sqlalchemy_drill_connect_query_parquet_workspace.py

1from sqlalchemy import create_engine
2from sqlalchemy.schema import Table, MetaData
3
4# Connection string for Apache Drill (Standard format)
5# drill+sadrill://<username>:<password>@<host>:<port>/<storage_plugin>/<workspace>
6engine = create_engine('drill+sadrill://localhost:8047/dfs/test')
7
8# Initialize metadata and reflect a specific table (e.g., a parquet file)
9metadata = MetaData()
10user_data = Table('user_data.parquet', metadata, autoload=True, autoload_with=engine)
11
12# Execute a standard SELECT query
13connection = engine.connect()
14query = user_data.select()
15result = connection.execute(query)
16
17for row in result:
18    print(row)
19
20connection.close()