added es_timeout for AWS ES and moved ingest_pipeline to inside with …

…block (#47)

grq2/es_connection.py

@@ -38,7 +38,10 @@ def get_grq_es(logger=None):
                 connection_class=RequestsHttpConnection,
                 use_ssl=True,
                 verify_certs=False,
-                ssl_show_warn=False
+                ssl_show_warn=False,
+                timeout=30,
+                max_retries=10,
+                retry_on_timeout=True,
             )
         else:
             GRQ_ES = ElasticsearchUtility(es_url, logger)

scripts/install_ingest_pipeline.py

@@ -11,11 +11,15 @@
 ingest_file = os.path.abspath(ingest_file)
 ingest_file = os.path.normpath(ingest_file)
 
-with open(ingest_file) as f:
-    pipeline_settings = json.load(f)
-    print(json.dumps(pipeline_settings, indent=2))
 
-    pipeline_name = 'dataset_pipeline'
+if __name__ == '__main__':
+    # TODO: delete pipeline here with a try except
 
-    # https://elasticsearch-py.readthedocs.io/en/master/api.html#elasticsearch.client.IngestClient
-    grq_es.es.ingest.put_pipeline(id=pipeline_name, body=pipeline_settings, ignore=400)
+    with open(ingest_file) as f:
+        pipeline_settings = json.load(f)
+        print(json.dumps(pipeline_settings, indent=2))
+
+        pipeline_name = 'dataset_pipeline'
+
+        # https://elasticsearch-py.readthedocs.io/en/master/api.html#elasticsearch.client.IngestClient
+        grq_es.es.ingest.put_pipeline(id=pipeline_name, body=pipeline_settings, ignore=400)