Query Expert

-- ✅ Select only needed columns
SELECT
    user_id,
    email,
    created_at
FROM users
WHERE status = 'active'
    AND created_at > NOW() - INTERVAL '30 days'
ORDER BY created_at DESC
LIMIT 100;

-- ❌ Avoid SELECT *
SELECT * FROM users;  -- Wastes resources

-- INNER JOIN (most common)
SELECT
    o.order_id,
    o.total,
    c.name AS customer_name,
    c.email
FROM orders o
INNER JOIN customers c ON o.customer_id = c.customer_id
WHERE o.created_at >= '2024-01-01';

-- LEFT JOIN (include all left rows)
SELECT
    c.customer_id,
    c.name,
    COUNT(o.order_id) AS order_count,
    COALESCE(SUM(o.total), 0) AS total_spent
FROM customers c
LEFT JOIN orders o ON c.customer_id = o.customer_id
GROUP BY c.customer_id, c.name;

-- Multiple JOINs
SELECT
    o.order_id,
    c.name AS customer_name,
    p.product_name,
    oi.quantity,
    oi.price
FROM orders o
INNER JOIN customers c ON o.customer_id = c.customer_id
INNER JOIN order_items oi ON o.order_id = oi.order_id
INNER JOIN products p ON oi.product_id = p.product_id
WHERE o.status = 'completed';

-- Subquery in WHERE
SELECT name, email
FROM customers
WHERE customer_id IN (
    SELECT DISTINCT customer_id
    FROM orders
    WHERE total > 1000
);

-- Correlated subquery
SELECT
    c.name,
    (SELECT COUNT(*)
     FROM orders o
     WHERE o.customer_id = c.customer_id) AS order_count
FROM customers c;

-- ✅ Better: Use JOIN instead
SELECT
    c.name,
    COUNT(o.order_id) AS order_count
FROM customers c
LEFT JOIN orders o ON c.customer_id = o.customer_id
GROUP BY c.customer_id, c.name;

-- GROUP BY with aggregates
SELECT
    category,
    COUNT(*) AS product_count,
    AVG(price) AS avg_price,
    MIN(price) AS min_price,
    MAX(price) AS max_price,
    SUM(stock_quantity) AS total_stock
FROM products
GROUP BY category
HAVING COUNT(*) > 5
ORDER BY avg_price DESC;

-- Multiple GROUP BY columns
SELECT
    DATE_TRUNC('month', created_at) AS month,
    category,
    SUM(total) AS monthly_sales
FROM orders
GROUP BY DATE_TRUNC('month', created_at), category
ORDER BY month DESC, monthly_sales DESC;

-- ROLLUP for subtotals
SELECT
    COALESCE(category, 'TOTAL') AS category,
    COALESCE(brand, 'All Brands') AS brand,
    SUM(sales) AS total_sales
FROM products
GROUP BY ROLLUP(category, brand);

-- ROW_NUMBER
SELECT
    customer_id,
    order_date,
    total,
    ROW_NUMBER() OVER (
        PARTITION BY customer_id
        ORDER BY order_date DESC
    ) AS order_rank
FROM orders;

-- Running totals
SELECT
    order_date,
    total,
    SUM(total) OVER (
        ORDER BY order_date
        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW
    ) AS running_total
FROM orders;

-- RANK vs DENSE_RANK
SELECT
    product_name,
    sales,
    RANK() OVER (ORDER BY sales DESC) AS rank,
    DENSE_RANK() OVER (ORDER BY sales DESC) AS dense_rank,
    NTILE(4) OVER (ORDER BY sales DESC) AS quartile
FROM products;

-- LAG and LEAD
SELECT
    order_date,
    total,
    LAG(total, 1) OVER (ORDER BY order_date) AS prev_total,
    LEAD(total, 1) OVER (ORDER BY order_date) AS next_total,
    total - LAG(total, 1) OVER (ORDER BY order_date) AS change
FROM orders;

-- Simple CTE
WITH active_customers AS (
    SELECT customer_id, name, email
    FROM customers
    WHERE status = 'active'
)
SELECT
    ac.name,
    COUNT(o.order_id) AS order_count
FROM active_customers ac
LEFT JOIN orders o ON ac.customer_id = o.customer_id
GROUP BY ac.customer_id, ac.name;

-- Multiple CTEs
WITH
monthly_sales AS (
    SELECT
        DATE_TRUNC('month', order_date) AS month,
        SUM(total) AS sales
    FROM orders
    GROUP BY DATE_TRUNC('month', order_date)
),
avg_monthly AS (
    SELECT AVG(sales) AS avg_sales
    FROM monthly_sales
)
SELECT
    ms.month,
    ms.sales,
    am.avg_sales,
    ms.sales - am.avg_sales AS variance
FROM monthly_sales ms
CROSS JOIN avg_monthly am
ORDER BY ms.month;

-- Recursive CTE (hierarchies)
WITH RECURSIVE org_tree AS (
    -- Base case
    SELECT
        employee_id,
        name,
        manager_id,
        1 AS level,
        ARRAY[employee_id] AS path
    FROM employees
    WHERE manager_id IS NULL

    UNION ALL

    -- Recursive case
    SELECT
        e.employee_id,
        e.name,
        e.manager_id,
        ot.level + 1,
        ot.path || e.employee_id
    FROM employees e
    INNER JOIN org_tree ot ON e.manager_id = ot.employee_id
)
SELECT * FROM org_tree ORDER BY path;

-- Create index on frequently queried columns
CREATE INDEX idx_users_email ON users(email);
CREATE INDEX idx_orders_customer_date ON orders(customer_id, order_date);

-- Composite index (order matters!)
CREATE INDEX idx_orders_composite
ON orders(status, customer_id, order_date);

-- ✅ This query uses the index
SELECT * FROM orders
WHERE status = 'pending'
    AND customer_id = 123
    AND order_date > '2024-01-01';

-- ❌ This doesn't use the index (skips first column)
SELECT * FROM orders
WHERE customer_id = 123;

-- Partial/Filtered index (smaller, faster)
CREATE INDEX idx_active_users
ON users(email)
WHERE status = 'active';

-- Covering index (includes all needed columns)
CREATE INDEX idx_users_covering
ON users(email)
INCLUDE (name, created_at);

-- ❌ Bad: Retrieves all columns
SELECT * FROM users;

-- ✅ Good: Select only needed columns
SELECT user_id, email, name FROM users;

-- ✅ Good: More efficient for joins
SELECT
    u.user_id,
    u.email,
    o.order_id,
    o.total
FROM users u
INNER JOIN orders o ON u.user_id = o.user_id;

-- ❌ Bad: Filtering after JOIN
SELECT u.name, o.total
FROM users u
LEFT JOIN orders o ON u.user_id = o.user_id
WHERE o.status = 'completed';

-- ✅ Good: Filter before JOIN
SELECT u.name, o.total
FROM users u
INNER JOIN (
    SELECT user_id, total
    FROM orders
    WHERE status = 'completed'
) o ON u.user_id = o.user_id;

-- ✅ Even better: Use WHERE with INNER JOIN
SELECT u.name, o.total
FROM users u
INNER JOIN orders o ON u.user_id = o.user_id
WHERE o.status = 'completed';

-- ❌ Slower: IN with subquery
SELECT name FROM customers
WHERE customer_id IN (
    SELECT customer_id FROM orders WHERE total > 1000
);

-- ✅ Faster: EXISTS
SELECT name FROM customers c
WHERE EXISTS (
    SELECT 1 FROM orders o
    WHERE o.customer_id = c.customer_id
        AND o.total > 1000
);

-- ❌ Bad: Function prevents index usage
SELECT * FROM users
WHERE LOWER(email) = 'john@example.com';

-- ✅ Good: Use functional index
CREATE INDEX idx_users_email_lower ON users(LOWER(email));

-- Or use case-insensitive collation
SELECT * FROM users
WHERE email = 'john@example.com' COLLATE utf8_general_ci;

-- ✅ Use LIMIT/TOP for pagination
SELECT * FROM orders
ORDER BY created_at DESC
LIMIT 20 OFFSET 0;

-- ✅ Use WHERE to reduce rows early
SELECT * FROM orders
WHERE created_at > NOW() - INTERVAL '7 days'
ORDER BY created_at DESC;

-- ❌ Bad: Multiple single inserts
INSERT INTO users (name, email) VALUES ('User1', 'user1@example.com');
INSERT INTO users (name, email) VALUES ('User2', 'user2@example.com');

-- ✅ Good: Batch insert
INSERT INTO users (name, email) VALUES
    ('User1', 'user1@example.com'),
    ('User2', 'user2@example.com'),
    ('User3', 'user3@example.com');

-- ✅ Good: Batch update
UPDATE products
SET price = price * 1.1
WHERE category IN ('Electronics', 'Computers');

-- Simple EXPLAIN
EXPLAIN
SELECT * FROM orders WHERE customer_id = 123;

-- EXPLAIN ANALYZE (actually runs query)
EXPLAIN ANALYZE
SELECT
    c.name,
    COUNT(o.order_id) AS order_count
FROM customers c
LEFT JOIN orders o ON c.customer_id = o.customer_id
GROUP BY c.customer_id, c.name;

-- Look for:
-- - Seq Scan (bad, needs index)
-- - Index Scan (good)
-- - Bitmap Heap Scan (good for multiple rows)
-- - Hash Join vs Nested Loop
-- - High cost numbers

-- EXPLAIN
EXPLAIN
SELECT * FROM orders WHERE customer_id = 123;

-- EXPLAIN ANALYZE (MySQL 8.0.18+)
EXPLAIN ANALYZE
SELECT * FROM orders WHERE customer_id = 123;

-- Look for:
-- - type: ALL (table scan, bad)
-- - type: index (index scan, good)
-- - type: ref (index lookup, great)
-- - Extra: Using filesort (may need index)
-- - Extra: Using temporary (may need optimization)