google-cloud-bigquery 3.33.0__tar.gz → 3.34.0__tar.gz

{google_cloud_bigquery-3.33.0/google_cloud_bigquery.egg-info → google_cloud_bigquery-3.34.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: google-cloud-bigquery
-Version: 3.33.0
+Version: 3.34.0
 Summary: Google BigQuery API client library
 Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache 2.0

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/_helpers.py

@@ -388,7 +388,7 @@ CELL_DATA_PARSER = CellDataParser()
 
 
 class DataFrameCellDataParser(CellDataParser):
-    """Override of CellDataParser to handle differences in expection of values in DataFrame-like outputs.
+    """Override of CellDataParser to handle differences in expression of values in DataFrame-like outputs.
 
     This is used to turn the output of the REST API into a pyarrow Table,
     emulating the serialized arrow from the BigQuery Storage Read API.

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/_job_helpers.py

@@ -37,7 +37,6 @@ predicates where it is safe to generate a new query ID.
 
 import copy
 import functools
-import os
 import uuid
 import textwrap
 from typing import Any, Dict, Optional, TYPE_CHECKING, Union
@@ -400,12 +399,6 @@ def query_and_wait(
 ) -> table.RowIterator:
     """Run the query, wait for it to finish, and return the results.
 
-    While ``jobCreationMode=JOB_CREATION_OPTIONAL`` is in preview in the
-    ``jobs.query`` REST API, use the default ``jobCreationMode`` unless
-    the environment variable ``QUERY_PREVIEW_ENABLED=true``. After
-    ``jobCreationMode`` is GA, this method will always use
-    ``jobCreationMode=JOB_CREATION_OPTIONAL``. See:
-    https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs/query
 
     Args:
         client:
@@ -500,9 +493,8 @@ def query_and_wait(
         request_body["maxResults"] = min(page_size, max_results)
     elif page_size is not None or max_results is not None:
         request_body["maxResults"] = page_size or max_results
-
-    if os.getenv("QUERY_PREVIEW_ENABLED", "").casefold() == "true":
-        request_body["jobCreationMode"] = "JOB_CREATION_OPTIONAL"
+    if client.default_job_creation_mode:
+        request_body["jobCreationMode"] = client.default_job_creation_mode
 
     def do_query():
         request_body["requestId"] = make_job_id()

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/_pandas_helpers.py

@@ -1144,7 +1144,7 @@ def determine_requested_streams(
     """
 
     if preserve_order:
-        # If preserve order is set, it takes precendence.
+        # If preserve order is set, it takes precedence.
         # Limit the requested streams to 1, to ensure that order
         # is preserved)
         return 1

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/client.py

@@ -221,6 +221,10 @@ class Client(ClientWithProject):
         client_options (Optional[Union[google.api_core.client_options.ClientOptions, Dict]]):
             Client options used to set user options on the client. API Endpoint
             should be set through client_options.
+        default_job_creation_mode (Optional[str]):
+            Sets the default job creation mode used by query methods such as
+            query_and_wait().  For lightweight queries, JOB_CREATION_OPTIONAL is
+            generally recommended.
 
     Raises:
         google.auth.exceptions.DefaultCredentialsError:
@@ -243,6 +247,7 @@ class Client(ClientWithProject):
         client_options: Optional[
             Union[google.api_core.client_options.ClientOptions, Dict[str, Any]]
         ] = None,
+        default_job_creation_mode: Optional[str] = None,
     ) -> None:
         if client_options is None:
             client_options = {}
@@ -277,6 +282,7 @@ class Client(ClientWithProject):
         self._connection = Connection(self, **kw_args)
         self._location = location
         self._default_load_job_config = copy.deepcopy(default_load_job_config)
+        self.default_job_creation_mode = default_job_creation_mode
 
         # Use property setter so validation can run.
         self.default_query_job_config = default_query_job_config
@@ -286,6 +292,15 @@ class Client(ClientWithProject):
         """Default location for jobs / datasets / tables."""
         return self._location
 
+    @property
+    def default_job_creation_mode(self):
+        """Default job creation mode used for query execution."""
+        return self._default_job_creation_mode
+
+    @default_job_creation_mode.setter
+    def default_job_creation_mode(self, value: Optional[str]):
+        self._default_job_creation_mode = value
+
     @property
     def default_query_job_config(self) -> Optional[QueryJobConfig]:
         """Default ``QueryJobConfig`` or ``None``.
@@ -3532,13 +3547,6 @@ class Client(ClientWithProject):
     ) -> RowIterator:
         """Run the query, wait for it to finish, and return the results.
 
-        While ``jobCreationMode=JOB_CREATION_OPTIONAL`` is in preview in the
-        ``jobs.query`` REST API, use the default ``jobCreationMode`` unless
-        the environment variable ``QUERY_PREVIEW_ENABLED=true``. After
-        ``jobCreationMode`` is GA, this method will always use
-        ``jobCreationMode=JOB_CREATION_OPTIONAL``. See:
-        https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs/query
-
         Args:
             query (str):
                 SQL query to be executed. Defaults to the standard SQL
@@ -4134,7 +4142,7 @@ class Client(ClientWithProject):
                 rows that were affected.
             query (Optional[str]):
                 The query text used.
-            total_bytes_processed (Optinal[int]):
+            total_bytes_processed (Optional[int]):
                 total bytes processed from job statistics, if present.
 
         Returns:

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/enums.py

@@ -407,3 +407,22 @@ class BigLakeTableFormat(object):
 
     ICEBERG = "ICEBERG"
     """Apache Iceberg format."""
+
+
+class JobCreationMode(object):
+    """Documented values for Job Creation Mode."""
+
+    JOB_CREATION_MODE_UNSPECIFIED = "JOB_CREATION_MODE_UNSPECIFIED"
+    """Job creation mode is unspecified."""
+
+    JOB_CREATION_REQUIRED = "JOB_CREATION_REQUIRED"
+    """Job creation is always required."""
+
+    JOB_CREATION_OPTIONAL = "JOB_CREATION_OPTIONAL"
+    """Job creation is optional.
+
+    Returning immediate results is prioritized.
+    BigQuery will automatically determine if a Job needs to be created.
+    The conditions under which BigQuery can decide to not create a Job are
+    subject to change.
+    """

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/job/query.py

@@ -1529,7 +1529,7 @@ class QueryJob(_AsyncJob):
                 a DDL query, an ``_EmptyRowIterator`` instance is returned.
 
         Raises:
-            google.cloud.exceptions.GoogleAPICallError:
+            google.api_core.exceptions.GoogleAPICallError:
                 If the job failed and retries aren't successful.
             concurrent.futures.TimeoutError:
                 If the job did not complete in the given timeout.

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/table.py

@@ -44,7 +44,7 @@ try:
     import geopandas  # type: ignore
 except ImportError:
     geopandas = None
-else:
+finally:
     _COORDINATE_REFERENCE_SYSTEM = "EPSG:4326"
 
 try:
@@ -1786,7 +1786,7 @@ class RowIterator(HTTPIterator):
             the first page is requested.
         query (Optional[str]):
             The query text used.
-        total_bytes_processed (Optinal[int]):
+        total_bytes_processed (Optional[int]):
             total bytes processed from job statistics, if present.
     """
 

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/google/cloud/bigquery/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "3.33.0"
+__version__ = "3.34.0"

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0/google_cloud_bigquery.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: google-cloud-bigquery
-Version: 3.33.0
+Version: 3.34.0
 Summary: Google BigQuery API client library
 Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache 2.0

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test__job_helpers.py

@@ -554,13 +554,9 @@ def test_query_and_wait_retries_job_times_out():
     )
 
 
-def test_query_and_wait_sets_job_creation_mode(monkeypatch: pytest.MonkeyPatch):
-    monkeypatch.setenv(
-        "QUERY_PREVIEW_ENABLED",
-        # The comparison should be case insensitive.
-        "TrUe",
-    )
+def test_query_and_wait_sets_job_creation_mode():
     client = mock.create_autospec(Client)
+    client.default_job_creation_mode = "JOB_CREATION_OPTIONAL"
     client._call_api.return_value = {
         "jobReference": {
             "projectId": "response-project",
@@ -642,6 +638,7 @@ def test_query_and_wait_sets_location():
                 "useInt64Timestamp": True,
             },
             "requestId": mock.ANY,
+            "jobCreationMode": mock.ANY,
         },
         timeout=None,
     )
@@ -658,6 +655,7 @@ def test_query_and_wait_sets_location():
 )
 def test_query_and_wait_sets_max_results(max_results, page_size, expected):
     client = mock.create_autospec(Client)
+    client.default_job_creation_mode = None
     client._call_api.return_value = {
         "jobReference": {
             "projectId": "response-project",
@@ -703,6 +701,7 @@ def test_query_and_wait_sets_max_results(max_results, page_size, expected):
 
 def test_query_and_wait_caches_completed_query_results_one_page():
     client = mock.create_autospec(Client)
+    client.default_job_creation_mode = None
     client._call_api.return_value = {
         "jobReference": {
             "projectId": "response-project",
@@ -768,6 +767,7 @@ def test_query_and_wait_caches_completed_query_results_one_page():
 
 def test_query_and_wait_caches_completed_query_results_one_page_no_rows():
     client = mock.create_autospec(Client)
+    client.default_job_creation_mode = None
     client._call_api.return_value = {
         "jobReference": {
             "projectId": "response-project",

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test__pandas_helpers.py

@@ -1856,6 +1856,7 @@ def test__download_table_bqstorage_shuts_down_workers(
     Make sure that when the top-level iterator goes out of scope (is deleted),
     the child threads are also stopped.
     """
+    pytest.importorskip("google.cloud.bigquery_storage_v1")
     from google.cloud.bigquery import dataset
     from google.cloud.bigquery import table
     import google.cloud.bigquery_storage_v1.reader

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test__pyarrow_helpers.py

@@ -14,7 +14,7 @@
 
 import pytest
 
-
+numpy = pytest.importorskip("numpy")
 pyarrow = pytest.importorskip("pyarrow", minversion="3.0.0")
 
 

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test_client.py

@@ -213,6 +213,17 @@ class TestClient(unittest.TestCase):
         )
         self.assertEqual(client._connection.API_BASE_URL, "https://bigquery.foo.com")
 
+    def test_ctor_w_job_creation_mode(self):
+        creds = _make_credentials()
+        http = object()
+        client = self._make_one(
+            project=self.PROJECT,
+            credentials=creds,
+            _http=http,
+            default_job_creation_mode="foo",
+        )
+        self.assertEqual(client.default_job_creation_mode, "foo")
+
     def test_ctor_w_location(self):
         from google.cloud.bigquery._http import Connection
 

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test_dbapi__helpers.py

@@ -210,6 +210,7 @@ class TestToBqTableRows(unittest.TestCase):
         self.assertEqual(list(result), [])
 
     def test_non_empty_iterable(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pyarrow")
         from tests.unit.helpers import _to_pyarrow
 

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test_magics.py

@@ -1276,6 +1276,11 @@ def test_bigquery_magic_with_no_query_cache(monkeypatch):
     bigquery.load_ipython_extension(ip)
     conn = make_connection()
     monkeypatch.setattr(magics.context, "_connection", conn)
+    monkeypatch.setattr(
+        magics.context,
+        "credentials",
+        mock.create_autospec(google.auth.credentials.Credentials, instance=True),
+    )
     monkeypatch.setattr(magics.context, "project", "project-from-context")
 
     # --no_query_cache option should override context.

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test_table.py

@@ -2416,6 +2416,7 @@ class Test_EmptyRowIterator(unittest.TestCase):
             row_iterator.to_arrow()
 
     def test_to_arrow(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip("pyarrow")
         row_iterator = self._make_one()
         tbl = row_iterator.to_arrow()
@@ -2423,6 +2424,7 @@ class Test_EmptyRowIterator(unittest.TestCase):
         self.assertEqual(tbl.num_rows, 0)
 
     def test_to_arrow_iterable(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3089,6 +3091,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_not_called()
 
     def test_to_arrow(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3173,6 +3176,7 @@ class TestRowIterator(unittest.TestCase):
         )
 
     def test_to_arrow_w_nulls(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3209,6 +3213,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertEqual(ages, [32, 29, None, 111])
 
     def test_to_arrow_w_unknown_type(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3254,6 +3259,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertTrue(all("sport" in str(warning) for warning in warned))
 
     def test_to_arrow_w_empty_table(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3295,6 +3301,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertEqual(child_field.type.value_type[1].name, "age")
 
     def test_to_arrow_max_results_w_explicit_bqstorage_client_warning(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery.schema import SchemaField
@@ -3337,6 +3344,7 @@ class TestRowIterator(unittest.TestCase):
         mock_client._ensure_bqstorage_client.assert_not_called()
 
     def test_to_arrow_max_results_w_create_bqstorage_client_no_warning(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery.schema import SchemaField
@@ -3375,6 +3383,7 @@ class TestRowIterator(unittest.TestCase):
         mock_client._ensure_bqstorage_client.assert_not_called()
 
     def test_to_arrow_w_bqstorage(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -3458,6 +3467,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_not_called()
 
     def test_to_arrow_w_bqstorage_creates_client(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -3491,6 +3501,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_called_once()
 
     def test_to_arrow_ensure_bqstorage_client_wo_bqstorage(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip(
             "pyarrow", minversion=self.PYARROW_MINIMUM_VERSION
         )
@@ -3524,6 +3535,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertEqual(tbl.num_rows, 2)
 
     def test_to_arrow_w_bqstorage_no_streams(self):
+        pytest.importorskip("numpy")
         pyarrow = pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -3563,6 +3575,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertEqual(actual_table.schema[2].name, "colB")
 
     def test_to_arrow_progress_bar(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pyarrow")
         pytest.importorskip("tqdm")
         pytest.importorskip("tqdm.notebook")
@@ -3696,6 +3709,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertEqual(df_2["age"][0], 33)
 
     def test_to_dataframe_iterable_w_bqstorage(self):
+        pytest.importorskip("numpy")
         pandas = pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
         pytest.importorskip("google.cloud.bigquery_storage")
@@ -3770,6 +3784,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_not_called()
 
     def test_to_dataframe_iterable_w_bqstorage_max_results_warning(self):
+        pytest.importorskip("numpy")
         pandas = pytest.importorskip("pandas")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -4513,7 +4528,7 @@ class TestRowIterator(unittest.TestCase):
 
     def test_to_dataframe_w_unsupported_dtypes_mapper(self):
         pytest.importorskip("pandas")
-        import numpy
+        numpy = pytest.importorskip("numpy")
         from google.cloud.bigquery.schema import SchemaField
 
         schema = [
@@ -4797,6 +4812,7 @@ class TestRowIterator(unittest.TestCase):
         mock_client._ensure_bqstorage_client.assert_not_called()
 
     def test_to_dataframe_w_bqstorage_creates_client(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pandas")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -4830,6 +4846,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_called_once()
 
     def test_to_dataframe_w_bqstorage_no_streams(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("pandas")
         pytest.importorskip("google.cloud.bigquery_storage")
         from google.cloud.bigquery import schema
@@ -4858,6 +4875,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertTrue(got.empty)
 
     def test_to_dataframe_w_bqstorage_logs_session(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pytest.importorskip("pyarrow")
@@ -4882,6 +4900,7 @@ class TestRowIterator(unittest.TestCase):
         )
 
     def test_to_dataframe_w_bqstorage_empty_streams(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -4936,6 +4955,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertTrue(got.empty)
 
     def test_to_dataframe_w_bqstorage_nonempty(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -5018,6 +5038,7 @@ class TestRowIterator(unittest.TestCase):
         bqstorage_client._transport.grpc_channel.close.assert_not_called()
 
     def test_to_dataframe_w_bqstorage_multiple_streams_return_unique_index(self):
+        pytest.importorskip("numpy")
         bigquery_storage = pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -5070,6 +5091,7 @@ class TestRowIterator(unittest.TestCase):
         self.assertTrue(got.index.is_unique)
 
     def test_to_dataframe_w_bqstorage_updates_progress_bar(self):
+        pytest.importorskip("numpy")
         bigquery_storage = pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -5147,6 +5169,7 @@ class TestRowIterator(unittest.TestCase):
             tqdm_mock().close.assert_called_once()
 
     def test_to_dataframe_w_bqstorage_exits_on_keyboardinterrupt(self):
+        pytest.importorskip("numpy")
         bigquery_storage = pytest.importorskip("google.cloud.bigquery_storage")
         pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -5322,6 +5345,7 @@ class TestRowIterator(unittest.TestCase):
             row_iterator.to_dataframe(bqstorage_client)
 
     def test_to_dataframe_concat_categorical_dtype_w_pyarrow(self):
+        pytest.importorskip("numpy")
         pytest.importorskip("google.cloud.bigquery_storage")
         pandas = pytest.importorskip("pandas")
         pyarrow = pytest.importorskip("pyarrow")
@@ -5604,7 +5628,7 @@ class TestRowIterator(unittest.TestCase):
         """
         pandas = pytest.importorskip("pandas")
         geopandas = pytest.importorskip("geopandas")
-        import numpy
+        numpy = pytest.importorskip("numpy")
         from shapely import wkt
 
         row_iterator = self._make_one_from_data(

{google_cloud_bigquery-3.33.0 → google_cloud_bigquery-3.34.0}/tests/unit/test_table_arrow.py

@@ -18,7 +18,8 @@ from google.cloud import bigquery
 import google.cloud.bigquery.table
 
 
-pyarrow = pytest.importorskip("pyarrow", minversion="3.0.0")
+pytest.importorskip("numpy")
+pytest.importorskip("pyarrow", minversion="3.0.0")
 
 
 def test_to_arrow_with_jobs_query_response():