[feat] Support Hive Conn (#1215)

Co-authored-by: xiuzhu <edy@dodge-pro.local>

dbgpt/datasource/manages/connection_manager.py

@@ -9,6 +9,7 @@ from dbgpt.datasource.rdbms.base import RDBMSDatabase
 from dbgpt.datasource.rdbms.conn_clickhouse import ClickhouseConnect
 from dbgpt.datasource.rdbms.conn_doris import DorisConnect
 from dbgpt.datasource.rdbms.conn_duckdb import DuckDbConnect
+from dbgpt.datasource.rdbms.conn_hive import HiveConnect
 from dbgpt.datasource.rdbms.conn_mssql import MSSQLConnect
 from dbgpt.datasource.rdbms.conn_mysql import MySQLConnect
 from dbgpt.datasource.rdbms.conn_postgresql import PostgreSQLDatabase

dbgpt/datasource/rdbms/conn_hive.py

@@ -0,0 +1,58 @@
+from typing import Any, Optional
+from urllib.parse import quote
+from urllib.parse import quote_plus as urlquote
+
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+from dbgpt.datasource.rdbms.base import RDBMSDatabase
+
+
+class HiveConnect(RDBMSDatabase):
+    """db type"""
+
+    db_type: str = "hive"
+    """db driver"""
+    driver: str = "hive"
+    """db dialect"""
+    dialect: str = "hive"
+
+    @classmethod
+    def from_uri_db(
+        cls,
+        host: str,
+        port: int,
+        user: str,
+        pwd: str,
+        db_name: str,
+        engine_args: Optional[dict] = None,
+        **kwargs: Any,
+    ) -> RDBMSDatabase:
+        """Construct a SQLAlchemy engine from uri database.
+        Args:
+            host (str): database host.
+            port (int): database port.
+            user (str): database user.
+            pwd (str): database password.
+            db_name (str): database name.
+            engine_args (Optional[dict]):other engine_args.
+        """
+        db_url: str = f"{cls.driver}://{host}:{str(port)}/{db_name}"
+        if user and pwd:
+            db_url: str = f"{cls.driver}://{quote(user)}:{urlquote(pwd)}@{host}:{str(port)}/{db_name}"
+        return cls.from_uri(db_url, engine_args, **kwargs)
+
+    def table_simple_info(self):
+        return []
+
+    def get_users(self):
+        return []
+
+    def get_grants(self):
+        return []
+
+    def get_collation(self):
+        """Get collation."""
+        return "UTF-8"
+
+    def get_charset(self):
+        return "UTF-8"

dbgpt/storage/schema.py

@@ -20,6 +20,7 @@ class DBType(Enum):
     StarRocks = DbInfo("starrocks")
     Spark = DbInfo("spark", True)
     Doris = DbInfo("doris")
+    Hive = DbInfo("hive")
 
     def value(self):
         return self._value_.name

setup.py

@@ -568,6 +568,9 @@ def all_datasource_requires():
         "mysqlclient==2.1.0",
         "pydoris>=1.0.2,<2.0.0",
         "clickhouse-connect",
+        "pyhive",
+        "thrift",
+        "thrift_sasl",
     ]
 
 

web/utils/constants.ts

@@ -64,5 +64,6 @@ export const dbMapper: Record<DBType, { label: string; icon: string; desc: strin
     desc: 'Powerful open-source relational database with extensibility and SQL standards.',
   },
   spark: { label: 'Spark', icon: '/icons/spark.png', desc: 'Unified engine for large-scale data analytics.' },
+  hive: { label: 'Hive', icon: '/icons/hive.png', desc: 'A distributed fault-tolerant data warehouse system.' },
   space: { label: 'Space', icon: '/icons/knowledge.png', desc: 'knowledge analytics.' },
 };