py-hive-iomete 2.1.5

DB-API

from pyhive import hive

connection = hive.connect(
    host="<data_plane_host>",
    port=<data_plane_port>,
    scheme="http", # or "https"
    lakehouse="<lakehouse_cluster_name>",
    data_plane=None # or data_plane (namespace)
    database="default",
    username="<username>",
    password="<password>"
)

cursor = connection.cursor()
cursor.execute("SELECT * FROM my_awesome_data LIMIT 10")

print(cursor.fetchone())
print(cursor.fetchall())

DB-API (asynchronous)

from pyhive import hive
from TCLIService.ttypes import TOperationState

connection = hive.connect(
    host="<data_plane_host>",
    port=<data_plane_port>,
    scheme="http", # or "https"
    lakehouse="<lakehouse_cluster_name>",
    data_plane=None # or data_plane (namespace)
    database="default",
    username="<username>",
    password="<password>"
)

cursor = connection.cursor()

cursor.execute("SELECT * FROM my_awesome_data LIMIT 10", async_=True)

status = cursor.poll().operationState

while status in (TOperationState.INITIALIZED_STATE, TOperationState.RUNNING_STATE):
    logs = cursor.fetch_logs()
    for message in logs:
        print(message)

    # If needed, an asynchronous query can be cancelled at any time with:
    # cursor.cancel()

    status = cursor.poll().operationState

print(cursor.fetchall())

SQLAlchemy

First install this package to register it with SQLAlchemy (see setup.py).

from sqlalchemy.engine import create_engine
from sqlalchemy.orm import sessionmaker
from sqlalchemy.schema import *

# Possible dialects (hive and iomete are both operate identically):
# hive+http
# hive+https
# iomete+http
# iomete+https
engine = create_engine(
    'iomete+https://<username>:<password>@<data_plane_host>:<data_plane_port>/<database>?lakehouse=<lakehouse_cluster_name>')

# or with data_plane specified
# engine = create_engine(
#    'iomete+https://<username>:<password>@<data_plane_host>:<data_plane_port>/<database>?lakehouse=<lakehouse_cluster_name>&data_plane=<data_plane>')

# Alternatively, "hive" driver could be used as well
# engine = create_engine(
#    'hive+https://<username>:<password>@<data_plane_host>:<data_plane_port>/<database>?lakehouse=<lakehouse_cluster_name>')

session = sessionmaker(bind=engine)()
records = session.query(Table('my_awesome_data', MetaData(bind=engine), autoload=True)) \
    .limit(10) \
    .all()
print(records)

Note: query generation functionality is not exhaustive or fully tested, but there should be no problem with raw SQL.