def init_collection_general(self,
prefix="test",
insert_data=False,
nb=ct.default_nb,
partition_num=0,
is_binary=False,
is_all_data_type=False,
auto_id=False,
dim=ct.default_dim,
is_index=False,
primary_field=ct.default_int64_field_name,
is_flush=True,
name=None,
**kwargs):
"""
target: create specified collections
method: 1. create collections (binary/non-binary, default/all data type, auto_id or not)
2. create partitions if specified
3. insert specified (binary/non-binary, default/all data type) data
into each partition if any
4. not load if specifying is_index as True
expected: return collection and raw data, insert ids
"""
log.info("Test case of search interface: initialize before test case")
self._connect()
collection_name = cf.gen_unique_str(prefix)
if name is not None:
collection_name = name
vectors = []
binary_raw_vectors = []
insert_ids = []
time_stamp = 0
# 1 create collection
default_schema = cf.gen_default_collection_schema(
auto_id=auto_id, dim=dim, primary_field=primary_field)
if is_binary:
default_schema = cf.gen_default_binary_collection_schema(
auto_id=auto_id, dim=dim, primary_field=primary_field)
if is_all_data_type:
default_schema = cf.gen_collection_schema_all_datatype(
auto_id=auto_id, dim=dim, primary_field=primary_field)
log.info("init_collection_general: collection creation")
collection_w = self.init_collection_wrap(name=collection_name,
schema=default_schema,
**kwargs)
# 2 add extra partitions if specified (default is 1 partition named "_default")
if partition_num > 0:
cf.gen_partitions(collection_w, partition_num)
# 3 insert data if specified
if insert_data:
collection_w, vectors, binary_raw_vectors, insert_ids, time_stamp = \
cf.insert_data(collection_w, nb, is_binary, is_all_data_type, auto_id=auto_id, dim=dim)
if is_flush:
assert collection_w.is_empty is False
assert collection_w.num_entities == nb
# This condition will be removed after auto index feature
if not is_index:
collection_w.load()
return collection_w, vectors, binary_raw_vectors, insert_ids, time_stamp
def test_search_new_data(self):
"""
target: test search new inserted data without load
method: 1 search the collection
2 insert new data
3 search the collection without load again
expected: new data should be searched
"""
log.info("test_search_new_data: search new data without another load")
# 1. initialize with data
limit = 1000
nb_old = 500
collection_w = self.init_collection_general(prefix, True, nb_old)[0]
# 2. search for original data after load
vectors = [[random.random() for _ in range(default_dim)]
for _ in range(default_nq)]
log.info(
"test_search_new_data: searching for original data after load")
collection_w.search(vectors[:default_nq],
default_search_field,
default_search_params,
limit,
default_search_exp,
check_task=CheckTasks.check_search_results,
check_items={
"nq": default_nq,
"limit": nb_old
})
# 3. insert new data
nb_new = 300
cf.insert_data(collection_w, nb_new, False)
conn = self.connection_wrap.get_connection()[0]
conn.flush([collection_w.name])
# 4. search for new data without load
collection_w.search(vectors[:default_nq],
default_search_field,
default_search_params,
limit,
default_search_exp,
check_task=CheckTasks.check_search_results,
check_items={
"nq": default_nq,
"limit": nb_old + nb_new
})
def init_collection_general(self,
prefix,
insert_data=False,
nb=ct.default_nb,
partition_num=0,
is_binary=False,
is_all_data_type=False,
auto_id=False,
dim=ct.default_dim,
is_index=False):
"""
target: create specified collections
method: 1. create collections (binary/non-binary)
2. create partitions if specified
3. insert specified binary/non-binary data
into each partition if any
expected: return collection and raw data
"""
log.info("Test case of search interface: initialize before test case")
self._connect()
collection_name = cf.gen_unique_str(prefix)
vectors = []
binary_raw_vectors = []
insert_ids = []
# 1 create collection
default_schema = cf.gen_default_collection_schema(auto_id=auto_id,
dim=dim)
if is_binary:
default_schema = cf.gen_default_binary_collection_schema(
auto_id=auto_id, dim=dim)
if is_all_data_type:
default_schema = cf.gen_collection_schema_all_datatype(
auto_id=auto_id, dim=dim)
log.info("init_collection_general: collection creation")
collection_w = self.init_collection_wrap(name=collection_name,
schema=default_schema)
# 2 add extra partitions if specified (default is 1 partition named "_default")
if partition_num > 0:
cf.gen_partitions(collection_w, partition_num)
# 3 insert data if specified
if insert_data:
collection_w, vectors, binary_raw_vectors, insert_ids = \
cf.insert_data(collection_w, nb, is_binary, is_all_data_type,
auto_id=auto_id, dim=dim)
assert collection_w.is_empty is False
assert collection_w.num_entities == nb
# This condition will be removed after auto index feature
if not is_index:
collection_w.load()
return collection_w, vectors, binary_raw_vectors, insert_ids
def init_collection_general(self,
prefix,
insert_data=False,
nb=ct.default_nb,
partition_num=0,
is_binary=False):
"""
target: create specified collections
method: 1. create collections (binary/non-binary)
2. create partitions if specified
3. insert specified binary/non-binary data
into each partition if any
expected: return collection and raw data
"""
log.info("Test case of search interface: initialize before test case")
conn = self._connect()
collection_name = cf.gen_unique_str(prefix)
vectors = []
binary_raw_vectors = []
# 1 create collection
if is_binary:
default_schema = cf.gen_default_binary_collection_schema()
else:
default_schema = cf.gen_default_collection_schema()
log.info("init_collection_general: collection creation")
collection_w = self.init_collection_wrap(name=collection_name,
schema=default_schema)
# 2 add extra partitions if specified (default is 1 partition named "_default")
if partition_num > 0:
cf.gen_partitions(collection_w, partition_num)
# 3 insert data if specified
if insert_data:
collection_w, vectors, binary_raw_vectors = cf.insert_data(
collection_w, nb, is_binary)
if nb <= 32000:
conn.flush([collection_w.name])
assert collection_w.is_empty == False
assert collection_w.num_entities == nb
collection_w.load()
return collection_w, vectors, binary_raw_vectors
