Skip to content

W
wendelin-telecom
Commit 68538ec9 authored by Paul Graydon's avatar Paul Graydon
Browse files
Options

ors_wendelin: Update ORS ingestion process

parent 8d7fe6ae
Hide whitespace changes
Inline Side-by-side
Showing with 539 additions and 29 deletions
bt5/ors_wendelin/PathTemplateItem/data_operation_module/ors_kpi.xml
View file @ 68538ec9
......@@ -72,7 +72,7 @@
</item>
<item>
<key> <string>script_id</string> </key>
<value> <string>DataAnalysisLine_calculateKPI</string> </value>
<value> <string>DataAnalysisLine_calculateOrsKpi</string> </value>
</item>
<item>
<key> <string>title</string> </key>
......@@ -152,7 +152,7 @@
</item>
<item>
<key> <string>serial</string> </key>
<value> <string>1007.25652.35251.43929</string> </value>
<value> <string>1017.25284.41439.37888</string> </value>
</item>
<item>
<key> <string>state</string> </key>
......@@ -172,7 +172,7 @@
</tuple>
<state>
<tuple>
<float>1680177876.53</float>
<float>1718889733.66</float>
<string>UTC</string>
</tuple>
</state>
......
bt5/ors_wendelin/PathTemplateItem/data_operation_module/ors_wendelin_ingest_log_data.xml 0 → 100644
View file @ 68538ec9
<?xml version="1.0"?>
<ZopeData>
<record id="1" aka="AAAAAAAAAAE=">
<pickle>
<global name="Data Operation" module="erp5.portal_type"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>_Access_contents_information_Permission</string> </key>
<value>
<tuple>
<string>Assignee</string>
<string>Assignor</string>
<string>Associate</string>
<string>Auditor</string>
<string>Manager</string>
</tuple>
</value>
</item>
<item>
<key> <string>_Add_portal_content_Permission</string> </key>
<value>
<tuple>
<string>Assignee</string>
<string>Assignor</string>
<string>Associate</string>
<string>Manager</string>
</tuple>
</value>
</item>
<item>
<key> <string>_Modify_portal_content_Permission</string> </key>
<value>
<tuple>
<string>Assignee</string>
<string>Assignor</string>
<string>Associate</string>
<string>Manager</string>
</tuple>
</value>
</item>
<item>
<key> <string>_View_Permission</string> </key>
<value>
<tuple>
<string>Assignee</string>
<string>Assignor</string>
<string>Associate</string>
<string>Auditor</string>
<string>Manager</string>
</tuple>
</value>
</item>
<item>
<key> <string>_local_properties</string> </key>
<value>
<tuple>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>reference</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>string</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>version</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>string</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>data_operation_script_id</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>string</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>use_list</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>lines</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>quantity_unit_list</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>lines</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>aggregated_portal_type_list</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>lines</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>base_contribution_list</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>lines</string> </value>
</item>
</dictionary>
</tuple>
</value>
</item>
<item>
<key> <string>aggregated_portal_type</string> </key>
<value>
<tuple>
<string>Data Acquisition Unit</string>
</tuple>
</value>
</item>
<item>
<key> <string>aggregated_portal_type_list</string> </key>
<value>
<tuple>
<string>Data Stream</string>
</tuple>
</value>
</item>
<item>
<key> <string>base_contribution_list</string> </key>
<value>
<tuple/>
</value>
</item>
<item>
<key> <string>categories</string> </key>
<value>
<tuple>
<string>quantity_unit/unit/piece</string>
</tuple>
</value>
</item>
<item>
<key> <string>data_operation_script_id</string> </key>
<value> <string>ERP5Site_runFourierDataOperation</string> </value>
</item>
<item>
<key> <string>default_reference</string> </key>
<value> <string>ors_ingest_log_data</string> </value>
</item>
<item>
<key> <string>description</string> </key>
<value> <string>This data operation can be used to ingest ORS log data with fluentd.\n
It assumes the data comes in MsgPack format, and extracts the log contents into a string stored in the Data Stream.</string> </value>
</item>
<item>
<key> <string>id</string> </key>
<value> <string>ors_wendelin_ingest_log_data</string> </value>
</item>
<item>
<key> <string>language</string> </key>
<value>
<none/>
</value>
</item>
<item>
<key> <string>portal_type</string> </key>
<value> <string>Data Operation</string> </value>
</item>
<item>
<key> <string>quantity_unit_list</string> </key>
<value>
<tuple>
<string>information/byte</string>
</tuple>
</value>
</item>
<item>
<key> <string>reference</string> </key>
<value> <string>FOURIER-MAX</string> </value>
</item>
<item>
<key> <string>script_id</string> </key>
<value> <string>DataIngestionLine_writeOrsLogFluentdIngestionToDataStream</string> </value>
</item>
<item>
<key> <string>title</string> </key>
<value> <string>ORS Ingest Log Data</string> </value>
</item>
<item>
<key> <string>use_list</string> </key>
<value>
<tuple>
<string>big_data/analysis</string>
</tuple>
</value>
</item>
<item>
<key> <string>version</string> </key>
<value> <string>001</string> </value>
</item>
<item>
<key> <string>workflow_history</string> </key>
<value>
<persistent> <string encoding="base64">AAAAAAAAAAI=</string> </persistent>
</value>
</item>
</dictionary>
</pickle>
</record>
<record id="2" aka="AAAAAAAAAAI=">
<pickle>
<global name="PersistentMapping" module="Persistence.mapping"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>data</string> </key>
<value>
<dictionary>
<item>
<key> <string>edit_workflow</string> </key>
<value>
<persistent> <string encoding="base64">AAAAAAAAAAM=</string> </persistent>
</value>
</item>
<item>
<key> <string>validation_workflow</string> </key>
<value>
<persistent> <string encoding="base64">AAAAAAAAAAQ=</string> </persistent>
</value>
</item>
</dictionary>
</value>
</item>
</dictionary>
</pickle>
</record>
<record id="3" aka="AAAAAAAAAAM=">
<pickle>
<global name="WorkflowHistoryList" module="Products.ERP5Type.Workflow"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>_log</string> </key>
<value>
<list>
<dictionary>
<item>
<key> <string>action</string> </key>
<value> <string>edit</string> </value>
</item>
<item>
<key> <string>actor</string> </key>
<value> <unicode>zope</unicode> </value>
</item>
<item>
<key> <string>comment</string> </key>
<value>
<none/>
</value>
</item>
<item>
<key> <string>error_message</string> </key>
<value> <string></string> </value>
</item>
<item>
<key> <string>serial</string> </key>
<value> <string>1017.25596.32627.4386</string> </value>
</item>
<item>
<key> <string>state</string> </key>
<value> <string>current</string> </value>
</item>
<item>
<key> <string>time</string> </key>
<value>
<object>
<klass>
<global name="_reconstructor" module="copy_reg"/>
</klass>
<tuple>
<global name="DateTime" module="DateTime.DateTime"/>
<global name="object" module="__builtin__"/>
<none/>
</tuple>
<state>
<tuple>
<float>1718891315.33</float>
<string>UTC</string>
</tuple>
</state>
</object>
</value>
</item>
</dictionary>
</list>
</value>
</item>
</dictionary>
</pickle>
</record>
<record id="4" aka="AAAAAAAAAAQ=">
<pickle>
<global name="WorkflowHistoryList" module="Products.ERP5Type.Workflow"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>_log</string> </key>
<value>
<list>
<dictionary>
<item>
<key> <string>action</string> </key>
<value> <string>validate</string> </value>
</item>
<item>
<key> <string>actor</string> </key>
<value> <unicode>zope</unicode> </value>
</item>
<item>
<key> <string>comment</string> </key>
<value> <string></string> </value>
</item>
<item>
<key> <string>error_message</string> </key>
<value> <string></string> </value>
</item>
<item>
<key> <string>time</string> </key>
<value>
<object>
<klass>
<global name="_reconstructor" module="copy_reg"/>
</klass>
<tuple>
<global name="DateTime" module="DateTime.DateTime"/>
<global name="object" module="__builtin__"/>
<none/>
</tuple>
<state>
<tuple>
<float>1718887532.69</float>
<string>UTC</string>
</tuple>
</state>
</object>
</value>
</item>
<item>
<key> <string>validation_state</string> </key>
<value> <string>validated</string> </value>
</item>
</dictionary>
</list>
</value>
</item>
</dictionary>
</pickle>
</record>
</ZopeData>
bt5/ors_wendelin/PathTemplateItem/portal_callables/DataAnalysisLine_calculateKPI.py → bt5/ors_wendelin/PathTemplateItem/portal_callables/DataAnalysisLine_calculateOrsKpi.py
View file @ 68538ec9
......@@ -8,22 +8,25 @@ total_size = in_data_stream.getSize()
if start >= total_size:
return
chunk_size = 1024*1024
chunk_size = 1024 * 1024
end = min(start + chunk_size, total_size)
if start + chunk_size > total_size:
end = total_size
else:
end = start + chunk_size
log_data = ''.join(in_data_stream.readChunkList(start, end))
chunk_data = "".join(in_data_stream.readChunkList(start, end))
# last one maybe a not valide json
split_chunk_data = chunk_data.splitlines()
if len(split_chunk_data) < 2:
# Some lines may contain several contiguous JSON objects
# Normalize to one JSON object per line
newlines_offset = log_data.count('}{')
log_data = log_data.replace('}{', '}\n{')
# Last chunk may be an incomplete JSON object: leave it for next iteration
log_data_lines = log_data.splitlines()
if len(log_data_lines) < 2:
return
chunk_data = '\n'.join(split_chunk_data[:-1])
end = start + len(chunk_data) + 1
log_data = '\n'.join(log_data_lines[:-1])
end = start + len(log_data) - newlines_offset + 1
chunk_data = chunk_data.decode('utf8')
log_data = log_data.decode('utf8')
e_rab_data_array = None
e_utran_data_array = None
......@@ -34,7 +37,12 @@ for array in out_array:
if array['variation'] == 'e_utran':
e_utran_data_array = array['Data Array']
vt, vInititialEPSBEstabSR, vAddedEPSBEstabSR, evt, vIPThp_qci = context.Base_getORSKPIValue(chunk_data)
try:
vt, vInititialEPSBEstabSR, vAddedEPSBEstabSR, evt, vIPThp_qci = context.Base_getORSKPIValue(log_data)
except AssertionError:
# If some data is invalid: ignore data chunk and move on rather than crashing the data analysis activity
progress_indicator.setIntOffsetIndex(end)
return
e_rab_dtype = np.dtype([
('vt', 'float'),
......@@ -44,7 +52,7 @@ e_rab_dtype = np.dtype([
('vAddedEPSBEstabSR_hi', 'float64'),
])
e_utran_dtype =np.dtype([
e_utran_dtype = np.dtype([
('evt', 'float'),
('dl_lo', 'float64'),
('dl_hi', 'float64'),
......@@ -57,7 +65,6 @@ if not e_rab_array:
e_rab_array = e_rab_data_array.initArray(shape=(0,), dtype=e_rab_dtype)
e_rab_array_data = []
e_utran_array = e_utran_data_array.getArray()
if not e_utran_array:
e_utran_array = e_utran_data_array.initArray(shape=(0,), dtype=e_utran_dtype )
......
bt5/ors_wendelin/PathTemplateItem/portal_callables/DataAnalysisLine_calculateKPI.xml → bt5/ors_wendelin/PathTemplateItem/portal_callables/DataAnalysisLine_calculateOrsKpi.xml
View file @ 68538ec9
......@@ -77,15 +77,15 @@
</item>
<item>
<key> <string>id</string> </key>
<value> <string>DataAnalysisLine_calculateKPI</string> </value>
<value> <string>DataAnalysisLine_calculateOrsKpi</string> </value>
</item>
<item>
<key> <string>reference</string> </key>
<value> <string>DataAnalysisLine_calculateKPI</string> </value>
<value> <string>DataAnalysisLine_calculateOrsKpi</string> </value>
</item>
<item>
<key> <string>title</string> </key>
<value> <string>DataAnalysisLine_calculateKPI</string> </value>
<value> <string>DataAnalysisLine_calculateOrsKpi</string> </value>
</item>
</dictionary>
</pickle>
......
bt5/ors_wendelin/PathTemplateItem/portal_callables/DataIngestionLine_writeOrsLogFluentdIngestionToDataStream.py 0 → 100644
View file @ 68538ec9
"""
This script is used during the ingestion of ORS log files through fluentd.
It assumes data comes encoded in the following format: msgpack(timestamp, data).
It will first unpack the msgpack, then remove the first item of the tuple (timestamp),
get the actual data stored under the 'log' key and append the corresponding string to "Data Stream".
"""
out_stream["Data Stream"].appendData('\n'.join([c[1]['log'] for c in context.unpack(data_chunk)]))
bt5/ors_wendelin/PathTemplateItem/portal_callables/DataIngestionLine_writeOrsLogFluentdIngestionToDataStream.xml 0 → 100644
View file @ 68538ec9
<?xml version="1.0"?>
<ZopeData>
<record id="1" aka="AAAAAAAAAAE=">
<pickle>
<global name="PyData Script" module="erp5.portal_type"/>
</pickle>
<pickle>
<dictionary>
<item>
<key> <string>_bind_names</string> </key>
<value>
<object>
<klass>
<global name="_reconstructor" module="copy_reg"/>
</klass>
<tuple>
<global name="NameAssignments" module="Shared.DC.Scripts.Bindings"/>
<global name="object" module="__builtin__"/>
<none/>
</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>_local_properties</string> </key>
<value>
<tuple>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>reference</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>string</string> </value>
</item>
</dictionary>
<dictionary>
<item>
<key> <string>id</string> </key>
<value> <string>comment</string> </value>
</item>
<item>
<key> <string>type</string> </key>
<value> <string>string</string> </value>
</item>
</dictionary>
</tuple>
</value>
</item>
<item>
<key> <string>_params</string> </key>
<value> <string>data_chunk, out_stream={}</string> </value>
</item>
<item>
<key> <string>comment</string> </key>
<value> <string>This script is used with default simple Wendelin model defined in erp5_wendelin_data.\n
For other models it will need adjustments.</string> </value>
</item>
<item>
<key> <string>description</string> </key>
<value> <string>Ingestion operation script to be used for ingestion of ORS logs through fluentd: unpack the data from MsgPack format and append it to the data stream.</string> </value>
</item>
<item>
<key> <string>id</string> </key>
<value> <string>DataIngestionLine_writeOrsLogFluentdIngestionToDataStream</string> </value>
</item>
<item>
<key> <string>portal_type</string> </key>
<value> <string>PyData Script</string> </value>
</item>
<item>
<key> <string>reference</string> </key>
<value> <string>DataIngestionLine_writeOrsLogFluentdIngestionToDataStream</string> </value>
</item>
<item>
<key> <string>title</string> </key>
<value> <string>DataIngestionLine_writeOrsLogFluentdIngestionToDataStream</string> </value>
</item>
</dictionary>
</pickle>
</record>
</ZopeData>
bt5/ors_wendelin/PathTemplateItem/portal_ingestion_policies/ors_ingestion.xml
View file @ 68538ec9
......@@ -52,15 +52,17 @@
</tuple>
</value>
</item>
<item>
<key> <string>data_operation_script_id</string> </key>
<value> <string>IngestionPolicy_getIngestionOperationAndParameterDict</string> </value>
</item>
<item>
<key> <string>default_reference</string> </key>
<value> <string>ors_ingestion</string> </value>
</item>
<item>
<key> <string>description</string> </key>
<value>
<none/>
</value>
<value> <string>Handles ingestion of packets of ORS enb.xlog data forwarded through fluentd in MessagePack format. </string> </value>
</item>
<item>
<key> <string>id</string> </key>
......@@ -148,7 +150,7 @@
</item>
<item>
<key> <string>serial</string> </key>
<value> <string>1007.25441.42822.58419</string> </value>
<value> <string>1017.20946.52185.63385</string> </value>
</item>
<item>
<key> <string>state</string> </key>
......@@ -168,7 +170,7 @@
</tuple>
<state>
<tuple>
<float>1680168713.51</float>
<float>1718612396.27</float>
<string>UTC</string>
</tuple>
</state>
......
bt5/ors_wendelin/SkinTemplateItem/portal_skins/ors_wendelin/DataAcquisitionUnit_createORSDataSupply.py
View file @ 68538ec9
......@@ -33,12 +33,12 @@ data_supply.newContent(
data_supply.newContent(
portal_type='Data Supply Line',
title='Ingest Data',
title='Ingest ORS Log Data',
reference='ingestion_operation',
quantity=1,
int_index=1,
aggregate_value=context,
resource='data_operation_module/wendelin_ingest_data'
resource='data_operation_module/ors_wendelin_ingest_log_data'
).validate()
data_supply.validate()
......
bt5/ors_wendelin/bt/template_path_list
View file @ 68538ec9
......@@ -4,7 +4,8 @@ data_product_module/ors_kpi/**
data_transformation_module/ors_data_transformation
data_transformation_module/ors_data_transformation/**
organisation_module/ors_*
portal_callables/DataAnalysisLine_calculateKPI
portal_callables/DataAnalysisLine_calculateOrsKpi
portal_callables/DataIngestionLine_writeOrsLogFluentdIngestionToDataStream
portal_callables/IngestionPolicy_parseORSTag
portal_ingestion_policies/ors_ingestion
web_page_module/ndarray_bundle.js
......
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
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7