PyHive-Hack 0.2.1b1

DB-API

from pyhive import presto
cursor = presto.connect('localhost').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
cursor = hive.connect('localhost').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 import *
from sqlalchemy.engine import create_engine
from sqlalchemy.schema import *
engine = create_engine('presto://localhost:8080/hive/default')
logs = Table('my_awesome_data', MetaData(bind=engine), autoload=True)
print select([func.count('*')], from_obj=logs).scalar()

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

Passing session configuration

# DB-API
hive.connect('localhost', configuration={'hive.exec.reducers.max': '123'})
presto.connect('localhost', session_props={'query_max_run_time': '1234m'})
# SQLAlchemy
create_engine(
    'hive://user@host:10000/database',
    connect_args={'configuration': {'hive.exec.reducers.max': '123'}},
)