Fixup string concatenations (#19099)

.pre-commit-config.yaml

@@ -563,7 +563,7 @@ repos:
         additional_dependencies:
           - 'PyYAML==5.3.1'
           - 'jsonschema==3.2.0'
-          - 'tabulate==0.8.7'
+          - 'tabulate==0.8.8'
           - 'jsonpath-ng==1.5.3'
           - 'rich==10.9.0'
       - id: mermaid

airflow/models/dagcode.py

@@ -94,10 +94,11 @@ def bulk_sync_to_db(cls, filelocs: Iterable[str], session=None):
             hashes_to_filelocs = {DagCode.dag_fileloc_hash(fileloc): fileloc for fileloc in filelocs}
             message = ""
             for fileloc in conflicting_filelocs:
+                filename = hashes_to_filelocs[DagCode.dag_fileloc_hash(fileloc)]
                 message += (
-                    "Filename '{}' causes a hash collision in the "
-                    + "database with '{}'. Please rename the file."
-                ).format(hashes_to_filelocs[DagCode.dag_fileloc_hash(fileloc)], fileloc)
+                    f"Filename '{filename}' causes a hash collision in the "
+                    f"database with '{fileloc}'. Please rename the file."
+                )
             raise AirflowException(message)
 
         existing_filelocs = {dag_code.fileloc for dag_code in existing_orm_dag_codes}

airflow/models/taskinstance.py

@@ -1267,8 +1267,8 @@ def _date_or_empty(self, attr: str):
     def _log_state(self, lead_msg: str = ''):
         self.log.info(
             '%sMarking task as %s.'
-            + ' dag_id=%s, task_id=%s,'
-            + ' execution_date=%s, start_date=%s, end_date=%s',
+            ' dag_id=%s, task_id=%s,'
+            ' execution_date=%s, start_date=%s, end_date=%s',
             lead_msg,
             self.state.upper(),
             self.dag_id,

airflow/operators/google_api_to_s3_transfer.py

@@ -40,10 +40,10 @@ class GoogleApiToS3Transfer(GoogleApiToS3Operator):
 
     def __init__(self, **kwargs):
         warnings.warn(
-            """This class is deprecated.
-            Please use
-            `airflow.providers.amazon.aws.transfers."""
-            + "google_api_to_s3_transfer.GoogleApiToS3Operator`.",
+            "This class is deprecated. "
+            "Please use "
+            "`airflow.providers.amazon.aws.transfers."
+            "google_api_to_s3_transfer.GoogleApiToS3Operator`.",
             DeprecationWarning,
             stacklevel=3,
         )

airflow/providers/alibaba/cloud/sensors/oss_key.py

@@ -76,8 +76,8 @@ def poke(self, context):
             if parsed_url.scheme != '' or parsed_url.netloc != '':
                 raise AirflowException(
                     'If bucket_name is provided, bucket_key'
-                    + ' should be relative path from root'
-                    + ' level, rather than a full oss:// url'
+                    ' should be relative path from root'
+                    ' level, rather than a full oss:// url'
                 )
 
         self.log.info('Poking for key : oss://%s/%s', self.bucket_name, self.bucket_key)

airflow/providers/amazon/aws/hooks/s3.py

@@ -716,8 +716,8 @@ def copy_object(
             if parsed_url.scheme != '' or parsed_url.netloc != '':
                 raise AirflowException(
                     'If dest_bucket_name is provided, '
-                    + 'dest_bucket_key should be relative path '
-                    + 'from root level, rather than a full s3:// url'
+                    'dest_bucket_key should be relative path '
+                    'from root level, rather than a full s3:// url'
                 )
 
         if source_bucket_name is None:
@@ -727,8 +727,8 @@ def copy_object(
             if parsed_url.scheme != '' or parsed_url.netloc != '':
                 raise AirflowException(
                     'If source_bucket_name is provided, '
-                    + 'source_bucket_key should be relative path '
-                    + 'from root level, rather than a full s3:// url'
+                    'source_bucket_key should be relative path '
+                    'from root level, rather than a full s3:// url'
                 )
 
         copy_source = {'Bucket': source_bucket_name, 'Key': source_bucket_key, 'VersionId': source_version_id}

airflow/providers/amazon/aws/sensors/s3_key.py

@@ -89,8 +89,8 @@ def poke(self, context):
             if parsed_url.scheme != '' or parsed_url.netloc != '':
                 raise AirflowException(
                     'If bucket_name is provided, bucket_key'
-                    + ' should be relative path from root'
-                    + ' level, rather than a full s3:// url'
+                    ' should be relative path from root'
+                    ' level, rather than a full s3:// url'
                 )
 
         self.log.info('Poking for key : s3://%s/%s', self.bucket_name, self.bucket_key)

airflow/providers/databricks/hooks/databricks.py

@@ -216,7 +216,7 @@ def _do_api_call(self, endpoint_info, json):
 
             if attempt_num == self.retry_limit:
                 raise AirflowException(
-                    ('API requests to Databricks failed {} times. ' + 'Giving up.').format(self.retry_limit)
+                    f'API requests to Databricks failed {self.retry_limit} times. Giving up.'
                 )
 
             attempt_num += 1

airflow/providers/docker/example_dags/example_docker_copy_data.py

@@ -75,7 +75,7 @@
         "/bin/bash",
         "-c",
         "/bin/sleep 30; "
-        "/bin/mv {{ params.source_location }}/" + f"{t_view.output}" + " {{ params.target_location }};"
+        "/bin/mv {{ params.source_location }}/" + str(t_view.output) + " {{ params.target_location }};"
         "/bin/echo '{{ params.target_location }}/" + f"{t_view.output}';",
     ],
     task_id="move_data",

airflow/providers/yandex/hooks/yandex.py

@@ -119,7 +119,7 @@ def _get_credentials(self) -> Dict[str, Any]:
         if not (service_account_json or oauth_token or service_account_json_path):
             raise AirflowException(
                 'No credentials are found in connection. Specify either service account '
-                + 'authentication JSON or user OAuth token in Yandex.Cloud connection'
+                'authentication JSON or user OAuth token in Yandex.Cloud connection'
             )
         if service_account_json_path:
             with open(service_account_json_path) as infile:

airflow/sensors/smart_sensor.py

@@ -125,7 +125,7 @@ def _get_sensor_logger(self, si):
         log_id = "-".join(
             [si.dag_id, si.task_id, si.execution_date.strftime("%Y_%m_%dT%H_%M_%S_%f"), str(si.try_number)]
         )
-        logger = logging.getLogger('airflow.task' + '.' + log_id)
+        logger = logging.getLogger(f'airflow.task.{log_id}')
 
         if len(logger.handlers) == 0:
             handler = self.create_new_task_handler()

dev/provider_packages/prepare_provider_packages.py

@@ -1238,7 +1238,7 @@ def validate_provider_info_with_runtime_schema(provider_info: Dict[str, Any]) ->
         console.print("[red]Provider info not validated against runtime schema[/]")
         raise Exception(
             "Error when validating schema. The schema must be compatible with "
-            + "airflow/provider_info.schema.json.",
+            "airflow/provider_info.schema.json.",
             ex,
         )
 

scripts/ci/pre_commit/pre_commit_check_extras_have_providers.py

@@ -71,7 +71,7 @@ def check_all_providers_are_listed_in_setup_py() -> None:
         if provider_name not in ALL_PROVIDERS:
             errors.append(
                 f"The provider {provider_name} is missing in setup.py "
-                + "[bold]PROVIDERS_REQUIREMENTS[/]: [red]NOK[/]"
+                "[bold]PROVIDERS_REQUIREMENTS[/]: [red]NOK[/]"
             )
 
 

tests/providers/amazon/aws/utils/eks_test_constants.py

@@ -187,49 +187,52 @@ class PageCount:
 
 
 FARGATE_PROFILE_UUID_PATTERN: str = (
-    "(?P<fargate_uuid>[-0-9a-z]{8}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{12})"
+    r"(?P<fargate_uuid>[-0-9a-z]{8}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{12})"
 )
 NODEGROUP_UUID_PATTERN: str = (
-    "(?P<nodegroup_uuid>[-0-9a-z]{8}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{12})"
+    r"(?P<nodegroup_uuid>[-0-9a-z]{8}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{4}-[-0-9a-z]{12})"
 )
 
 
 class RegExTemplates:
     """The compiled RegEx patterns used in testing."""
 
     CLUSTER_ARN: Pattern = re.compile(
-        "arn:"
-        + "(?P<partition>.+):"
-        + "eks:"
-        + "(?P<region>[-0-9a-zA-Z]+):"
-        + "(?P<account_id>[0-9]{12}):"
-        + "cluster/"
-        + "(?P<cluster_name>.+)"
+        r"""arn:
+        (?P<partition>.+):
+        eks:
+        (?P<region>[-0-9a-zA-Z]+):
+        (?P<account_id>[0-9]{12}):
+        cluster/
+        (?P<cluster_name>.+)""",
+        re.VERBOSE,
     )
     FARGATE_PROFILE_ARN: Pattern = re.compile(
-        "arn:"
-        + "(?P<partition>.+):"
-        + "eks:"
-        + "(?P<region>[-0-9a-zA-Z]+):"
-        + "(?P<account_id>[0-9]{12}):"
-        + "fargateprofile/"
-        + "(?P<cluster_name>.+)/"
-        + "(?P<fargate_name>.+)/"
-        + FARGATE_PROFILE_UUID_PATTERN
+        r"""arn:
+        (?P<partition>.+):
+        eks:
+        (?P<region>[-0-9a-zA-Z]+):
+        (?P<account_id>[0-9]{12}):
+        fargateprofile/
+        (?P<cluster_name>.+)/
+        (?P<fargate_name>.+)/"""
+        + FARGATE_PROFILE_UUID_PATTERN,
+        re.VERBOSE,
     )
     NODEGROUP_ARN: Pattern = re.compile(
-        "arn:"
-        + "(?P<partition>.+):"
-        + "eks:"
-        + "(?P<region>[-0-9a-zA-Z]+):"
-        + "(?P<account_id>[0-9]{12}):"
-        + "nodegroup/"
-        + "(?P<cluster_name>.+)/"
-        + "(?P<nodegroup_name>.+)/"
-        + NODEGROUP_UUID_PATTERN
+        r"""arn:
+        (?P<partition>.+):
+        eks:
+        (?P<region>[-0-9a-zA-Z]+):
+        (?P<account_id>[0-9]{12}):
+        nodegroup/
+        (?P<cluster_name>.+)/
+        (?P<nodegroup_name>.+)/"""
+        + NODEGROUP_UUID_PATTERN,
+        re.VERBOSE,
     )
-    NODEGROUP_ASG_NAME_PATTERN: Pattern = re.compile("eks-" + NODEGROUP_UUID_PATTERN)
-    NODEGROUP_SECURITY_GROUP_NAME_PATTERN: Pattern = re.compile("sg-" + "([-0-9a-z]{17})")
+    NODEGROUP_ASG_NAME_PATTERN: Pattern = re.compile(f"eks-{NODEGROUP_UUID_PATTERN}")
+    NODEGROUP_SECURITY_GROUP_NAME_PATTERN: Pattern = re.compile(r"sg-([-0-9a-z]{17})")
 
 
 class MethodNames:

tests/providers/apache/hive/operators/test_hive_stats.py

@@ -308,17 +308,19 @@ def test_runs_for_hive_stats(self, mock_hive_metastore_hook):
                 op.run(start_date=DEFAULT_DATE, end_date=DEFAULT_DATE, ignore_ti_state=True)
 
         select_count_query = (
-            "SELECT COUNT(*) AS __count FROM airflow."
-            + "static_babynames_partitioned WHERE ds = '2015-01-01';"
+            "SELECT COUNT(*) AS __count "
+            "FROM airflow.static_babynames_partitioned "
+            "WHERE ds = '2015-01-01';"
         )
         mock_presto_hook.get_first.assert_called_with(hql=select_count_query)
 
         expected_stats_select_query = (
-            "SELECT 1 FROM hive_stats WHERE table_name='airflow."
-            + "static_babynames_partitioned' AND "
-            + "partition_repr='{\"ds\": \"2015-01-01\"}' AND "
-            + "dttm='2015-01-01T00:00:00+00:00' "
-            + "LIMIT 1;"
+            "SELECT 1 "
+            "FROM hive_stats "
+            "WHERE table_name='airflow.static_babynames_partitioned' "
+            "  AND partition_repr='{\"ds\": \"2015-01-01\"}' "
+            "  AND dttm='2015-01-01T00:00:00+00:00' "
+            "LIMIT 1;"
         )
 
         raw_stats_select_query = mock_mysql_hook.get_records.call_args_list[0][0][0]