Commit b0be31a9 authored by Roque's avatar Roque

erp5_wendelin_data_lake_ingestion: drop obsolete script and use new name

parent 7357b3db
Pipeline #14051 failed with stage
in 0 seconds
"""
Return list of Data Streams belonging to a Date Set.
Data Ingestion line aggregates both Data Set and Data Stream.
Note: This code is quite computationally costly (for Data Streams having thousands of iles) as it needs to:
1. Query MariaDB to find ingestion lines
2. Read from ZODB both Data Ingestion Lines and Data Streams (which itself can be big too)
"""
data_ingestion_line_list = context.portal_catalog(
portal_type = "Data Ingestion Line",
aggregate_uid = context.getUid())
return [x.getAggregateValue(portal_type = "Data Stream") \
for x in data_ingestion_line_list]
<?xml version="1.0"?>
<ZopeData>
<record id="1" aka="AAAAAAAAAAE=">
<pickle>
<global name="PythonScript" module="Products.PythonScripts.PythonScript"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>Script_magic</string> </key>
<value> <int>3</int> </value>
</item>
<item>
<key> <string>_bind_names</string> </key>
<value>
<object>
<klass>
<global name="NameAssignments" module="Shared.DC.Scripts.Bindings"/>
</klass>
<tuple/>
<state>
<dictionary>
<item>
<key> <string>_asgns</string> </key>
<value>
<dictionary>
<item>
<key> <string>name_container</string> </key>
<value> <string>container</string> </value>
</item>
<item>
<key> <string>name_context</string> </key>
<value> <string>context</string> </value>
</item>
<item>
<key> <string>name_m_self</string> </key>
<value> <string>script</string> </value>
</item>
<item>
<key> <string>name_subpath</string> </key>
<value> <string>traverse_subpath</string> </value>
</item>
</dictionary>
</value>
</item>
</dictionary>
</state>
</object>
</value>
</item>
<item>
<key> <string>_params</string> </key>
<value> <string></string> </value>
</item>
<item>
<key> <string>id</string> </key>
<value> <string>DataSet_getDataStreamList</string> </value>
</item>
</dictionary>
</pickle>
</record>
</ZopeData>
...@@ -14,6 +14,6 @@ except Exception as e: ...@@ -14,6 +14,6 @@ except Exception as e:
return { "status_code": 1, "error_message": "401 - Unauthorized access. Please check your user credentials and try again." } return { "status_code": 1, "error_message": "401 - Unauthorized access. Please check your user credentials and try again." }
data_set_uid = data_set.getUid() data_set_uid = data_set.getUid()
data_stream_list = context.ERP5Site_getDataStreamList(data_set_uid) data_stream_list = context.DataSet_getDataStreamList(data_set_uid)
return { "status_code": 0, "result": len(data_stream_list) } return { "status_code": 0, "result": len(data_stream_list) }
...@@ -19,7 +19,7 @@ except Exception as e: # fails because unauthorized access ...@@ -19,7 +19,7 @@ except Exception as e: # fails because unauthorized access
return json.dumps({ "status_code": 1, "error_message": "401 - Unauthorized access. Please check your user credentials and try again." }) return json.dumps({ "status_code": 1, "error_message": "401 - Unauthorized access. Please check your user credentials and try again." })
data_set_uid = data_set.getUid() data_set_uid = data_set.getUid()
data_stream_list = context.ERP5Site_getDataStreamList(data_set_uid, limit) data_stream_list = context.DataSet_getDataStreamList(data_set_uid, limit)
data_stream_dict = {} data_stream_dict = {}
for stream_brain in data_stream_list: for stream_brain in data_stream_list:
......
...@@ -227,7 +227,7 @@ class TestDataIngestion(SecurityTestCase): ...@@ -227,7 +227,7 @@ class TestDataIngestion(SecurityTestCase):
self.tic() self.tic()
# check data relation between Data Set and Data Streams work # check data relation between Data Set and Data Streams work
self.assertSameSet(data_stream_list, data_set.DataSet_getDataStreamList()) self.assertSameSet(data_stream_list, data_set.DataSet_getDataStreamList(data_set.getUid()))
# check data set and all Data Streams states # check data set and all Data Streams states
self.assertEqual('validated', data_set.getValidationState()) self.assertEqual('validated', data_set.getValidationState())
...@@ -359,6 +359,6 @@ class TestDataIngestion(SecurityTestCase): ...@@ -359,6 +359,6 @@ class TestDataIngestion(SecurityTestCase):
select_list = ['reference', 'relative_url', 'versioning.size', 'versioning.version']) select_list = ['reference', 'relative_url', 'versioning.size', 'versioning.version'])
data_stream_list = [x.getObject() for x in data_stream_list] data_stream_list = [x.getObject() for x in data_stream_list]
# assert that the list from the search is the same as DataSet_getDataStreamList # assert that the list from the search is the same as DataSet_getDataStreamList
self.assertSameSet(data_stream_list, data_set.DataSet_getDataStreamList()) self.assertSameSet(data_stream_list, data_set.DataSet_getDataStreamList(data_set.getUid()))
# XXX: new test which simulates download / upload of Data Set and increase DS version # XXX: new test which simulates download / upload of Data Set and increase DS version
\ No newline at end of file
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment