initial stage

airflow/dags/dag_utils.py

@@ -0,0 +1,23 @@
+from airflow.hooks.base import BaseHook
+from opensearchpy import OpenSearch
+from airflow.providers.amazon.aws.hooks.s3 import S3Hook
+
+
+def get_opensearch_client(kwargs) -> OpenSearch:
+    conn = BaseHook.get_connection(kwargs["params"]["OPENSEARCH_CONN_ID"])
+    return OpenSearch(
+        hosts=[{'host': conn.host, 'port': conn.port}],
+        http_auth=(conn.login, conn.password),
+        use_ssl=True,
+        verify_certs=False,
+        ssl_show_warn=False,
+        pool_maxsize=20,
+        timeout=180
+    )
+
+
+def get_bucket_name(context: dict, hook: S3Hook, param_name: str):
+    bucket_name = context["params"][param_name]
+    if not bucket_name:
+        bucket_name = hook.extra_args['bucket_name']
+    return bucket_name

airflow/dags/remove_old_indexes.py

@@ -1,21 +1,12 @@
 import json
-from datetime import datetime, timedelta
-import requests
-from airflow import DAG
-from airflow.operators.python_operator import PythonOperator
-from airflow.providers.http.hooks.http import HttpHook
-import os
 from datetime import timedelta
 
 import pendulum
 from airflow.decorators import dag
 from airflow.decorators import task
-from airflow.exceptions import AirflowSkipException
-from airflow.models.param import Param
 from airflow.operators.python import get_current_context
-from airflow.providers.amazon.aws.hooks.s3 import S3Hook
 
-from dag_utils import get_bucket_name, get_opensearch_client
+from dag_utils import get_opensearch_client
 
 # Define default arguments
 default_args = {