ClickHouse 中的存储过程和查询参数

-- 简单计算函数
CREATE FUNCTION calculate_tax AS (price, rate) -> price * rate;

SELECT
    product_name,
    price,
    calculate_tax(price, 0.08) AS tax
FROM products;

-- 使用 if() 的条件逻辑
CREATE FUNCTION price_tier AS (price) ->
    if(price < 100, 'Budget',
       if(price < 500, 'Mid-range', 'Premium'));

SELECT
    product_name,
    price,
    price_tier(price) AS tier
FROM products;

-- 字符串操作
CREATE FUNCTION format_phone AS (phone) ->
    concat('(', substring(phone, 1, 3), ') ',
           substring(phone, 4, 3), '-',
           substring(phone, 7, 4));

SELECT format_phone('5551234567');
-- 结果：(555) 123-4567

<!-- /etc/clickhouse-server/sentiment_analysis_function.xml -->
<functions>
    <function>
        <type>executable</type>
        <name>sentiment_score</name>
        <return_type>Float32</return_type>
        <argument>
            <type>String</type>
        </argument>
        <format>TabSeparated</format>
        <command>python3 /opt/scripts/sentiment.py</command>
    </function>
</functions>

-- 使用 executable UDF
SELECT
    review_text,
    sentiment_score(review_text) AS score
FROM customer_reviews;

-- 创建参数化视图
CREATE VIEW sales_by_date AS
SELECT
    date,
    product_id,
    sum(quantity) AS total_quantity,
    sum(revenue) AS total_revenue
FROM sales
WHERE date BETWEEN {start_date:Date} AND {end_date:Date}
GROUP BY date, product_id;

-- 使用参数查询视图
SELECT *
FROM sales_by_date(start_date='2024-01-01', end_date='2024-01-31')
WHERE product_id = 12345;

-- 更复杂的参数化视图
CREATE VIEW top_products_by_category AS
SELECT
    category,
    product_name,
    revenue,
    rank
FROM (
    SELECT
        category,
        product_name,
        revenue,
        rank() OVER (PARTITION BY category ORDER BY revenue DESC) AS rank
    FROM (
        SELECT
            category,
            product_name,
            sum(sales_amount) AS revenue
        FROM sales
        WHERE category = {category:String}
            AND date >= {min_date:Date}
        GROUP BY category, product_name
    )
)
WHERE rank <= {top_n:UInt32};

-- 使用示例
SELECT * FROM top_products_by_category(
    category='Electronics',
    min_date='2024-01-01',
    top_n=10
);

-- 源表
CREATE TABLE page_views (
    user_id UInt64,
    page String,
    timestamp DateTime,
    session_id String
)
ENGINE = MergeTree()
ORDER BY (user_id, timestamp);

-- 维护聚合统计信息的 materialized view
CREATE MATERIALIZED VIEW daily_user_stats
ENGINE = SummingMergeTree()
ORDER BY (date, user_id)
AS SELECT
    toDate(timestamp) AS date,
    user_id,
    count() AS page_views,
    uniq(session_id) AS sessions,
    uniq(page) AS unique_pages
FROM page_views
GROUP BY date, user_id;

-- 向源表插入样本数据
INSERT INTO page_views VALUES
(101, '/home', '2024-01-15 10:00:00', 'session_a1'),
(101, '/products', '2024-01-15 10:05:00', 'session_a1'),
(101, '/checkout', '2024-01-15 10:10:00', 'session_a1'),
(102, '/home', '2024-01-15 11:00:00', 'session_b1'),
(102, '/about', '2024-01-15 11:05:00', 'session_b1'),
(101, '/home', '2024-01-16 09:00:00', 'session_a2'),
(101, '/products', '2024-01-16 09:15:00', 'session_a2'),
(103, '/home', '2024-01-16 14:00:00', 'session_c1'),
(103, '/products', '2024-01-16 14:05:00', 'session_c1'),
(103, '/products', '2024-01-16 14:10:00', 'session_c1'),
(102, '/home', '2024-01-17 10:30:00', 'session_b2'),
(102, '/contact', '2024-01-17 10:35:00', 'session_b2');

-- 查询预聚合数据
SELECT
    user_id,
    sum(page_views) AS total_views,
    sum(sessions) AS total_sessions
FROM daily_user_stats
WHERE date BETWEEN '2024-01-01' AND '2024-01-31'
GROUP BY user_id;

-- 每天凌晨 2 点自动刷新
CREATE MATERIALIZED VIEW monthly_sales_report
REFRESH EVERY 1 DAY OFFSET 2 HOUR
AS SELECT
    toStartOfMonth(order_date) AS month,
    region,
    product_category,
    count() AS order_count,
    sum(amount) AS total_revenue,
    avg(amount) AS avg_order_value
FROM orders
WHERE order_date >= today() - INTERVAL 13 MONTH
GROUP BY month, region, product_category;

-- 查询始终获取最新数据
SELECT * FROM monthly_sales_report
WHERE month = toStartOfMonth(today());

SET param_user_id = 12345;
SET param_start_date = '2024-01-01';
SET param_end_date = '2024-01-31';

SELECT
    event_name,
    count() AS event_count
FROM user_events
WHERE user_id = {user_id: UInt64}
    AND event_date BETWEEN {start_date: Date} AND {end_date: Date}
GROUP BY event_name;

clickhouse-client \
    --param_user_id=12345 \
    --param_start_date='2024-01-01' \
    --param_end_date='2024-01-31' \
    --query="SELECT count() FROM user_events
             WHERE user_id = {user_id: UInt64}
             AND event_date BETWEEN {start_date: Date} AND {end_date: Date}"

-- ✓ WHERE 子句中的值
SELECT * FROM users WHERE id = {user_id: UInt64};

-- ✓ 表/数据库名称
SELECT * FROM {db: Identifier}.{table: Identifier};

-- ✓ IN 子句中的值
SELECT * FROM products WHERE id IN {ids: Array(UInt32)};

-- ✓ CREATE TABLE
CREATE TABLE {table_name: Identifier} (id UInt64, name String) ENGINE = MergeTree() ORDER BY id;

-- ✗ SELECT 中的列名（谨慎使用 Identifier）
SELECT {column: Identifier} FROM users;  -- 支持有限

-- ✗ 任意 SQL 片段
SELECT * FROM users {where_clause: String};  -- 不支持

-- ✗ ALTER TABLE 语句
ALTER TABLE {table: Identifier} ADD COLUMN new_col String;  -- 不支持

-- ✗ 多条语句
{statements: String};  -- 不支持

# ✓ 安全 - 使用参数
user_input = request.get('user_id')
result = client.query(
    "SELECT * FROM orders WHERE user_id = {uid: UInt64}",
    parameters={'uid': user_input}
)

# ✗ 危险 - 存在 SQL 注入风险！
user_input = request.get('user_id')
result = client.query(f"SELECT * FROM orders WHERE user_id = {user_input}")

def get_user_orders(user_id: int, start_date: str):
    # 查询前验证类型
    if not isinstance(user_id, int) or user_id <= 0:
        raise ValueError("Invalid user_id")

    # 参数确保类型安全
    return client.query(
        """
        SELECT * FROM orders
        WHERE user_id = {uid: UInt64}
            AND order_date >= {start: Date}
        """,
        parameters={'uid': user_id, 'start': start_date}
    )

-- 这种带参数的 MySQL 风格预处理语句在 ClickHouse 中不起作用
PREPARE stmt FROM 'SELECT * FROM users WHERE id = ?';
EXECUTE stmt USING @user_id;  -- 不支持参数绑定