milvus/tests/python_client/milvus_client/test_milvus_client_delete.py

import pytest

from base.client_v2_base import TestMilvusClientV2Base
from utils.util_log import test_log as log
from common import common_func as cf
from common import common_type as ct
from common.common_type import CaseLabel, CheckTasks
from utils.util_pymilvus import *

prefix = "client_delete"
epsilon = ct.epsilon
default_nb = ct.default_nb
default_nb_medium = ct.default_nb_medium
default_nq = ct.default_nq
default_dim = ct.default_dim
default_limit = ct.default_limit
default_search_exp = "id >= 0"
exp_res = "exp_res"
default_search_string_exp = "varchar >= \"0\""
default_search_mix_exp = "int64 >= 0 && varchar >= \"0\""
default_invaild_string_exp = "varchar >= 0"
default_json_search_exp = "json_field[\"number\"] >= 0"
perfix_expr = 'varchar like "0%"'
default_search_field = ct.default_float_vec_field_name
default_search_params = ct.default_search_params
default_primary_key_field_name = "id"
default_vector_field_name = "vector"
default_float_field_name = ct.default_float_field_name
default_bool_field_name = ct.default_bool_field_name
default_string_field_name = ct.default_string_field_name
default_int32_array_field_name = ct.default_int32_array_field_name
default_string_array_field_name = ct.default_string_array_field_name


class TestMilvusClientDeleteInvalid(TestMilvusClientV2Base):
    """ Test case of search interface """

    @pytest.fixture(scope="function", params=[False, True])
    def auto_id(self, request):
        yield request.param

    @pytest.fixture(scope="function", params=["COSINE", "L2"])
    def metric_type(self, request):
        yield request.param

    """
    ******************************************************************
    #  The following are invalid base cases
    ******************************************************************
    """

    @pytest.mark.tags(CaseLabel.L1)
    def test_milvus_client_delete_with_filters_and_ids(self):
        """
        target: test delete (high level api) with ids and filters
        method: create connection, collection, insert, delete, and search
        expected: raise exception
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. insert
        default_nb = 1000
        rng = np.random.default_rng(seed=19530)
        rows = [{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
                 default_float_field_name: i * 1.0, default_string_field_name: str(i)} for i in range(default_nb)]
        pks = self.insert(client, collection_name, rows)[0]
        # 3. delete
        delete_num = 3
        self.delete(client, collection_name, ids=[i for i in range(delete_num)], filter=f"id < {delete_num}",
                    check_task=CheckTasks.err_res,
                    check_items={"err_code": 1,
                                 "err_msg": "Ambiguous filter parameter, "
                                            "only one deletion condition can be specified."})
        self.drop_collection(client, collection_name)

    @pytest.mark.tags(CaseLabel.L1)
    @pytest.mark.xfail(reason="pymilvus issue 1869")
    def test_milvus_client_delete_with_invalid_id_type(self):
        """
        target: test delete (high level api)
        method: create connection, collection, insert delete, and search
        expected: search/query successfully without deleted data
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. delete
        self.delete(client, collection_name, ids=0,
                    check_task=CheckTasks.err_res,
                    check_items={"err_code": 1,
                                 "err_msg": "expr cannot be empty"})

    @pytest.mark.tags(CaseLabel.L2)
    def test_milvus_client_delete_with_not_all_required_params(self):
        """
        target: test delete (high level api)
        method: create connection, collection, insert delete, and search
        expected: search/query successfully without deleted data
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. delete
        self.delete(client, collection_name,
                    check_task=CheckTasks.err_res,
                    check_items={"err_code": 999,
                                 "err_msg": "The type of expr must be string ,but <class 'NoneType'> is given."})


class TestMilvusClientDeleteValid(TestMilvusClientV2Base):
    """ Test case of search interface """

    @pytest.fixture(scope="function", params=[False, True])
    def auto_id(self, request):
        yield request.param

    @pytest.fixture(scope="function", params=["COSINE", "L2"])
    def metric_type(self, request):
        yield request.param

    """
    ******************************************************************
    #  The following are valid base cases
    ******************************************************************
    """

    @pytest.mark.tags(CaseLabel.L1)
    def test_milvus_client_delete_with_ids(self):
        """
        target: test delete (high level api)
        method: create connection, collection, insert delete, and search
        expected: search/query successfully without deleted data
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. insert
        default_nb = 1000
        rng = np.random.default_rng(seed=19530)
        rows = [{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
                 default_float_field_name: i * 1.0, default_string_field_name: str(i)} for i in range(default_nb)]
        pks = self.insert(client, collection_name, rows)[0]
        # 3. delete
        delete_num = 3
        self.delete(client, collection_name, ids=[i for i in range(delete_num)])
        # 4. search
        vectors_to_search = rng.random((1, default_dim))
        insert_ids = [i for i in range(default_nb)]
        for insert_id in range(delete_num):
            if insert_id in insert_ids:
                insert_ids.remove(insert_id)
        limit = default_nb - delete_num
        self.search(client, collection_name, vectors_to_search, limit=default_nb,
                    check_task=CheckTasks.check_search_results,
                    check_items={"enable_milvus_client_api": True,
                                 "nq": len(vectors_to_search),
                                 "ids": insert_ids,
                                 "limit": limit})
        # 5. query
        self.query(client, collection_name, filter=default_search_exp,
                   check_task=CheckTasks.check_query_results,
                   check_items={exp_res: rows[delete_num:],
                                "with_vec": True,
                                "primary_field": default_primary_key_field_name})
        self.drop_collection(client, collection_name)

    @pytest.mark.tags(CaseLabel.L1)
    def test_milvus_client_delete_with_filters(self):
        """
        target: test delete (high level api)
        method: create connection, collection, insert delete, and search
        expected: search/query successfully without deleted data
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. insert
        default_nb = 1000
        rng = np.random.default_rng(seed=19530)
        rows = [{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
                 default_float_field_name: i * 1.0, default_string_field_name: str(i)} for i in range(default_nb)]
        pks = self.insert(client, collection_name, rows)[0]
        # 3. delete
        delete_num = 3
        self.delete(client, collection_name, filter=f"id < {delete_num}")
        # 4. search
        vectors_to_search = rng.random((1, default_dim))
        insert_ids = [i for i in range(default_nb)]
        for insert_id in range(delete_num):
            if insert_id in insert_ids:
                insert_ids.remove(insert_id)
        limit = default_nb - delete_num
        self.search(client, collection_name, vectors_to_search, limit=default_nb,
                    check_task=CheckTasks.check_search_results,
                    check_items={"enable_milvus_client_api": True,
                                 "nq": len(vectors_to_search),
                                 "ids": insert_ids,
                                 "limit": limit})
        # 5. query
        self.query(client, collection_name, filter=default_search_exp,
                   check_task=CheckTasks.check_query_results,
                   check_items={exp_res: rows[delete_num:],
                                "with_vec": True,
                                "primary_field": default_primary_key_field_name})
        self.drop_collection(client, collection_name)

    @pytest.mark.tags(CaseLabel.L1)
    def test_milvus_client_delete_with_filters_partition(self):
        """
        target: test delete (high level api)
        method: create connection, collection, insert delete, and search
        expected: search/query successfully without deleted data
        """
        client = self._client()
        collection_name = cf.gen_unique_str(prefix)
        # 1. create collection
        self.create_collection(client, collection_name, default_dim, consistency_level="Strong")
        # 2. insert
        default_nb = 1000
        rng = np.random.default_rng(seed=19530)
        rows = [{default_primary_key_field_name: i, default_vector_field_name: list(rng.random((1, default_dim))[0]),
                 default_float_field_name: i * 1.0, default_string_field_name: str(i)} for i in range(default_nb)]
        pks = self.insert(client, collection_name, rows)[0]
        # 3. get partition lists
        partition_names = self.list_partitions(client, collection_name)
        # 4. delete
        delete_num = 3
        self.delete(client, collection_name, filter=f"id < {delete_num}", partition_names=partition_names)
        # 5. search
        vectors_to_search = rng.random((1, default_dim))
        insert_ids = [i for i in range(default_nb)]
        for insert_id in range(delete_num):
            if insert_id in insert_ids:
                insert_ids.remove(insert_id)
        limit = default_nb - delete_num
        self.search(client, collection_name, vectors_to_search, limit=default_nb,
                    check_task=CheckTasks.check_search_results,
                    check_items={"enable_milvus_client_api": True,
                                 "nq": len(vectors_to_search),
                                 "ids": insert_ids,
                                 "limit": limit})
        # 6. query
        self.query(client, collection_name, filter=default_search_exp,
                   check_task=CheckTasks.check_query_results,
                   check_items={exp_res: rows[delete_num:],
                                "with_vec": True,
                                "primary_field": default_primary_key_field_name})
        self.drop_collection(client, collection_name)