Unify Logger Config for Tasks (#1709)

### Feature or Bugfix
<!-- please choose -->
- Refactoring

### Detail
-  Unify Logger Config in Backend (focused on `/tasks`)
-  Fix Log Level setting

### Relates
- #1680
- #1662
### Security
Please answer the questions below briefly where applicable, or write
`N/A`. Based on
[OWASP 10](https://owasp.org/Top10/en/).

- Does this PR introduce or modify any input fields or queries - this
includes
fetching data from storage outside the application (e.g. a database, an
S3 bucket)?
  - Is the input sanitized?
- What precautions are you taking before deserializing the data you
consume?
  - Is injection prevented by parametrizing queries?
  - Have you ensured no `eval` or similar functions are used?
- Does this PR introduce any functionality or component that requires
authorization?
- How have you ensured it respects the existing AuthN/AuthZ mechanisms?
  - Are you logging failed auth attempts?
- Are you using or adding any cryptographic features?
  - Do you use a standard proven implementations?
  - Are the used keys controlled by the customer? Where are they stored?
- Are you introducing any new policies/roles/users?
  - Have you used the least-privilege principle? How?


By submitting this pull request, I confirm that my contribution is made
under the terms of the Apache 2.0 license.

backend/dataall/__init__.py

@@ -1,2 +1,13 @@
 from . import core, version
 from .base import utils, db, api
+import logging
+import os
+import sys
+
+logging.basicConfig(
+    level=os.environ.get('LOG_LEVEL', 'INFO'),
+    handlers=[logging.StreamHandler(sys.stdout)],
+    format='[%(levelname)s] %(message)s',
+)
+for name in ['boto3', 's3transfer', 'botocore', 'boto', 'urllib3']:
+    logging.getLogger(name).setLevel(logging.ERROR)

backend/dataall/core/environment/tasks/env_stacks_updater.py

@@ -12,11 +12,8 @@
 from dataall.base.db import get_engine
 from dataall.base.utils import Parameter
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
+
 
 RETRIES = 30
 SLEEP_TIME = 30

backend/dataall/core/stacks/tasks/cdkproxy.py

@@ -5,11 +5,7 @@
 from dataall.base.cdkproxy.cdk_cli_wrapper import deploy_cdk_stack
 from dataall.base.db import get_engine
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 logger = logging.getLogger(__name__)
-logger.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 if __name__ == '__main__':

backend/dataall/modules/catalog/tasks/catalog_indexer_task.py

@@ -9,11 +9,7 @@
 from dataall.base.loader import load_modules, ImportMode
 from dataall.base.utils.alarm_service import AlarmService
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 class CatalogIndexerTask:

backend/dataall/modules/omics/tasks/omics_workflows_fetcher.py

@@ -11,11 +11,7 @@
 from dataall.modules.omics.db.omics_repository import OmicsRepository
 
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 def fetch_omics_workflows(engine):

backend/dataall/modules/s3_datasets/tasks/tables_syncer.py

@@ -16,11 +16,7 @@
 from dataall.modules.s3_datasets.indexers.dataset_indexer import DatasetIndexer
 from dataall.modules.s3_datasets.services.dataset_alarm_service import DatasetAlarmService
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 def sync_tables(engine):

backend/dataall/modules/s3_datasets_shares/tasks/dataset_subscription_task.py

@@ -22,11 +22,7 @@
 from dataall.modules.shares_base.db.share_object_models import ShareObject
 from dataall.modules.shares_base.services.share_notification_service import DataSharingNotificationType
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 # TODO: review this task usage and remove if not needed
 

backend/dataall/modules/s3_datasets_shares/tasks/subscriptions/sqs_poller.py

@@ -6,11 +6,8 @@
 import boto3
 from botocore.exceptions import ClientError
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
+
 
 ENVNAME = os.getenv('envname', 'local')
 region = os.getenv('AWS_REGION', 'eu-west-1')

backend/dataall/modules/shares_base/tasks/persistent_email_reminders_task.py

@@ -9,11 +9,7 @@
 from dataall.modules.datasets_base.db.dataset_repositories import DatasetBaseRepository
 
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 def persistent_email_reminders(engine):

backend/dataall/modules/shares_base/tasks/share_expiration_task.py

@@ -12,11 +12,7 @@
 from dataall.modules.shares_base.services.shares_enums import ShareObjectActions
 from dataall.modules.shares_base.services.sharing_service import SharingService
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 def share_expiration_checker(engine):

backend/dataall/modules/shares_base/tasks/share_manager_task.py

@@ -6,12 +6,7 @@
 from dataall.base.db import get_engine
 from dataall.base.loader import load_modules, ImportMode
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
-
 
 if __name__ == '__main__':
     try:

backend/dataall/modules/shares_base/tasks/share_reapplier_task.py

@@ -11,11 +11,7 @@
 
 from dataall.base.loader import load_modules, ImportMode
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 class EcsBulkShareRepplyService:

backend/dataall/modules/shares_base/tasks/share_verifier_task.py

@@ -11,11 +11,7 @@
 
 from dataall.base.loader import load_modules, ImportMode
 
-root = logging.getLogger()
-if not root.hasHandlers():
-    root.addHandler(logging.StreamHandler(sys.stdout))
 log = logging.getLogger(__name__)
-log.setLevel(os.environ.get('LOG_LEVEL', 'INFO'))
 
 
 def verify_shares(engine):