python下建立elasticsearch索引实现大数据搜索——之编程实现（三）

Go on.......

接下来我们来实现ElasticGraphObj类，上面已经得到包含有相关需求的素材list，那么该类的目的是根据得到的material list可以找到相应的设计graph

3. ElasticGraphObj类

• 3.1 __init__方法

 def __init__(self,index_name,index_type,ip="127.0.0.1"):
        '''
        :param index_name: 索引名
        :param index_type: 索引类型
        :param ip: ip
        '''
        self.index_name = index_name
        self.index_type = index_type
        # 无用户名密码状态
        self.esObj = Elasticsearch([ip])
        # 用户名密码状态
        # self.esObj = Elasticsearch([ip],http_auth=('elastic', 'password'),port=9200)

• 3.2 create_index方法

    def create_index(self,index_name='stylepatternshow',index_type='stylepatternshow_type'):
        '''
        创建索引,创建索引名称为stylepatternshow，类型为stylepatternshow_type的索引
        :param index_name:
        :param index_type:
        :return:
        '''
        # 创建索引
        _index_mappings = {
            "mappings": {
                self.index_type: {
                    "properties": {
                        "id": {
                            "type": "long",
                            "index": "false"
                        },
                        "serial": {
                            "type": "text",  # keyword不会进行分词,text会分词,默认按空格切分
                            "index": "false"  # 不建索引
                        },
                        "taskType": {
                            "type": "long",
                            "index": "false"
                        },
                        "taskParam": {
                            "type": "text",
                            "index": True
                        },
                        "createTime": {
                            "type": "date",
                            "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis"
                        }
                    }
                }
            }
        }
        if self.esObj.indices.exists(index = self.index_name) is not True:
            res = self.esObj.indices.create(index = self.index_name,body = _index_mappings)
            print('index is create->',res)
        else:
            print('index is already exist')

• 3.3 bulk_Index_Data方法

 def bulk_Index_Data(self, jsonFile):
        '''
        用bulk将批量数据存储到es
        :return:
        '''
        with open(jsonFile, 'r') as load_f:
            load_json = json.load(load_f)
        ACTIONS = []
        i = 1
        for line in load_json:
            if line['status'] == 1 and (line['taskType'] == 500 or line['taskType'] == 501):
               taskParam_dict = json.loads(line['taskParam'])
               if 'main_groups' in taskParam_dict.keys():
                   layers_list = taskParam_dict['main_groups'][0]['layers']
                   serial_set = self.get_singel_serial_set(layers_list)
                   serial_str = ""
                    '''为了利用es本身的standard分析器，能够把空格切割，故意构造带空格material serial的字符串'''
                   for col in serial_set:
                       serial_str += col+' '
                   if serial_str == "":
                        continue
                   action = {
                        "_index": self.index_name,
                        "_type": self.index_type,
                        "_id": i,  # _id 也可以默认生成，不赋值
                        "_source": {
                            "id": line['id'],
                            "serial": line['serial'],
                            "taskType":line['taskType'],
                            "taskParam