_streams(
+    preserve_order: bool,
+    max_stream_count: Union[int, None],
+) -> int:
+    """Determines the value of requested_streams based on the values of
+    `preserve_order` and `max_stream_count`.
+
+    Args:
+        preserve_order (bool): Whether to preserve the order of streams. If True,
+            this limits the number of streams to one. `preserve_order` takes
+            precedence over `max_stream_count`.
+        max_stream_count (Union[int, None]]): The maximum number of streams
+            allowed. Must be a non-negative number or None, where None indicates
+            the value is unset. NOTE: if `preserve_order` is also set, it takes
+            precedence over `max_stream_count`, thus to ensure that `max_stream_count`
+            is used, ensure that `preserve_order` is None.
+
+    Returns:
+        (int) The appropriate value for requested_streams.
+    """
+
+    if preserve_order:
+        # If preserve order is set, it takes precendence.
+        # Limit the requested streams to 1, to ensure that order
+        # is preserved)
+        return 1
+
+    elif max_stream_count is not None:
+        # If preserve_order is not set, only then do we consider max_stream_count
+        if max_stream_count <= -1:
+            raise ValueError("max_stream_count must be non-negative OR None")
+        return max_stream_count
+
+    # Default to zero requested streams (unbounded).
+    return 0

{google_cloud_bigquery-3.26.0 → google_cloud_bigquery-3.28.0}/google/cloud/bigquery/client.py

@@ -44,6 +44,8 @@ from typing import (
 import uuid
 import warnings
 
+import requests
+
 from google import resumable_media  # type: ignore
 from google.resumable_media.requests import MultipartUpload  # type: ignore
 from google.resumable_media.requests import ResumableUpload
@@ -65,6 +67,7 @@ except ImportError:
     DEFAULT_BQSTORAGE_CLIENT_INFO = None  # type: ignore
 
 
+from google.auth.credentials import Credentials
 from google.cloud.bigquery._http import Connection
 from google.cloud.bigquery import _job_helpers
 from google.cloud.bigquery import _pandas_helpers
@@ -126,6 +129,7 @@ pandas = (
     _versions_helpers.PANDAS_VERSIONS.try_import()
 )  # mypy check fails because pandas import is outside module, there are type: ignore comments related to this
 
+
 ResumableTimeoutType = Union[
     None, float, Tuple[float, float]
 ]  # for resumable media methods
@@ -133,8 +137,6 @@ ResumableTimeoutType = Union[
 if typing.TYPE_CHECKING:  # pragma: NO COVER
     # os.PathLike is only subscriptable in Python 3.9+, thus shielding with a condition.
     PathType = Union[str, bytes, os.PathLike[str], os.PathLike[bytes]]
-    import requests  # required by api-core
-
 _DEFAULT_CHUNKSIZE = 100 * 1024 * 1024  # 100 MB
 _MAX_MULTIPART_SIZE = 5 * 1024 * 1024
 _DEFAULT_NUM_RETRIES = 6
@@ -231,15 +233,23 @@ class Client(ClientWithProject):
 
     def __init__(
         self,
-        project=None,
-        credentials=None,
-        _http=None,
-        location=None,
-        default_query_job_config=None,
-        default_load_job_config=None,
-        client_info=None,
-        client_options=None,
+        project: Optional[str] = None,
+        credentials: Optional[Credentials] = None,
+        _http: Optional[requests.Session] = None,
+        location: Optional[str] = None,
+        default_query_job_config: Optional[QueryJobConfig] = None,
+        default_load_job_config: Optional[LoadJobConfig] = None,
+        client_info: Optional[google.api_core.client_info.ClientInfo] = None,
+        client_options: Optional[
+            Union[google.api_core.client_options.ClientOptions, Dict[str, Any]]
+        ] = None,
     ) -> None:
+        if client_options is None:
+            client_options = {}
+        if isinstance(client_options, dict):
+            client_options = google.api_core.client_options.from_dict(client_options)
+        # assert isinstance(client_options, google.api_core.client_options.ClientOptions)
+
         super(Client, self).__init__(
             project=project,
             credentials=credentials,
@@ -247,14 +257,10 @@ class Client(ClientWithProject):
             _http=_http,
         )
 
-        kw_args = {"client_info": client_info}
+        kw_args: Dict[str, Any] = {"client_info": client_info}
         bq_host = _get_bigquery_host()
         kw_args["api_endpoint"] = bq_host if bq_host != _DEFAULT_HOST else None
         client_universe = None
-        if client_options is None:
-            client_options = {}
-        if isinstance(client_options, dict):
-            client_options = google.api_core.client_options.from_dict(client_options)
         if client_options.api_endpoint:
             api_endpoint = client_options.api_endpoint
             kw_args["api_endpoint"] = api_endpoint
@@ -328,6 +334,15 @@ class Client(ClientWithProject):
     ) -> str:
         """Get the email address of the project's BigQuery service account
 
+        Example:
+
+        .. code-block:: python
+
+            from google.cloud import bigquery
+            client = bigquery.Client()
+            client.get_service_account_email()
+            # returns an email similar to: my_service_account@my-project.iam.gserviceaccount.com
+
         Note:
             This is the service account that BigQuery uses to manage tables
             encrypted by a key in KMS.
@@ -345,13 +360,6 @@ class Client(ClientWithProject):
             str:
                 service account email address
 
-        Example:
-
-            >>> from google.cloud import bigquery
-            >>> client = bigquery.Client()
-            >>> client.get_service_account_email()
-            my_service_account@my-project.iam.gserviceaccount.com
-
         """
         if project is None:
             project = self.project
@@ -629,9 +637,19 @@ class Client(ClientWithProject):
     ) -> Dataset:
         """API call: create the dataset via a POST request.
 
+
         See
         https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets/insert
 
+        Example:
+
+        .. code-block:: python
+
+            from google.cloud import bigquery
+            client = bigquery.Client()
+            dataset = bigquery.Dataset('my_project.my_dataset')
+            dataset = client.create_dataset(dataset)
+
         Args:
             dataset (Union[ \
                 google.cloud.bigquery.dataset.Dataset, \
@@ -658,14 +676,6 @@ class Client(ClientWithProject):
         Raises:
             google.cloud.exceptions.Conflict:
                 If the dataset already exists.
-
-        Example:
-
-            >>> from google.cloud import bigquery
-            >>> client = bigquery.Client()
-            >>> dataset = bigquery.Dataset('my_project.my_dataset')
-            >>> dataset = client.create_dataset(dataset)
-
         """
         dataset = self._dataset_from_arg(dataset)
         if isinstance(dataset, DatasetReference):
@@ -1180,6 +1190,19 @@ class Client(ClientWithProject):
         must be provided. If a field is listed in ``fields`` and is ``None`` in
         ``dataset``, it will be deleted.
 
+        For example, to update the default expiration times, specify
+        both properties in the ``fields`` argument:
+
+        .. code-block:: python
+
+            bigquery_client.update_dataset(
+                dataset,
+                [
+                    "default_partition_expiration_ms",
+                    "default_table_expiration_ms",
+                ]
+            )
+
         If ``dataset.etag`` is not ``None``, the update will only
         succeed if the dataset on the server has the same ETag. Thus
         reading a dataset with ``get_dataset``, changing its fields,
@@ -1194,19 +1217,6 @@ class Client(ClientWithProject):
                 The properties of ``dataset`` to change. These are strings
                 corresponding to the properties of
                 :class:`~google.cloud.bigquery.dataset.Dataset`.
-
-                For example, to update the default expiration times, specify
-                both properties in the ``fields`` argument:
-
-                .. code-block:: python
-
-                    bigquery_client.update_dataset(
-                        dataset,
-                        [
-                            "default_partition_expiration_ms",
-                            "default_table_expiration_ms",
-                        ]
-                    )
             retry (Optional[google.api_core.retry.Retry]):
                 How to retry the RPC.
             timeout (Optional[float]):
@@ -1250,6 +1260,15 @@ class Client(ClientWithProject):
         must be provided. If a field is listed in ``fields`` and is ``None``
         in ``model``, the field value will be deleted.
 
+        For example, to update the descriptive properties of the model,
+        specify them in the ``fields`` argument:
+
+        .. code-block:: python
+
+            bigquery_client.update_model(
+                model, ["description", "friendly_name"]
+            )
+
         If ``model.etag`` is not ``None``, the update will only succeed if
         the model on the server has the same ETag. Thus reading a model with
         ``get_model``, changing its fields, and then passing it to
@@ -1262,15 +1281,6 @@ class Client(ClientWithProject):
                 The properties of ``model`` to change. These are strings
                 corresponding to the properties of
                 :class:`~google.cloud.bigquery.model.Model`.
-
-                For example, to update the descriptive properties of the model,
-                specify them in the ``fields`` argument:
-
-                .. code-block:: python
-
-                    bigquery_client.update_model(
-                        model, ["description", "friendly_name"]
-                    )
             retry (Optional[google.api_core.retry.Retry]):
                 A description of how to retry the API call.
             timeout (Optional[float]):
@@ -1314,6 +1324,15 @@ class Client(ClientWithProject):
         must be provided. If a field is listed in ``fields`` and is ``None``
         in ``routine``, the field value will be deleted.
 
+        For example, to update the description property of the routine,
+        specify it in the ``fields`` argument:
+
+        .. code-block:: python
+
+            bigquery_client.update_routine(
+                routine, ["description"]
+            )
+
         .. warning::
            During beta, partial updates are not supported. You must provide
            all fields in the resource.
@@ -1332,15 +1351,6 @@ class Client(ClientWithProject):
             fields (Sequence[str]):
                 The fields of ``routine`` to change, spelled as the
                 :class:`~google.cloud.bigquery.routine.Routine` properties.
-
-                For example, to update the description property of the routine,
-                specify it in the ``fields`` argument:
-
-                .. code-block:: python
-
-                    bigquery_client.update_routine(
-                        routine, ["description"]
-                    )
             retry (Optional[google.api_core.retry.Retry]):
                 A description of how to retry the API call.
             timeout (Optional[float]):
@@ -1388,6 +1398,16 @@ class Client(ClientWithProject):
         must be provided. If a field is listed in ``fields`` and is ``None``
         in ``table``, the field value will be deleted.
 
+        For example, to update the descriptive properties of the table,
+        specify them in the ``fields`` argument:
+
+        .. code-block:: python
+
+            bigquery_client.update_table(
+                table,
+                ["description", "friendly_name"]
+            )
+
         If ``table.etag`` is not ``None``, the update will only succeed if
         the table on the server has the same ETag. Thus reading a table with
         ``get_table``, changing its fields, and then passing it to
@@ -1399,16 +1419,6 @@ class Client(ClientWithProject):
             fields (Sequence[str]):
                 The fields of ``table`` to change, spelled as the
                 :class:`~google.cloud.bigquery.table.Table` properties.
-
-                For example, to update the descriptive properties of the table,
-                specify them in the ``fields`` argument:
-
-                .. code-block:: python
-
-                    bigquery_client.update_table(
-                        table,
-                        ["description", "friendly_name"]
-                    )
             retry (Optional[google.api_core.retry.Retry]):
                 A description of how to retry the API call.
             timeout (Optional[float]):

{google_cloud_bigquery-3.26.0 → google_cloud_bigquery-3.28.0}/google/cloud/bigquery/dataset.py

@@ -27,6 +27,7 @@ from google.cloud.bigquery.model import ModelReference
 from google.cloud.bigquery.routine import Routine, RoutineReference
 from google.cloud.bigquery.table import Table, TableReference
 from google.cloud.bigquery.encryption_configuration import EncryptionConfiguration
+from google.cloud.bigquery import external_config
 
 from typing import Optional, List, Dict, Any, Union
 
@@ -530,6 +531,8 @@ class Dataset(object):
         "storage_billing_model": "storageBillingModel",
         "max_time_travel_hours": "maxTimeTravelHours",
         "default_rounding_mode": "defaultRoundingMode",
+        "resource_tags": "resourceTags",
+        "external_catalog_dataset_options": "externalCatalogDatasetOptions",
     }
 
     def __init__(self, dataset_ref) -> None:
@@ -801,6 +804,28 @@ class Dataset(object):
             raise ValueError("Pass a dict")
         self._properties["labels"] = value
 
+    @property
+    def resource_tags(self):
+        """Dict[str, str]: Resource tags of the dataset.
+
+        Optional. The tags attached to this dataset. Tag keys are globally
+        unique. Tag key is expected to be in the namespaced format, for
+        example "123456789012/environment" where 123456789012 is
+        the ID of the parent organization or project resource for this tag
+        key. Tag value is expected to be the short name, for example
+        "Production".
+
+        Raises:
+            ValueError: for invalid value types.
+        """
+        return self._properties.setdefault("resourceTags", {})
+
+    @resource_tags.setter
+    def resource_tags(self, value):
+        if not isinstance(value, dict) and value is not None:
+            raise ValueError("Pass a dict")
+        self._properties["resourceTags"] = value
+
     @property
     def default_encryption_configuration(self):
         """google.cloud.bigquery.encryption_configuration.EncryptionConfiguration: Custom
@@ -875,6 +900,29 @@ class Dataset(object):
             )
         self._properties["storageBillingModel"] = value
 
+    @property
+    def external_catalog_dataset_options(self):
+        """Options defining open source compatible datasets living in the
+        BigQuery catalog. Contains metadata of open source database, schema
+        or namespace represented by the current dataset."""
+
+        prop = _helpers._get_sub_prop(
+            self._properties, ["externalCatalogDatasetOptions"]
+        )
+
+        if prop is not None:
+            prop = external_config.ExternalCatalogDatasetOptions.from_api_repr(prop)
+        return prop
+
+    @external_catalog_dataset_options.setter
+    def external_catalog_dataset_options(self, value):
+        value = _helpers._isinstance_or_raise(
+            value, external_config.ExternalCatalogDatasetOptions, none_allowed=True
+        )
+        self._properties[
+            self._PROPERTY_TO_API_FIELD["external_catalog_dataset_options"]
+        ] = (value.to_api_repr() if value is not None else None)
+
     @classmethod
     def from_string(cls, full_dataset_id: str) -> "Dataset":
         """Construct a dataset from fully-qualified dataset ID.