Merge pull request #18 from 4dn-dcic/0.3.2

0.3.2

dcicutils/_version.py

@@ -1,4 +1,4 @@
 """Version information."""
 
 # The following line *must* be the last in the module, exactly as formatted:
-__version__ = "0.3.1"
+__version__ = "0.3.2"

dcicutils/es_utils.py

@@ -8,35 +8,41 @@
 '''
 
 
-def get_index_list(client, name, days_old=0, timestring='%Y.%m.%d', ilo=None):
-    if ilo is None:
-        ilo = curator.IndexList(client)
-
-    ilo.filter_by_regex(kind='prefix', value=name)
-    ilo.filter_by_age(source='name', direction='older', timestring=timestring, unit='days',
-                      unit_count=days_old)
-    return ilo
-
-
-def create_es_client(es_url, use_aws_auth=False):
+def create_es_client(es_url, use_aws_auth=True, **options):
+    """
+    Use to create a ES that supports the signature version 4 signing process.
+    Need to do role-based IAM access control for AWS hosted ES.
+    Takes a string es server url, boolean whether or not to use aws auth
+    signing procedure, and any additional kwargs that will be passed to
+    creation of the Elasticsearch client.
+    """
+    # may be passed in as a list, as was done previously
     if isinstance(es_url, (list, tuple)):
-        addresses = es_url
-    else:
-        addresses = [es_url, ]
+        es_url = es_url[0]
 
     es_options = {'retry_on_timeout': True,
-                  'maxsize': 50  # parallellism...
-                  }
+                  'maxsize': 50}  # parallellism...
     if use_aws_auth:
-        host = addresses[0].split('//')
+        host = es_url.split('//')  # remove schema from url
         host = host[-1].split(":")
         auth = BotoAWSRequestsAuth(aws_host=host[0].rstrip('/'),
                                    aws_region='us-east-1',
                                    aws_service='es')
         es_options['connection_class'] = RequestsHttpConnection
         es_options['http_auth'] = auth
+    es_options.update(**options)  # add any given keyword options at the end
 
-    return Elasticsearch(addresses, **es_options)
+    return Elasticsearch(es_url, **es_options)
+
+
+def get_index_list(client, name, days_old=0, timestring='%Y.%m.%d', ilo=None):
+    if ilo is None:
+        ilo = curator.IndexList(client)
+
+    ilo.filter_by_regex(kind='prefix', value=name)
+    ilo.filter_by_age(source='name', direction='older', timestring=timestring, unit='days',
+                      unit_count=days_old)
+    return ilo
 
 
 def create_snapshot_repo(client, repo_name,  s3_bucket):

setup.py

@@ -27,8 +27,8 @@
     packages=['dcicutils'],
     include_package_data=True,
     zip_safe=False,
-    author='$dn Team at Harvard Medical School',
-    author_email='jeremy_johnson@hms.harvard.edu',
+    author='4DN Team at Harvard Medical School',
+    author_email='burak_alver@hms.harvard.edu',
     url='https://data.4dnucleome.org',
     license='MIT',
     install_requires=requires,