python操作Kudu

具體步驟如下：
import kudu
from kudu.client import Partitioning
from datetime import datetime

# 連接到kudu主服務器
client = kudu.connect(host='kudu.master', port=7051)

# 為新表定義架構
builder = kudu.schema_builder()
builder.add_column('key').type(kudu.int64).nullable(False).primary_key()
builder.add_column('ts_val', type_=kudu.unixtime_micros, nullable=False, compression='lz4')
schema = builder.build()

# 定義分區模式
partitioning = Partitioning().add_hash_partitions(column_names=['key'], num_buckets=3)

# 創建新表
client.create_table('python-example', schema, partitioning)

# 打開表
table = client.table('python-example')

# 創建一個新會話用於操作表
session = client.new_session()

# 往表插入數據
op = table.new_insert({'key': 1, 'ts_val': datetime.utcnow()})
session.apply(op)

# 更新插入，即有則更新，無則插入
op = table.new_upsert({'key': 2, 'ts_val': "2016-01-01T00:00:00.000000"})
session.apply(op)

# 更新行
op = table.new_update({'key': 1, 'ts_val': ("2017-01-01", "%Y-%m-%d")})
session.apply(op)

# 刪除數據
op = table.new_delete({'key': 2})
session.apply(op)

# 刷新寫入操作，如果發生異常，則捕獲異常並打印.
try:
    session.flush()
except kudu.KuduBadStatus as e:
    print(session.get_pending_errors())

# 創建一個掃描，並增加一個python-example表的斷言
scanner = table.scanner()
scanner.add_predicate(table['ts_val'] == datetime(2017, 1, 1))

# 打開掃描儀並讀取所有元組
# 注: 這不適用於大掃描
result = scanner.open().read_all_tuples()