def query_ec(self, str_query, q_fields, start_date=0, end_date=0, index='logs-*', doc_type='logs',
hours=24, debug=False):
if start_date > end_date:
raise Exception('The start_date can\'t be greater than the end_date')
if start_date == 0 or end_date == 0:
dt_end_date = datetime.now().timestamp()
dt_start_date = (datetime.now() - timedelta(hours=hours)).timestamp()
start_date = int(dt_start_date) * 1000
end_date = int(dt_end_date) * 1000
# print(str(start_date) + ' -- ' + str(end_date))
elastic_qry = ElasticQuery(es=self.elastic_client, index=index, doc_type=doc_type)
elastic_qry.query(
Query.bool(
must=[Query.query_string(str_query),
Query.range('normalDate', gte=start_date, lte=end_date)]
)
)
elastic_qry.aggregate(
Aggregate.date_histogram('2', 'normalDate', '12h')
)
my_qry = elastic_qry.dict()
my_qry['stored_fields'] = q_fields
search_arr = list()
header_qry = {"index": ["logs-*"], "ignore_unavailable": True}
search_arr.append(header_qry)
search_arr.append(my_qry)
print('Elastic Query: ' + str(search_arr))
print('------------------------------------------------------------------------------------')
print('Lucene Query: ' + str_query)
request = ''
for each in search_arr:
request += '%s \n' % json.dumps(each)
# print(request)
resp = self.elastic_client.msearch(body=request)
if resp is None and len(resp['responses']) <= 0:
return None
else:
response = resp['responses'][0]
hits_data = list()
if response['hits']['total'] > 0:
for hit in response['hits']['hits']:
hits_data.append(hit)
# print(str(hits_data))
return search_arr, hits_data
def search(self, parms):
device_controller = DeviceController(self.db, self.logger)
if "location" in parms.keys():
list_location_ip = device_controller.get_device_list_by_locationid(
parms["location"])
if "device" in parms.keys():
list_device_ip = device_controller.get_device_list_by_hostname(
parms["device"])
#Doing intersection between device search and device in location
search_ip = list(set(list_location_ip) & set(list_device_ip))
print search_ip
query_search = []
if search_ip:
query_search.append(Query.terms('host', search_ip))
if parms["time"]:
time_from = parms["time"]["from"].split(" ")[0]
time_to = parms["time"]["to"].split(" ")[0]
query_search.append(
Query.range('@timestamp', gte=time_from, lte=time_to))
if parms["severityLevel"]:
query_search.append(
Query.terms('severity', parms["severityLevel"]))
if parms["keywordMessage"]:
message_search = []
message_search.append(parms["keywordMessage"])
query_search.append(Query.terms('message', message_search))
index = "syslog*"
es = Elasticsearch(["http://192.168.100.249:9200"])
q = ElasticQuery(es=es, index=index, doc_type='doc')
# q.query(Query.match_all())
q.size(1000)
q.query(Query.bool(must=query_search))
#q.query(Aggregate.terms(must=query_search))
print q.json(indent=4)
query_result = self.format_results(q.get())
return query_result
#No index to query
else:
return []
def test_query_aggregate_and_suggester(self):
q = ElasticQuery()
q.query(Query.match('field', 'query'))
q.aggregate(Aggregate.max('agg_name', 'field'))
q.suggest(Suggester.term('sugg_name', 'term text', 'term_field'))
assert_equal(
self, q.dict(), {
'query': {
'match': {
'field': {
'query': 'query'
}
}
},
'aggregations': {
'agg_name': {
'max': {
'field': 'field'
}
}
},
'suggest': {
'sugg_name': {
'text': 'term text',
'term': {
'field': 'term_field'
}
}
}
})
def freeSearch(self, searchquery):
searchquery = re.sub(r'\s+', ' ', searchquery)
# Elasticsearch connection initialization
es = Elasticsearch(hosts = [{"host": self.host, "port": self.port}])
size = 500
index = ""
# Find all indexes and remove them from the query
if searchquery.find("\index") != -1:
index = searchquery.replace(", ",",").replace(" ",",")[searchquery.find("\index") + 7:]
searchquery = searchquery[:searchquery.find("\index")]
q = ElasticQuery(es, index=index, doc_type='')
ElasticQuery.sort(q,"_score",order="desc")
ElasticQuery.size(q,size)
# Check correct query syntax (query must have max 2 '\in' and max 1 '\filter')
if searchquery.count("\in ") <= 2 and searchquery.count("\\filter ") <= 1:
# Code for query creation like "SELECT *** IN *** FILTER *** IN ***"
if searchquery.count("\in ") == 2 and searchquery.find("\\filter ") != -1:
q.query(Query.bool(
must=[self.compose_query(searchquery[:searchquery.find("\in")-1],searchquery[searchquery.find("\in") + 4:searchquery.find("\\filter")])],
must_not=[self.compose_query(searchquery[searchquery.find("\\filter") + 8:searchquery.rfind("\in")-1],searchquery[searchquery.rfind("\in") + 4:])]
))
# Code for query creation like "SELECT *** IN *** FILTER ***"
elif searchquery.count("\in ") == 1 and searchquery.find("\\filter ") != -1:
q.query(Query.bool(
must=[self.compose_query(searchquery[:searchquery.find("\in")-1],searchquery[searchquery.find("\in") + 4:searchquery.find("\\filter")])],
must_not=[self.compose_query(searchquery[searchquery.find("\\filter") + 8:],"_all")]
))
# Code for query creation like "SELECT *** IN ***"
elif searchquery.count("\in ") == 1 and searchquery.find("\\filter ") == -1 and searchquery.find("\\filter") == -1:
q.query(self.compose_query(searchquery[:searchquery.find("\in")-1],searchquery[searchquery.find("\in") + 4:]))
# Code for query creation like "SELECT ***"
elif searchquery.count("\in ") == 0 and searchquery.count("\in") == 0 and searchquery.find("\\filter ") == -1 and searchquery.find("\\filter") == -1:
q.query(self.compose_query(searchquery,"_all"))
# ERROR
else:
return HttpResponse('Server: Wrong query syntax!')
else:
return HttpResponse('Server: Wrong query syntax!')
return q.get()
def test_invalid_arg(self):
# Test passing not a list
with self.assertRaises(ValueError):
Query.bool(must=set())
# And now an invalid list
with self.assertRaises(ValueError):
Query.bool(must=[None])
# And now an invalid list
with self.assertRaises(ValueError):
Query.bool(must=[Aggregate.terms('test', 'test')])
# And now an invalid list
with self.assertRaises(ValueError):
Query.range('field', gte=['error'])
# Empty list should be OK/ignored
Query.bool(must=[])
def test_just_query(self):
q = ElasticQuery()
q.query(Query.query_string('this is a querystring'))
assert_equal(
self, q.dict(),
{'query': {
'query_string': {
'query': 'this is a querystring'
}
}})
def compose_query(self,terms,fields):
terms = terms.replace(' ,',',').replace(', ',',').replace(" ","_").replace(","," ").split()
result = ''
for each in terms:
if each.find("*") == -1 and each.find("?") == -1:
result = result + '"' + each.replace("_"," ") + '" '
else:
result = result + each.replace("_"," ") + ' '
return Query.query_string(
'(' + result[:-1] + ') OR (' + result[:-1].lower() + ') OR (' + result[:-1].upper() + ') OR (' + result[:-1].title() + ')',
fields=fields.replace(", ",",").replace(","," ").split(),lowercase_expanded_terms=False
)
'default_operator': 'AND'
}
},
'STRING': {
'query_string': {
'query':
'field_name1:value_name1 AND (field_name2:((value_name2) OR (value_name3)))',
'default_operator': 'AND'
}
},
'NESTED_FILTER': {}
}
# Test filters
print '[ElasticQuery] Testing: filters & queries'
query = Query.range('field_name1', gt=0, lte=100)[1]
test('Query.range', query, FILTERS['RANGE'])
query = Query.prefix(field_name1='value_name1')[1]
test('Query.prefix', query, FILTERS['PREFIX'])
query = Query.term(field_name1='value_name1')[1]
test('Query.term', query, FILTERS['TERM'])
query = Query.terms(field_name1=['value_name1', 'value_name2'])[1]
test('Query.terms', query, FILTERS['TERMS'])
query = Filter.missing('field_name1')[1]
test('Filter.missing', query, FILTERS['FILTER_MISSING'])
query = Query.missing('field_name1')[1]
test('Query.missing', query, FILTERS['QUERY_MISSING'])
def logicalSearch(self,query):
size = 500
must_fields = ""
must_values = ""
should_fields = ""
should_values = ""
mustnot_fields = ""
mustnot_values = ""
all_indexes = ""
# Remove space on query string and add % as prefix and suffix searchquery = re.sub(r'\s+', ' ', searchquery)
query = re.sub(r'\s+', ' ', query).replace(") (",")(").replace("MUST(","%MUST%(").replace("SHOULD(","%SHOULD%(").replace("MUST_NOT(","%MUST_NOT%(").replace("MUST (","%MUST%(").replace("SHOULD (","%SHOULD%(").replace("MUST_NOT (","%MUST_NOT%(") + " %"
# Populate class variables with values only if the relative condition is present on our query
if query.find("%MUST%") != -1:
result = self.return_elements(query,"MUST")
must_fields = self.return_values(result,".","=")
must_fields = must_fields[:len(self.remove_dupl(must_fields))]
must_values = self.return_values(result,"=",")")
if query.find("%SHOULD%") != -1:
result = self.return_elements(query,"SHOULD")
should_fields = self.return_values(result,".","=")
should_fields = should_fields[:len(self.remove_dupl(should_fields))]
should_values = self.return_values(result,"=",")")
if query.find("%MUST_NOT%") != -1:
result = self.return_elements(query,"MUST_NOT")
mustnot_fields = self.return_values(result,".","=")
mustnot_fields = mustnot_fields[:len(self.remove_dupl(mustnot_fields))]
mustnot_values = self.return_values(result,"=",")")
# Elasticsearch connection initialization
all_indexes = self.return_values(result,"(",".")
es = Elasticsearch(hosts = [{"host": self.host, "port": self.port}])
q = ElasticQuery(es,index=self.remove_dupl(all_indexes),doc_type='')
ElasticQuery.sort(q,"_score",order="desc")
ElasticQuery.size(q,str(size))
# Code for query creation like "MUST (...) SHOULD (...) MUST_NOT(...)"
if must_fields != "" and should_fields != "" and mustnot_fields != "":
q.query(Query.bool(
must=[self.compose_query(must_values,must_fields)],
should=[self.compose_query(should_values,should_fields)],
must_not=[self.compose_query(mustnot_values,mustnot_fields)]
))
# Code for query creation like "MUST (...) SHOULD (...)"
elif must_fields != "" and should_fields != "" and mustnot_fields == "":
q.query(Query.bool(
must=[self.compose_query(must_values,must_fields)],
should=[self.compose_query(should_values,should_fields)]
))
# Code for query creation like "SHOULD (...) MUST_NOT(...)"
elif must_fields == "" and should_fields != "" and mustnot_fields != "":
q.query(Query.bool(
should=[self.compose_query(should_values,should_fields)],
must_not=[self.compose_query(mustnot_values,mustnot_fields)]
))
# Code for query creation like "MUST (...) MUST_NOT(...)"
elif must_fields != "" and should_fields == "" and mustnot_fields != "":
q.query(Query.bool(
must=[self.compose_query(must_values,must_fields)],
must_not=[self.compose_query(mustnot_values,mustnot_fields)]
))
# Code for query creation like "MUST (...)"
elif must_fields != "" and should_fields == "" and mustnot_fields == "":
q.query(Query.bool(
must=[self.compose_query(must_values,must_fields)]
))
# Code for query creation like "SHOULD (...)"
elif must_fields == "" and should_fields != "" and mustnot_fields == "":
q.query(Query.bool(
should=[self.compose_query(should_values,should_fields)]
))
# Code for query creation like "MUST_NOT (...)"
elif must_fields == "" and should_fields == "" and mustnot_fields != "":
q.query(Query.bool(
must_not=[self.compose_query(mustnot_values,mustnot_fields)]
))
# ERROR
else:
return HttpResponse('Server: Wrong query syntax!')
return q.get()
def return_single_field_search(field,search):
q = ElasticQuery(es=Elasticsearch(),index=all_indexes,doc_type='')
q.aggregate(Aggregate.terms(search,field))
q.query(Query.query_string(search,field,default_operator='OR',analyze_wildcard=True))
q.fields(field)
ElasticQuery.sort(q,"_score",order="desc")
def test_missing_arg(self):
with self.assertRaises(MissingArgError):
Query.term(None)
def test_no_query(self):
with self.assertRaises(NoQueryError):
Query.doesnotexist()