chore: sync v3 with master (#851)

(no issue)

Just a regular update of the `v3` branch.

Author: plamut

.github/CODEOWNERS

@@ -8,4 +8,4 @@
 *               @googleapis/api-bigquery @googleapis/yoshi-python
 
 # The python-samples-reviewers team is the default owner for samples changes
-/samples/   @googleapis/python-samples-owners
+/samples/   @googleapis/api-bigquery @googleapis/python-samples-owners

.github/sync-repo-settings.yaml

@@ -3,7 +3,20 @@
 branchProtectionRules:
 # Identifies the protection rule pattern. Name of the branch to be protected.
 # Defaults to `master`
-- pattern: '{master,v3}'
+- pattern: master
+  requiresCodeOwnerReviews: true
+  requiresStrictStatusChecks: true
+  requiredStatusCheckContexts:
+    - 'Kokoro'
+    - 'Kokoro snippets-3.8'
+    - 'cla/google'
+    - 'Samples - Lint'
+    - 'Samples - Python 3.6'
+    - 'Samples - Python 3.7'
+    - 'Samples - Python 3.8'
+- pattern: v3
+  requiresCodeOwnerReviews: true
+  requiresStrictStatusChecks: true
   requiredStatusCheckContexts:
     - 'Kokoro'
     - 'Kokoro snippets-3.8'

CHANGELOG.md

@@ -5,6 +5,20 @@
 [1]: https://pypi.org/project/google-cloud-bigquery/#history
 
 
+### [2.23.2](https://www.github.com/googleapis/python-bigquery/compare/v2.23.1...v2.23.2) (2021-07-29)
+
+
+### Dependencies
+
+* expand pyarrow pins to support 5.x releases ([#833](https://www.github.com/googleapis/python-bigquery/issues/833)) ([80e3a61](https://www.github.com/googleapis/python-bigquery/commit/80e3a61c60419fb19b70b664c6415cd01ba82f5b))
+
+### [2.23.1](https://www.github.com/googleapis/python-bigquery/compare/v2.23.0...v2.23.1) (2021-07-28)
+
+
+### Bug Fixes
+
+* `insert_rows()` accepts float column values as strings again ([#824](https://www.github.com/googleapis/python-bigquery/issues/824)) ([d9378af](https://www.github.com/googleapis/python-bigquery/commit/d9378af13add879118a1d004529b811f72c325d6))
+
 ## [2.23.0](https://www.github.com/googleapis/python-bigquery/compare/v2.22.1...v2.23.0) (2021-07-27)
 
 

google/cloud/bigquery/_helpers.py

@@ -19,6 +19,7 @@
 import decimal
 import math
 import re
+from typing import Union
 
 from google.cloud._helpers import UTC
 from google.cloud._helpers import _date_from_iso8601_date
@@ -312,14 +313,15 @@ def _int_to_json(value):
     return value
 
 
-def _float_to_json(value):
+def _float_to_json(value) -> Union[None, str, float]:
     """Coerce 'value' to an JSON-compatible representation."""
     if value is None:
         return None
-    elif math.isnan(value) or math.isinf(value):
-        return str(value)
-    else:
-        return float(value)
+
+    if isinstance(value, str):
+        value = float(value)
+
+    return str(value) if (math.isnan(value) or math.isinf(value)) else float(value)
 
 
 def _decimal_to_json(value):

google/cloud/bigquery/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "2.23.0"
+__version__ = "2.23.2"

samples/geography/requirements.txt

@@ -1,4 +1,4 @@
 geojson==2.5.0
-google-cloud-bigquery==2.22.1
-google-cloud-bigquery-storage==2.6.0
+google-cloud-bigquery==2.23.2
+google-cloud-bigquery-storage==2.6.2
 Shapely==1.7.1

samples/snippets/requirements-test.txt

@@ -1,3 +1,3 @@
-google-cloud-testutils==0.3.0
+google-cloud-testutils==1.0.0
 pytest==6.2.4
 mock==4.0.3

samples/snippets/requirements.txt

@@ -1,12 +1,12 @@
-google-cloud-bigquery==2.22.1
-google-cloud-bigquery-storage==2.6.0
-google-auth-oauthlib==0.4.4
+google-cloud-bigquery==2.23.2
+google-cloud-bigquery-storage==2.6.2
+google-auth-oauthlib==0.4.5
 grpcio==1.39.0
 ipython==7.16.1; python_version < '3.7'
 ipython==7.17.0; 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==1.2.0; python_version >= '3.7'
-pyarrow==4.0.1
+pyarrow==5.0.0
 pytz==2021.1

setup.py

@@ -43,7 +43,7 @@
     "google-resumable-media >= 0.6.0, < 3.0dev",
     "packaging >= 14.3",
     "protobuf >= 3.12.0",
-    "pyarrow >= 3.0.0, < 5.0dev",
+    "pyarrow >= 3.0.0, < 6.0dev",
     "requests >= 2.18.0, < 3.0.0dev",
 ]
 extras = {

tests/system/test_pandas.py

@@ -21,6 +21,7 @@
 import io
 import operator
 
+import google.api_core.retry
 import pkg_resources
 import pytest
 import pytz
@@ -37,6 +38,10 @@
 PANDAS_INT64_VERSION = pkg_resources.parse_version("1.0.0")
 
 
+class MissingDataError(Exception):
+    pass
+
+
 def test_load_table_from_dataframe_w_automatic_schema(bigquery_client, dataset_id):
     """Test that a DataFrame with dtypes that map well to BigQuery types
     can be uploaded without specifying a schema.
@@ -657,27 +662,34 @@ def test_insert_rows_from_dataframe(bigquery_client, dataset_id):
     )
     for errors in chunk_errors:
         assert not errors
-
-    # Use query to fetch rows instead of listing directly from the table so
-    # that we get values from the streaming buffer.
-    rows = list(
-        bigquery_client.query(
-            "SELECT * FROM `{}.{}.{}`".format(
-                table.project, table.dataset_id, table.table_id
-            )
-        )
-    )
-
-    sorted_rows = sorted(rows, key=operator.attrgetter("int_col"))
-    row_tuples = [r.values() for r in sorted_rows]
     expected = [
         # Pandas often represents NULL values as NaN. Convert to None for
         # easier comparison.
         tuple(None if col != col else col for col in data_row)
         for data_row in dataframe.itertuples(index=False)
     ]
 
-    assert len(row_tuples) == len(expected)
+    # Use query to fetch rows instead of listing directly from the table so
+    # that we get values from the streaming buffer "within a few seconds".
+    # https://cloud.google.com/bigquery/streaming-data-into-bigquery#dataavailability
+    @google.api_core.retry.Retry(
+        predicate=google.api_core.retry.if_exception_type(MissingDataError)
+    )
+    def get_rows():
+        rows = list(
+            bigquery_client.query(
+                "SELECT * FROM `{}.{}.{}`".format(
+                    table.project, table.dataset_id, table.table_id
+                )
+            )
+        )
+        if len(rows) != len(expected):
+            raise MissingDataError()
+        return rows
+
+    rows = get_rows()
+    sorted_rows = sorted(rows, key=operator.attrgetter("int_col"))
+    row_tuples = [r.values() for r in sorted_rows]
 
     for row, expected_row in zip(row_tuples, expected):
         assert (