def cbr_retain(event, context=None):
"""
End-point: Completes the Retain step of the CBR cycle. Note: If the new case have id of an existing case, the new case will replace the existing entry.
"""
result = {}
# retain logic here
statusCode = 201
params = json.loads(event['body']) # parameters in request body
proj = params.get('project')
es = getESConn()
if proj is None:
projId = params.get('projectId') # name of casebase
proj = utility.getByUniqueField(es, projects_db, "casebase", projId)
# print(params)
new_case = params['data']
new_case = retrieve.add_vector_fields(proj['attributes'], new_case) # add vectors to Semantic USE fields
new_case['hash__'] = str(hashlib.md5(json.dumps(OrderedDict(sorted(new_case.items()))).encode('utf-8')).digest())
if not proj['retainDuplicateCases'] and utility.indexHasDocWithFieldVal(es, index=proj['casebase'], field='hash__',
value=new_case['hash__']):
result = "The case already exists in the casebase"
statusCode = 400
else:
result = es.index(index=proj['casebase'], body=new_case)
response = {
"statusCode": statusCode,
"headers": headers,
"body": json.dumps(result)
}
return response
def save_case_list(event, context=None):
"""
End-point: Saves list of case instances
Creates index for the casebase if one does not exist
"""
# try:
doc_list = json.loads(event['body']) # parameters in request body
es = getESConn()
pid = event['pathParameters']['id']
proj = utility.getByUniqueField(es, projects_db, "_id", pid) # project
# create index with mapping if it does not exist already
project.indexMapping(es, proj)
# Add documents to created index
# print("Adding a hash field to each case for duplicate-checking")
for x in doc_list: # generate a hash after ordering dict by key
x = retrieve.add_vector_fields(proj['attributes'],
x) # add vectors to Semantic USE fields
x = retrieve.add_lowercase_fields(
proj['attributes'],
x) # use lowercase values for EqualIgnoreCase fields
x['hash__'] = str(
hashlib.md5(
json.dumps(OrderedDict(sorted(x.items()))).encode('utf-8')).
digest()) # case hash for easy detection of duplicates
# print("Attempting to index the list of docs using helpers.bulk()")
resp = helpers.bulk(es, doc_list, index=proj['casebase'], doc_type="_doc")
# Indicate that the project has a casebase
# print("Casebase added. Attempting to update project detail. Set hasCasebase => True")
proj['hasCasebase'] = True
source_to_update = {'doc': proj}
# print(source_to_update)
res = es.update(index=projects_db, id=pid, body=source_to_update)
# print(res)
# create the ontology similarity if specified as part of project attributes (can be a lengthy operation for mid to large ontologies!)
for attrib in proj['attributes']:
if attrib['type'] == "Ontology Concept" and attrib.get(
'similarityType') is not None and attrib.get(
'options') is not None and retrieve.checkOntoSimilarity(
attrib['options'].get('id'))['statusCode'] != 200:
sim_method = 'san' if attrib[
'similarityType'] == 'Feature-based' else 'wup'
retrieve.setOntoSimilarity(
attrib['options'].get('id'),
attrib['options'].get('sources'),
relation_type=attrib['options'].get('relation_type'),
root_node=attrib['options'].get('root'),
similarity_method=sim_method)
response = {
"statusCode": 201,
"headers": headers,
"body": json.dumps(resp)
}
return response