ClickHouse Connect 驱动 API

import clickhouse_connect

client = clickhouse_connect.get_client()
print(client.server_version)

import clickhouse_connect

client = clickhouse_connect.get_client(
    host="play.clickhouse.com",
    secure=True,
    port=443,
    username="play",
    password="clickhouse",
)
print(client.command("SELECT timezone()"))

import clickhouse_connect

client = clickhouse_connect.get_client(
    host="play.clickhouse.com",
    username="play",
    password="clickhouse",
    port=443,
    secure=True,
    session_id="example_session_1",
    connect_timeout=15,
    database="github",
    settings={"distributed_ddl_task_timeout": 300},
)
print(client.database)
# Output: github

import clickhouse_connect

with clickhouse_connect.get_client(interface="chdb") as client:
    result = client.query("SELECT sum(number) FROM numbers(10)")
    print(result.first_row)
    # Output: (45,)

import clickhouse_connect

# Create once at startup
client = clickhouse_connect.get_client(
    host="my-host",
    username="default",
    password="password",
)

# Reuse for all queries
for i in range(1000):
    result = client.query("SELECT count() FROM users")

# Close on shutdown
client.close()

# BAD: Creates 1000 clients with expensive initialization overhead
for i in range(1000):
    client = clickhouse_connect.get_client(
        host="my-host",
        username="default",
        password="password",
    )
    result = client.query("SELECT count() FROM users")
    client.close()

import clickhouse_connect
import threading

# Option 1: Disable sessions (recommended for shared clients)
client = clickhouse_connect.get_client(
    host="my-host",
    username="default",
    password="password",
    autogenerate_session_id=False,
)

def worker(thread_id):
    # All threads can now safely use the same client
    result = client.query(f"SELECT {thread_id}")
    print(f"Thread {thread_id}: {result.result_rows[0][0]}")

threads = [threading.Thread(target=worker, args=(i,)) for i in range(10)]
for t in threads:
    t.start()
for t in threads:
    t.join()

client.close()

def worker(thread_id):
    # Each thread gets its own client with isolated session
    client = clickhouse_connect.get_client(
        host="my-host",
        username="default",
        password="password",
    )
    client.command("CREATE TEMPORARY TABLE temp (id UInt32) ENGINE = Memory")
    # ... use temp table ...
    client.close()

client = clickhouse_connect.get_client(
    host="my-host",
    username="default",
    password="password",
)
try:
    result = client.query("SELECT 1")
finally:
    client.close()

with clickhouse_connect.get_client(
    host="my-host",
    username="default",
    password="password",
) as client:
    result = client.query("SELECT 1")

import datetime

my_date = datetime.datetime(2022, 10, 1, 15, 20, 5)

parameters = {
    "table": "my_table",
    "v1": my_date,
    "v2": "a string with a single quote'",
}
client.query(
    "SELECT * FROM {table:Identifier} "
    "WHERE date >= {v1:DateTime} AND string ILIKE {v2:String}",
    parameters=parameters,
)

SELECT *
FROM my_table
WHERE date >= '2022-10-01 15:20:05'
  AND string ILIKE 'a string with a single quote\''

import datetime

my_date = datetime.datetime(2022, 10, 1, 15, 20, 5)

parameters = {"v1": my_date, "v2": "a string with a single quote'"}
client.query(
    "SELECT * FROM my_table "
    "WHERE date >= %(v1)s AND string ILIKE %(v2)s",
    parameters=parameters,
)

SELECT *
FROM my_table
WHERE date >= '2022-10-01 15:20:05'
  AND string ILIKE 'a string with a single quote\''

import ipaddress

parameters = (35200.44, ipaddress.IPv4Address(0x443d04fe))
client.query(
    "SELECT * FROM some_table WHERE metric >= %s AND ip_address = %s",
    parameters=parameters,
)

SELECT *
FROM some_table
WHERE metric >= 35200.44
  AND ip_address = '68.61.4.254'

settings = {
    "merge_tree_min_rows_for_concurrent_read": 65535,
    "session_id": "session_1234",
    "use_skip_indexes": False,
}
client.query(
    "SELECT event_type, sum(timeout) "
    "FROM event_errors WHERE event_time > '2022-08-01'",
    settings=settings,
)

import clickhouse_connect

client = clickhouse_connect.get_client()

# Create a table. A successful DDL returns QuerySummary.
summary = client.command(
    "CREATE TABLE test_command "
    "(col_1 String, col_2 DateTime) "
    "ENGINE MergeTree ORDER BY tuple()"
)
print(summary.query_id())

# Show table definition
result = client.command("SHOW CREATE TABLE test_command")
print(result)
# Output:
# CREATE TABLE default.test_command
# (
#     `col_1` String,
#     `col_2` DateTime
# )
# ENGINE = MergeTree
# ORDER BY tuple()

# Drop table
client.command("DROP TABLE test_command")

import clickhouse_connect

client = clickhouse_connect.get_client()

# Single value result
count = client.command("SELECT count() FROM system.tables")
print(count)

# Server version
version = client.command("SELECT version()")
print(version)

import clickhouse_connect

client = clickhouse_connect.get_client()

# 使用客户端参数
table_name = "system"
result = client.command(
    "SELECT count() FROM system.tables WHERE database = %(db)s",
    parameters={"db": table_name}
)

# 使用服务端参数
result = client.command(
    "SELECT count() FROM system.tables WHERE database = {db:String}",
    parameters={"db": "system"}
)

import clickhouse_connect

client = clickhouse_connect.get_client()

# 使用特定设置执行命令
result = client.command(
    "OPTIMIZE TABLE large_table FINAL",
    settings={"optimize_throw_if_noop": 1}
)

import clickhouse_connect

client = clickhouse_connect.get_client()

# Simple SELECT query
result = client.query(
    "SELECT number, toString(number) AS label FROM numbers(3)"
)

# Access results as rows
for row in result.result_rows:
    print(row)
# Output:
# (0, '0')
# (1, '1')
# (2, '2')

# Access column names and types
print(result.column_names)
# Output: ('number', 'label')
print([col_type.name for col_type in result.column_types])
# Output: ['UInt64', 'String']

import clickhouse_connect

client = clickhouse_connect.get_client()

result = client.query("SELECT number, toString(number) AS str FROM system.numbers LIMIT 3")

# Row-oriented access (default)
print(result.result_rows)
# Output: [(0, '0'), (1, '1'), (2, '2')]

# Column-oriented access
print(result.result_columns)
# Output: [[0, 1, 2], ['0', '1', '2']]

# Named results (list of dictionaries)
for row_dict in result.named_results():
    print(row_dict)
# Output:
# {'number': 0, 'str': '0'}
# {'number': 1, 'str': '1'}
# {'number': 2, 'str': '2'}

# First row as dictionary
print(result.first_item)
# Output: {'number': 0, 'str': '0'}

# First row as tuple
print(result.first_row)
# Output: (0, '0')

import clickhouse_connect

client = clickhouse_connect.get_client()

# 使用字典参数（printf 风格）
query = "SELECT * FROM system.tables WHERE database = %(db)s AND name LIKE %(pattern)s"
parameters = {"db": "system", "pattern": "%query%"}
result = client.query(query, parameters=parameters)

# 使用 Tuple 参数
query = "SELECT * FROM system.tables WHERE database = %s LIMIT %s"
parameters = ("system", 5)
result = client.query(query, parameters=parameters)

import clickhouse_connect

client = clickhouse_connect.get_client()

# 服务器端绑定（更安全，SELECT 查询性能更佳）
query = "SELECT * FROM system.tables WHERE database = {db:String} AND name = {tbl:String}"
parameters = {"db": "system", "tbl": "query_log"}

result = client.query(query, parameters=parameters)

import clickhouse_connect

client = clickhouse_connect.get_client()

# 在查询中传递 ClickHouse 设置
result = client.query(
    "SELECT sum(number) FROM numbers(1000000)",
    settings={
        "max_block_size": 100000,
        "max_execution_time": 30
    }
)

import clickhouse_connect

client = clickhouse_connect.get_client()

# Row-oriented data: each inner list is a row
data = [
    [13, "user_1", 25],
    [79, "user_2", 30],
]

client.insert("users", data, column_names=["id", "name", "age"])

import clickhouse_connect

client = clickhouse_connect.get_client()

# Column-oriented data: each inner list is a column
data = [
    [13, 79],  # id column
    ["user_1", "user_2"],  # name column
    [25, 30],  # age column
]

client.insert("users", data, column_names=["id", "name", "age"], column_oriented=True)

import clickhouse_connect

client = clickhouse_connect.get_client()

# Useful when you want to avoid a DESCRIBE query to the server
data = [
    [13, "user_1", 25],
    [79, "user_2", 30],
]

client.insert(
    "users",
    data,
    column_names=["id", "name", "age"],
    column_type_names=["UInt32", "String", "UInt8"],
)

import clickhouse_connect

client = clickhouse_connect.get_client()

data = [
    [13, "user_1", 25],
    [79, "user_2", 30],
]

# Insert into a table in a specific database
client.insert(
    "users",
    data,
    column_names=["id", "name", "age"],
    database="production",
)

from clickhouse_connect import dbapi

connection = dbapi.connect(
    host="localhost",
    username="default",
    password="password",
    database="default",
)
cursor = connection.cursor()

try:
    cursor.execute(
        "SELECT name FROM system.tables "
        "WHERE database = %(database)s ORDER BY name LIMIT 5",
        {"database": "system"},
    )
    print(cursor.description)
    print(cursor.fetchall())
finally:
    cursor.close()
    connection.close()