def handler(event, context):
es_endpoint = os.getenv('ELASTICSEARCH_SERVICE_ENDPOINT')
photo_id = event["photo_id"]
# Connect to Elasticsearch service
try:
es = es_client.get_elasticsearch_client(es_endpoint)
except Exception:
logging.exception('Failed to connect to Elasticsearch cluster')
return response(500, {
'error': 'elasticsearch-client-connection',
'message': 'Elasticsearch service is not available'
})
try:
update = UpdateByQuery(using=es).index(cars_index_name)
update = update.filter('term', photoId=photo_id)
update = update.script(source='ctx._source.photoId = params.nullPhoto', params={'nullPhoto': None})
update.execute()
return response(200, {'result': 'Update seccessfull'})
except Exception:
logging.exception('Failed to cenzor photo')
return response(500, {
'error': 'car-photo-cenzor-fail',
'message': 'Failed to cenzor requested photo'
})
def test_params_being_passed_to_search(mock_client):
ubq = UpdateByQuery(using="mock")
ubq = ubq.params(routing="42")
ubq.execute()
mock_client.update_by_query.assert_called_once_with(index=None,
body={},
routing="42")
def test_params_being_passed_to_search(mock_client):
ubq = UpdateByQuery(using='mock')
ubq = ubq.params(routing='42')
ubq.execute()
mock_client.update_by_query.assert_called_once_with(
index=None,
body={},
routing='42'
)
def update_by_query(self, query, script_source):
try:
self.fix_read_only_allow_delete()
ubq = UpdateByQuery(using=self.es, index=self.index).update_from_dict(query).script(source=script_source)
ubq.execute()
except Exception as err:
print("Error: ", err)
return False
return True
def remove_from_field(doc_type_name, field_name, field_value):
"""Remove a value from all documents in the doc_type's index."""
doc_type = next(cls for cls in get_doc_types() if cls.__name__ == doc_type_name)
script = (
f"if (ctx._source.{field_name}.contains(params.value)) {{"
f"ctx._source.{field_name}.remove(ctx._source.{field_name}.indexOf(params.value))"
f"}}"
)
update = UpdateByQuery(using=es7_client(), index=doc_type._index._name)
update = update.filter("term", **{field_name: field_value})
update = update.script(source=script, params={"value": field_value}, conflicts="proceed")
# refresh index to ensure search fetches all matches
doc_type._index.refresh()
update.execute()
def update_all(self, field, value, **kwargs):
# Process hits here
# def process_hits(hits):
# for item in hits:
# self.update_field(item['_id'], field, value)
logger = kwargs.get("logger", None)
# Check index exists
if not self.es.indices.exists(index=self.index):
# print("Index " + self.index + " not exists")
exit()
ubq = UpdateByQuery(using=self.es, index=self.index).update_from_dict({"query": {"match_all": {}}}).script(
source="ctx._source." + field + " = '" + value + "'")
response = ubq.execute()
# # Init scroll by search
# data = self.es.search(
# index=self.index,
# doc_type=self.doc_type,
# scroll='15m',
# size=self.size,
# body=self.body
# )
#
# # Get the scroll ID
# sid = data['_scroll_id']
# scroll_size = len(data['hits']['hits'])
#
# # Before scroll, process current batch of hits
# # print(data['hits']['total'])
# process_hits(data['hits']['hits'])
# processed_docs = 0
#
# while scroll_size > 0:
#
# data = self.es.scroll(scroll_id=sid, scroll='15m')
#
# # Process current batch of hits
# process_hits(data['hits']['hits'])
#
# # Update the scroll ID
# sid = data['_scroll_id']
#
# # Get the number of results that returned in the last scroll
# scroll_size = len(data['hits']['hits'])
#
# if (logger):
# processed_docs += scroll_size
# logger.add_log("Scrolling " + str(round(processed_docs * 100 / data['hits']['total'],2)) + "% documents")
return True
def run_update_by_query(esc, query, index):
ubq = UpdateByQuery(using=esc, index=index).update_from_dict(
query).params(request_timeout=100)
finished = False
count = 0
while not finished and count < 3:
try:
count += 1
response = ubq.execute()
finished = True
except Exception as e:
print(e)
sleep(10 * count)
pass