-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Feature]Add StarRocks 2.5+ DB adapter
- Loading branch information
Showing
8 changed files
with
462 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,147 @@ | ||
from typing import Iterable, Optional, Any | ||
from sqlalchemy import text | ||
from urllib.parse import quote | ||
import re | ||
from pilot.connections.rdbms.base import RDBMSDatabase | ||
from pilot.connections.rdbms.dialect.starrocks.sqlalchemy import * | ||
|
||
|
||
class StarRocksConnect(RDBMSDatabase): | ||
driver = "starrocks" | ||
db_type = "starrocks" | ||
db_dialect = "starrocks" | ||
|
||
@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: | ||
db_url: str = ( | ||
f"{cls.driver}://{quote(user)}:{quote(pwd)}@{host}:{str(port)}/{db_name}" | ||
) | ||
return cls.from_uri(db_url, engine_args, **kwargs) | ||
|
||
def _sync_tables_from_db(self) -> Iterable[str]: | ||
db_name = self.get_current_db_name() | ||
table_results = self.session.execute(text(f'SELECT TABLE_NAME FROM information_schema.tables where TABLE_SCHEMA="{db_name}"' )) | ||
#view_results = self.session.execute(text(f'SELECT TABLE_NAME from information_schema.materialized_views where TABLE_SCHEMA="{db_name}"')) | ||
table_results = set(row[0] for row in table_results) | ||
#view_results = set(row[0] for row in view_results) | ||
self._all_tables = table_results | ||
self._metadata.reflect(bind=self._engine) | ||
return self._all_tables | ||
|
||
def get_grants(self): | ||
session = self._db_sessions() | ||
cursor = session.execute(text("SHOW GRANTS")) | ||
grants = cursor.fetchall() | ||
if len(grants) == 0: | ||
return [] | ||
if len(grants[0]) == 2: | ||
grants_list = [x[1] for x in grants] | ||
else: | ||
grants_list = [x[2] for x in grants] | ||
return grants_list | ||
|
||
def _get_current_version(self): | ||
"""Get database current version""" | ||
return int(self.session.execute(text("select current_version()")).scalar()) | ||
|
||
def get_collation(self): | ||
"""Get collation.""" | ||
# StarRocks 排序是表级别的 | ||
return None | ||
|
||
def get_users(self): | ||
"""Get user info.""" | ||
return [] | ||
|
||
def get_fields(self, table_name, db_name="database()"): | ||
"""Get column fields about specified table.""" | ||
session = self._db_sessions() | ||
if db_name != "database()": | ||
db_name = f'"{db_name}"' | ||
cursor = session.execute( | ||
text( | ||
f'select COLUMN_NAME, COLUMN_TYPE, COLUMN_DEFAULT, IS_NULLABLE, COLUMN_COMMENT from information_schema.columns where TABLE_NAME="{table_name}" and TABLE_SCHEMA = {db_name}' | ||
) | ||
) | ||
fields = cursor.fetchall() | ||
return [(field[0], field[1], field[2], field[3], field[4]) for field in fields] | ||
|
||
def get_charset(self): | ||
"""Get character_set.""" | ||
|
||
return "utf-8" | ||
|
||
def get_show_create_table(self, table_name): | ||
# cur = self.session.execute( | ||
# text( | ||
# f"""show create table {table_name}""" | ||
# ) | ||
# ) | ||
# rows = cur.fetchone() | ||
# create_sql = rows[0] | ||
|
||
# return create_sql | ||
# 这里是要表描述, 返回建表语句会导致token过长而失败 | ||
cur = self.session.execute( | ||
text( | ||
f'SELECT TABLE_COMMENT FROM information_schema.tables where TABLE_NAME="{table_name}" and TABLE_SCHEMA=database()' | ||
) | ||
) | ||
table = cur.fetchone() | ||
if table: | ||
return str(table[0]) | ||
else: | ||
return "" | ||
|
||
def get_table_comments(self, db_name=None): | ||
if not db_name: | ||
db_name = self.get_current_db_name() | ||
cur = self.session.execute( | ||
text( | ||
f'SELECT TABLE_NAME,TABLE_COMMENT FROM information_schema.tables where TABLE_SCHEMA="{db_name}"' | ||
) | ||
) | ||
tables = cur.fetchall() | ||
return [(table[0], table[1]) for table in tables] | ||
|
||
def get_database_list(self): | ||
return self.get_database_names() | ||
|
||
def get_database_names(self): | ||
session = self._db_sessions() | ||
cursor = session.execute(text("SHOW DATABASES;")) | ||
results = cursor.fetchall() | ||
return [ | ||
d[0] | ||
for d in results | ||
if d[0] not in ["information_schema", "sys", "_statistics_", "dataease"] | ||
] | ||
|
||
def get_current_db_name(self) -> str: | ||
return self.session.execute(text("select database()")).scalar() | ||
|
||
def table_simple_info(self): | ||
_sql = f""" | ||
SELECT concat(TABLE_NAME,"(",group_concat(COLUMN_NAME,","),");") FROM information_schema.columns where TABLE_SCHEMA=database() | ||
GROUP BY TABLE_NAME | ||
""" | ||
cursor = self.session.execute(text(_sql)) | ||
results = cursor.fetchall() | ||
return [x[0] for x in results] | ||
|
||
def get_indexes(self, table_name): | ||
"""Get table indexes about specified table.""" | ||
session = self._db_sessions() | ||
cursor = session.execute(text(f"SHOW INDEX FROM {table_name}")) | ||
indexes = cursor.fetchall() | ||
return [(index[2], index[4]) for index in indexes] | ||
|
Empty file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,14 @@ | ||
#! /usr/bin/python3 | ||
# Copyright 2021-present StarRocks, Inc. All rights reserved. | ||
# | ||
# Licensed under the Apache License, Version 2.0 (the "License"); | ||
# you may not use this file except in compliance with the License. | ||
# You may obtain a copy of the License at | ||
# | ||
# https:#www.apache.org/licenses/LICENSE-2.0 | ||
# | ||
# Unless required by applicable law or agreed to in writing, software | ||
# distributed under the License is distributed on an "AS IS" BASIS, | ||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
# See the License for the specific language governing permissions and | ||
# limitations under the License. |
22 changes: 22 additions & 0 deletions
22
pilot/connections/rdbms/dialect/starrocks/sqlalchemy/__init__.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,22 @@ | ||
#! /usr/bin/python3 | ||
# Copyright 2021-present StarRocks, Inc. All rights reserved. | ||
# | ||
# Licensed under the Apache License, Version 2.0 (the "License"); | ||
# you may not use this file except in compliance with the License. | ||
# You may obtain a copy of the License at | ||
# | ||
# https:#www.apache.org/licenses/LICENSE-2.0 | ||
# | ||
# Unless required by applicable law or agreed to in writing, software | ||
# distributed under the License is distributed on an "AS IS" BASIS, | ||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
# See the License for the specific language governing permissions and | ||
# limitations under the License. | ||
|
||
from sqlalchemy.dialects import registry | ||
|
||
registry.register( | ||
"starrocks", | ||
"pilot.connections.rdbms.dialect.starrocks.sqlalchemy.dialect", | ||
"StarRocksDialect", | ||
) |
104 changes: 104 additions & 0 deletions
104
pilot/connections/rdbms/dialect/starrocks/sqlalchemy/datatype.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,104 @@ | ||
import logging | ||
import re | ||
from typing import Optional, List, Any, Type, Dict | ||
|
||
from sqlalchemy import Numeric, Integer, Float | ||
from sqlalchemy.sql import sqltypes | ||
from sqlalchemy.sql.type_api import TypeEngine | ||
|
||
logger = logging.getLogger(__name__) | ||
|
||
|
||
class TINYINT(Integer): # pylint: disable=no-init | ||
__visit_name__ = "TINYINT" | ||
|
||
|
||
class LARGEINT(Integer): # pylint: disable=no-init | ||
__visit_name__ = "LARGEINT" | ||
|
||
|
||
class DOUBLE(Float): # pylint: disable=no-init | ||
__visit_name__ = "DOUBLE" | ||
|
||
|
||
class HLL(Numeric): # pylint: disable=no-init | ||
__visit_name__ = "HLL" | ||
|
||
|
||
class BITMAP(Numeric): # pylint: disable=no-init | ||
__visit_name__ = "BITMAP" | ||
|
||
|
||
class PERCENTILE(Numeric): # pylint: disable=no-init | ||
__visit_name__ = "PERCENTILE" | ||
|
||
|
||
class ARRAY(TypeEngine): # pylint: disable=no-init | ||
__visit_name__ = "ARRAY" | ||
|
||
@property | ||
def python_type(self) -> Optional[Type[List[Any]]]: | ||
return list | ||
|
||
|
||
class MAP(TypeEngine): # pylint: disable=no-init | ||
__visit_name__ = "MAP" | ||
|
||
@property | ||
def python_type(self) -> Optional[Type[Dict[Any, Any]]]: | ||
return dict | ||
|
||
|
||
class STRUCT(TypeEngine): # pylint: disable=no-init | ||
__visit_name__ = "STRUCT" | ||
|
||
@property | ||
def python_type(self) -> Optional[Type[Any]]: | ||
return None | ||
|
||
|
||
_type_map = { | ||
# === Boolean === | ||
"boolean": sqltypes.BOOLEAN, | ||
# === Integer === | ||
"tinyint": sqltypes.SMALLINT, | ||
"smallint": sqltypes.SMALLINT, | ||
"int": sqltypes.INTEGER, | ||
"bigint": sqltypes.BIGINT, | ||
"largeint": LARGEINT, | ||
# === Floating-point === | ||
"float": sqltypes.FLOAT, | ||
"double": DOUBLE, | ||
# === Fixed-precision === | ||
"decimal": sqltypes.DECIMAL, | ||
# === String === | ||
"varchar": sqltypes.VARCHAR, | ||
"char": sqltypes.CHAR, | ||
"json": sqltypes.JSON, | ||
# === Date and time === | ||
"date": sqltypes.DATE, | ||
"datetime": sqltypes.DATETIME, | ||
"timestamp": sqltypes.DATETIME, | ||
# === Structural === | ||
"array": ARRAY, | ||
"map": MAP, | ||
"struct": STRUCT, | ||
"hll": HLL, | ||
"percentile": PERCENTILE, | ||
"bitmap": BITMAP, | ||
} | ||
|
||
|
||
def parse_sqltype(type_str: str) -> TypeEngine: | ||
type_str = type_str.strip().lower() | ||
match = re.match(r"^(?P<type>\w+)\s*(?:\((?P<options>.*)\))?", type_str) | ||
if not match: | ||
logger.warning(f"Could not parse type name '{type_str}'") | ||
return sqltypes.NULLTYPE | ||
type_name = match.group("type") | ||
|
||
if type_name not in _type_map: | ||
logger.warning(f"Did not recognize type '{type_name}'") | ||
return sqltypes.NULLTYPE | ||
type_class = _type_map[type_name] | ||
return type_class() |
Oops, something went wrong.