python 操作hive pyhs2

使用kerberos时

import pyhs2

class HiveClient:
    # 初始化
    def __init__(self, db_host, user, password, database, port=10000, authMechanism="PLAIN", configuration=None):
        self.conn = pyhs2.connect(host=db_host,
                                  port=port,
                                  authMechanism=authMechanism,
                                  user=user,
                                  password=password,
                                  database=database,
                                  configuration=configuration,
                                  )

    # 查询方法
    def query(self, sql):
        with self.conn.cursor() as cursor:
            cursor.execute(sql)
            return cursor.fetch()

    def close(self):
        self.conn.close()


def getHiveData(sql):
    config = {"mapreduce.job.queuename": "default", 'krb_host': 'hiveserve2ip', 'krb_service': 'hive'}
    hive_client = HiveClient(db_host='hiveserve2ip', port=10000, user='user@kdc.com', password='hive', database='dw.usee',
                             authMechanism='KERBEROS', configuration=config)
    print  sql
    result = hive_client.query(sql)
    return result

Could not start SASL: Error in sasl_client_start (-1) SASL(-1)

安装
yum install cyrus-sasl-plain cyrus-sasl-devel cyrus-sasl-gssapi

pyhs2 安装 sasl问题

yum install cyrus-sasl-devel
yum install cyrus-sasl-lib
yum install libgsasl-devel
yum install saslwrapper

对接superset hive kerberos

SQLAlchemy URI

hive://herverser2ip:10000/db

扩展 连接参数

{
    "metadata_params": {},
    "engine_params": {
        "connect_args": {
        "auth": "KERBEROS",
                "kerberos_service_name": "hive",
        "username" : "user@KDC.COM"
        }
    }
}