[pre-commit.ci] pre-commit autoupdate (#2115)

<!--pre-commit.ci start-->
updates:
- [github.com/psf/black: 23.12.1 →
24.1.1](psf/black@23.12.1...24.1.1)
- [github.com/astral-sh/ruff-pre-commit: v0.1.14 →
v0.2.0](astral-sh/ruff-pre-commit@v0.1.14...v0.2.0)
<!--pre-commit.ci end-->

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

.pre-commit-config.yaml

@@ -55,7 +55,7 @@ repos:
         exclude: ^python-sdk/mk/|^python-sdk/docs/Makefile|^python-sdk/Makefile$|^python-sdk/tests/benchmark/Makefile$
 
   - repo: https://github.com/psf/black
-    rev: 23.12.1
+    rev: 24.1.1
     hooks:
       - id: black
         args: ["--config", "./python-sdk/pyproject.toml"]
@@ -68,7 +68,7 @@ repos:
         additional_dependencies: [black>=22.10.0]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.1.14'
+    rev: 'v0.2.0'
     hooks:
       - id: ruff
         args:

python-sdk/dev/integration_test_scripts/get_latest_runtime_image_tag.py

@@ -1,4 +1,5 @@
 """This script fetches the latest runtime image tag from the provided Quay.io repository URL."""
+
 from __future__ import annotations
 
 import sys

python-sdk/dev/scripts/integration_test_scripts/replace_dependencies.py

@@ -60,9 +60,11 @@ def parse_providers_release_testing_gh_issue(issue_url: str) -> list[str]:
     h2_titles = first_comment.find_all("h2")
     package_urls = [_parse_pypi_url_from_h2_title(h2_title) for h2_title in h2_titles]
     pinned_packages = [
-        _parse_pinned_package_from_pypi_url(url)
-        if "apache-airflow-providers-cncf-kubernetes" not in url
-        else _parse_pinned_pacakge_from_cncf(url)
+        (
+            _parse_pinned_package_from_pypi_url(url)
+            if "apache-airflow-providers-cncf-kubernetes" not in url
+            else _parse_pinned_pacakge_from_cncf(url)
+        )
         for url in package_urls
     ]
     return pinned_packages

python-sdk/example_dags/example_bigquery_dynamic_map_task.py

@@ -6,6 +6,7 @@
     n copy of ``summarize_campaign`` task will be created dynamically
     using dynamic task mapping
 """
+
 import os
 from datetime import datetime
 

python-sdk/example_dags/example_google_bigquery_gcs_load_and_save.py

@@ -12,6 +12,7 @@
  - You can either specify a service account key file and set `GOOGLE_APPLICATION_CREDENTIALS`
     with the file path to the service account.
 """
+
 import os
 
 import pandas as pd

python-sdk/example_dags/example_load_file.py

@@ -16,6 +16,7 @@
     For sharing a file/folder
     please refer https://www.labnol.org/google-api-service-account-220404#4-share-a-drive-folder
 """
+
 import os
 import pathlib
 from datetime import datetime

python-sdk/src/astro/databases/aws/redshift.py

@@ -1,4 +1,5 @@
 """AWS Redshift table implementation."""
+
 from __future__ import annotations
 
 from typing import Any

python-sdk/src/astro/databases/google/bigquery.py

@@ -1,4 +1,5 @@
 """Google BigQuery table implementation."""
+
 from __future__ import annotations
 
 import time

python-sdk/src/astro/databases/postgres.py

@@ -1,4 +1,5 @@
 """Postgres database implementation."""
+
 from __future__ import annotations
 
 import io

python-sdk/src/astro/databases/snowflake.py

@@ -1,4 +1,5 @@
 """Snowflake database implementation."""
+
 from __future__ import annotations
 
 import logging

python-sdk/src/astro/files/locations/amazon/s3.py

@@ -81,9 +81,9 @@ def databricks_auth_settings(self) -> dict:
             "fs.s3a.secret.key": credentials.secret_key,
         }
         if credentials.token:
-            cred_dict[
-                "fs.s3a.aws.credentials.provider"
-            ] = "org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider"
+            cred_dict["fs.s3a.aws.credentials.provider"] = (
+                "org.apache.hadoop.fs.s3a.TemporaryAWSCredentialsProvider"
+            )
             cred_dict["fs.s3a.session.token"] = credentials.token
         return cred_dict
 

python-sdk/src/astro/sql/operators/dataframe.py

@@ -247,9 +247,11 @@ def get_openlineage_facets_on_complete(self, task_instance):  # skipcq: PYL-W061
                             fields=[
                                 SchemaField(
                                     name=self.schema if self.schema else self.output_table.metadata.schema,
-                                    type=self.database
-                                    if self.database
-                                    else self.output_table.metadata.database,
+                                    type=(
+                                        self.database
+                                        if self.database
+                                        else self.output_table.metadata.database
+                                    ),
                                 )
                             ]
                         ),

python-sdk/src/astro/sql/operators/export_to_file.py

@@ -120,9 +120,11 @@ def get_openlineage_facets_on_complete(self, task_instance):  # skipcq: PYL-W061
                     ),
                     "dataSource": DataSourceDatasetFacet(name=self.output_file.path, uri=output_uri),
                     "outputStatistics": OutputStatisticsOutputDatasetFacet(
-                        rowCount=self.input_data.row_count
-                        if isinstance(self.input_data, BaseTable)
-                        else len(self.input_data),
+                        rowCount=(
+                            self.input_data.row_count
+                            if isinstance(self.input_data, BaseTable)
+                            else len(self.input_data)
+                        ),
                         size=self.output_file.size,
                     ),
                 },

python-sdk/src/astro/utils/table.py

@@ -48,9 +48,11 @@ def _find_first_table_from_op_kwargs(
     :return: first valid table found in op_kwargs.
     """
     kwargs = [
-        op_kwargs[kwarg.name].resolve(context)
-        if isinstance(op_kwargs[kwarg.name], XComArg)
-        else op_kwargs[kwarg.name]
+        (
+            op_kwargs[kwarg.name].resolve(context)
+            if isinstance(op_kwargs[kwarg.name], XComArg)
+            else op_kwargs[kwarg.name]
+        )
         for kwarg in inspect.signature(python_callable).parameters.values()
     ]
     tables = [kwarg for kwarg in kwargs if isinstance(kwarg, BaseTable)]

python-sdk/tests/benchmark/dags/benchmark_gcs_to_big_query.py

@@ -1,6 +1,7 @@
 """
 This DAG is to benchmark GCSToBigQueryOperator for various dataset
 """
+
 import os
 from datetime import datetime, timedelta
 
@@ -83,9 +84,11 @@
     task_id="load_five_gb",
     bucket="astro-sdk",
     source_objects=[
-        f"benchmark/trimmed/pypi/pypi-downloads-2021-03-28-0000000000{str(i)}.ndjson"
-        if i >= 10
-        else f"benchmark/trimmed/pypi/pypi-downloads-2021-03-28-00000000000{str(i)}.ndjson"
+        (
+            f"benchmark/trimmed/pypi/pypi-downloads-2021-03-28-0000000000{str(i)}.ndjson"
+            if i >= 10
+            else f"benchmark/trimmed/pypi/pypi-downloads-2021-03-28-00000000000{str(i)}.ndjson"
+        )
         for i in range(20)
     ],
     destination_project_dataset_table=f"{DATASET_NAME}.{TABLE_NAME}",

python-sdk/tests/benchmark/synthetic_csv_generator.py

@@ -1,6 +1,7 @@
 """
 Function to generate csv files of various sizes
 """
+
 import csv
 import random
 

python-sdk/tests/benchmark/synthetic_ndjson_generator.py

@@ -1,6 +1,7 @@
 """
 Function to generate ndjson files of various sizes
 """
+
 import ndjson
 from faker import Faker
 

python-sdk/tests/benchmark/synthetic_parquet_generator.py

@@ -1,6 +1,7 @@
 """
 Function to generate PARQUET files of various sizes
 """
+
 import pandas as pd
 from faker import Faker
 

python-sdk/tests/databases/test_redshift.py

@@ -1,4 +1,5 @@
 """Tests specific to the Sqlite Database implementation."""
+
 from unittest import mock
 
 from airflow.models import Connection

python-sdk/tests/databases/test_snowflake.py

@@ -1,4 +1,5 @@
 """Tests specific to the Snowflake Database implementation."""
+
 import pathlib
 from unittest import mock
 from unittest.mock import MagicMock, PropertyMock, patch

python-sdk/tests_integration/astro_deploy/astronomer_migration_dag.py

@@ -1,4 +1,5 @@
 """Astronomer migration DAG to transform metadata from source deployment to target Astro Cloud deployment."""
+
 from datetime import datetime
 
 from airflow import DAG

python-sdk/tests_integration/databases/test_all_databases.py

@@ -1,4 +1,5 @@
 """Tests all Database implementations."""
+
 import pathlib
 from unittest import mock
 

python-sdk/tests_integration/databases/test_bigquery.py

@@ -1,4 +1,5 @@
 """Tests specific to the Sqlite Database implementation."""
+
 import os
 import pathlib
 from unittest import mock

python-sdk/tests_integration/databases/test_mssql.py

@@ -1,4 +1,5 @@
 """Tests specific to the SqlServer Database implementation."""
+
 import pathlib
 import re
 from urllib.parse import urlparse

python-sdk/tests_integration/databases/test_mysql.py

@@ -1,4 +1,5 @@
 """Tests specific to the MySql Database implementation."""
+
 import pathlib
 
 import pandas as pd

python-sdk/tests_integration/databases/test_postgres.py

@@ -1,4 +1,5 @@
 """Tests specific to the Sqlite Database implementation."""
+
 import os
 import pathlib
 from urllib.parse import urlparse

python-sdk/tests_integration/databases/test_redshift.py

@@ -1,4 +1,5 @@
 """Tests specific to the Sqlite Database implementation."""
+
 import os
 import pathlib
 import re

python-sdk/tests_integration/databases/test_snowflake.py

@@ -1,4 +1,5 @@
 """Tests specific to the Snowflake Database implementation."""
+
 import os
 import pathlib
 from unittest import mock