Add one-skill

one-skill/smart-data-developer/references/sql/templates/spark/create-table-template.sql

@@ -0,0 +1,176 @@
+-- =====================================================================
+-- @SparkSqlName:    PAIMONA-D-SQL-{表名}-CREATE
+-- @Version:         1.0
+-- @Desc:            建表模板（CREATE TABLE）
+-- @TargetTables:    {新表名}
+-- @TargetDatabase:  Paimon
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：基础表创建（非分区）
+-- ============================================================================
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.basic_table (
+    -- 主键/标识字段
+    id BIGINT COMMENT '主键ID',
+    
+    -- 业务字段
+    name STRING COMMENT '名称',
+    category STRING COMMENT '类别',
+    amount DECIMAL(18,2) COMMENT '金额',
+    status STRING COMMENT '状态',
+    
+    -- 时间字段
+    created_at TIMESTAMP COMMENT '创建时间',
+    updated_at TIMESTAMP COMMENT '更新时间',
+    
+    -- 技术字段
+    etl_time TIMESTAMP COMMENT '数据加工时间',
+    etl_remark STRING COMMENT '备注信息'
+)
+COMMENT '基础业务表'
+STORED AS PARQUET;                   -- 存储格式
+
+-- ============================================================================
+-- 场景2：分区表创建（单分区字段）
+-- ============================================================================
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.partitioned_table (
+    -- 主键/标识字段
+    id BIGINT COMMENT '主键ID',
+    
+    -- 业务字段
+    user_id STRING COMMENT '用户ID',
+    user_name STRING COMMENT '用户姓名',
+    order_count BIGINT COMMENT '订单数',
+    total_amount DECIMAL(18,2) COMMENT '总金额',
+    
+    -- 维度字段
+    department STRING COMMENT '部门',
+    region STRING COMMENT '地区',
+    
+    -- 技术字段
+    etl_time TIMESTAMP COMMENT '数据加工时间'
+)
+COMMENT '按日分区的统计表'
+PARTITIONED BY (day_id STRING COMMENT '统计日期，格式yyyy-MM-dd')
+STORED AS PARQUET;
+
+-- ============================================================================
+-- 场景3：多分区字段表
+-- ============================================================================
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.multi_partition_table (
+    id BIGINT COMMENT '主键ID',
+    name STRING COMMENT '名称',
+    amount DECIMAL(18,2) COMMENT '金额',
+    etl_time TIMESTAMP COMMENT '数据加工时间'
+)
+COMMENT '多分区字段示例表'
+PARTITIONED BY (
+    year_id STRING COMMENT '年份',
+    month_id STRING COMMENT '月份'
+)
+STORED AS PARQUET;
+
+-- ============================================================================
+-- 场景4：带表属性配置
+-- ============================================================================
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.configured_table (
+    id BIGINT COMMENT '主键ID',
+    name STRING COMMENT '名称',
+    amount DECIMAL(18,2) COMMENT '金额',
+    etl_time TIMESTAMP COMMENT '数据加工时间'
+)
+COMMENT '带属性配置的表'
+PARTITIONED BY (day_id STRING)
+STORED AS PARQUET
+TBLPROPERTIES (
+    'parquet.compression' = 'SNAPPY',           -- 压缩格式
+    'spark.sql.partitionOverwriteMode' = 'dynamic'  -- 动态分区覆盖模式
+);
+
+-- ============================================================================
+-- 场景5：Paimon 表创建（主键表）
+-- ============================================================================
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.paimon_pk_table (
+    -- 主键字段（Paimon 主键表必须包含所有主键字段）
+    id BIGINT COMMENT '主键ID',
+    day_id STRING COMMENT '分区日期',
+    
+    -- 业务字段
+    name STRING COMMENT '名称',
+    amount DECIMAL(18,2) COMMENT '金额',
+    status STRING COMMENT '状态',
+    
+    -- 技术字段
+    etl_time TIMESTAMP COMMENT '数据加工时间'
+)
+COMMENT 'Paimon 主键表（支持 MERGE INTO）'
+PARTITIONED BY (day_id)
+TBLPROPERTIES (
+    'primary-key' = 'id,day_id',                -- 主键定义
+    'bucket' = '4',                              -- 分桶数
+    'changelog-producer' = 'input'               -- 变更日志生产
+);
+
+-- ============================================================================
+-- 场景6：临时表创建
+-- ============================================================================
+CREATE TEMPORARY TABLE tmp_processing_table (
+    id BIGINT,
+    name STRING,
+    amount DECIMAL(18,2)
+);
+
+-- 或使用 AS 创建临时表
+CREATE TEMPORARY TABLE tmp_source AS
+SELECT id, name, amount
+FROM source_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 字段类型速查
+-- ============================================================================
+/*
+| 类型          | 说明           | 适用场景               |
+|---------------|----------------|------------------------|
+| STRING        | 字符串         | 名称、编码、描述       |
+| INT           | 整数           | 数量、等级、标志       |
+| BIGINT        | 大整数         | ID、计数、金额（整数） |
+| DECIMAL(p,s)  | 定点数         | 金额、比例、精度数值   |
+| DOUBLE        | 浮点数         | 科学计算（慎用于金额） |
+| BOOLEAN       | 布尔           | 状态标志               |
+| DATE          | 日期           | 日期字段               |
+| TIMESTAMP     | 时间戳         | 时间字段               |
+| ARRAY<type>   | 数组           | 多值字段               |
+| MAP<k,v>      | 映射           | 属性字典               |
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 字段命名规范
+   - 使用 snake_case：user_id, total_amount
+   - 主键：id 或 {业务}_id
+   - 技术字段：etl_time, etl_remark
+
+2. COMMENT 必须添加
+   - 每个字段必须有 COMMENT
+   - 表必须有 COMMENT
+
+3. 分区字段选择
+   - 按时间分区：day_id, month_id
+   - 分区粒度：日分区最常用
+
+4. 存储格式
+   - 推荐：PARQUET（列存储，压缩好）
+   - 可选：ORC、AVRO
+
+5. Paimon 表特性
+   - primary-key：主键字段列表
+   - bucket：分桶数（影响并发）
+   - 支持 MERGE INTO 操作
+
+6. 表属性配置
+   - 压缩格式：SNAPPY（推荐）、GZIP、LZ4
+   - 动态分区模式：dynamic（推荐）
+*/

one-skill/smart-data-developer/references/sql/templates/spark/etl-template.sql

@@ -0,0 +1,148 @@
+-- =====================================================================
+-- @SparkSqlName:    PAIMONA-D-SQL-{表名}-ETL
+-- @Version:         1.0
+-- @Desc:            ETL 数据处理模板（临时表链式处理）
+-- @TargetTables:    ${db_eda_env}.{目标表名}
+-- @SourceTables:    {源表列表}
+-- @TargetDatabase:  Paimon
+-- @SourceDatabase:  Paimon
+-- @任务调度频度:    {日/周/月}
+-- @修改记录:
+--  版本号          更新时间       更新人员       更新内容
+--  V1.0            {日期}        {人员}          创建脚本
+-- @数据处理步骤：
+-- Step01: {步骤描述}
+-- Step02: {步骤描述}
+-- Step03: {步骤描述}
+-- 参数说明
+-- 账期参数：
+-- ${day_id}         日账期，格式：20250101
+-- 环境变量:
+-- 变量名                       测试环境值                生产环境值
+-- ${db_tmp_env}        {库名}                  {库名}
+-- ${db_eda_env}        {库名}                  {库名}
+-- =====================================================================
+
+-- ============================================================================
+-- Step01: 基础清洗与过滤
+-- ============================================================================
+-- 说明：从源表读取数据，进行基础过滤和清洗
+-- 输入：{源表名}
+-- 输出：${db_tmp_env}.tmp_{表名}_01
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_01;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    id,
+    name,
+    amount,
+    status,
+    created_at,
+    day_id
+FROM source_table
+WHERE day_id = '${day_id}'              -- 分区过滤（必须）
+  AND status IN ('active', 'valid')    -- 业务过滤
+  AND amount > 0                       -- 数据质量过滤
+  AND id IS NOT NULL                   -- NULL过滤;
+
+-- ============================================================================
+-- Step02: 多表关联与维度补全
+-- ============================================================================
+-- 说明：关联维度表，补全业务属性字段
+-- 输入：${db_tmp_env}.tmp_xxx_01, {维度表1}, {维度表2}
+-- 输出：${db_tmp_env}.tmp_xxx_02
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_02;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_02 AS
+SELECT 
+    a.id,
+    a.name,
+    a.amount,
+    a.status,
+    b.category_name,                    -- 维度补全：类别名称
+    c.department_name,                  -- 维度补全：部门名称
+    a.created_at,
+    a.day_id
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN dim_category b 
+    ON a.category_id = b.id
+    AND b.day_id = '${day_id}'          -- 维度表分区过滤
+LEFT JOIN dim_department c 
+    ON a.department_id = c.id
+    AND c.day_id = '${day_id}';         -- 维度表分区过滤
+
+-- ============================================================================
+-- Step03: 聚合计算与指标生成
+-- ============================================================================
+-- 说明：按业务维度聚合，计算统计指标
+-- 输入：${db_tmp_env}.tmp_xxx_02
+-- 输出：${db_tmp_env}.tmp_xxx_03
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_03;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_03 AS
+SELECT 
+    day_id,
+    category_name,
+    department_name,
+    COUNT(*) AS record_count,           -- 记录数
+    COUNT(DISTINCT id) AS unique_count, -- 唯一计数
+    SUM(amount) AS total_amount,        -- 总金额
+    AVG(amount) AS avg_amount,          -- 平均金额
+    MAX(amount) AS max_amount,          -- 最大金额
+    MIN(amount) AS min_amount           -- 最小金额
+FROM ${db_tmp_env}.tmp_xxx_02
+GROUP BY day_id, category_name, department_name;
+
+-- ============================================================================
+-- Step04: 最终输出写入目标表
+-- ============================================================================
+-- 说明：补全目标表标准字段，写入结果表
+-- 输入：${db_tmp_env}.tmp_xxx_03
+-- 输出：${db_eda_env}.{目标表名}
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+PARTITION (day_id = '${day_id}')
+SELECT 
+    -- 业务字段
+    category_name,
+    department_name,
+    record_count,
+    unique_count,
+    total_amount,
+    avg_amount,
+    max_amount,
+    min_amount,
+    
+    -- 技术字段
+    current_timestamp() AS etl_time,    -- 数据加工时间
+    '${day_id}' AS stat_date            -- 统计日期;
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. 禁止使用 CTE (WITH 子句)
+   - 每个步骤必须物化为临时表
+   - 原因：避免内存溢出，便于调试和断点续跑
+
+2. 先 DROP 再 CREATE
+   - 每个临时表创建前必须先 DROP
+   - 原因：防止表已存在导致失败
+
+3. 分区过滤必须前置
+   - 所有源表和维度表查询必须带 day_id 过滤
+   - 原因：避免全表扫描，提升性能
+
+4. JOIN 条件下推
+   - 维度表关联时带上分区过滤条件
+   - 原因：减少关联数据量
+
+5. 临时表命名规范
+   - 格式：tmp_{业务简称}_{步骤序号}
+   - 示例：tmp_order_stats_01, tmp_order_stats_02
+
+6. 目标表写入规范
+   - 使用 INSERT OVERWRITE（覆盖写入）
+   - 明确指定分区
+   - 补全技术字段（etl_time 等）
+*/

one-skill/smart-data-developer/references/sql/templates/spark/insert-template.sql

@@ -0,0 +1,131 @@
+-- =====================================================================
+-- @SparkSqlName:    PAIMONA-D-SQL-{表名}-INSERT
+-- @Version:         1.0
+-- @Desc:            数据插入模板（INSERT OVERWRITE）
+-- @TargetTables:    ${db_eda_env}.{目标表名}
+-- @SourceTables:    {源表列表}
+-- @TargetDatabase:  Paimon
+-- @SourceDatabase:  Paimon
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：分区表覆盖写入
+-- ============================================================================
+-- 适用：每日/每周/每月增量写入分区表
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+PARTITION (day_id = '${day_id}')
+SELECT 
+    field1,
+    field2,
+    field3,
+    current_timestamp() AS etl_time
+FROM source_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 场景2：动态分区写入
+-- ============================================================================
+-- 适用：多分区字段，数据中包含分区值
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+PARTITION (day_id, region)        -- 动态分区字段
+SELECT 
+    field1,
+    field2,
+    field3,
+    day_id,                        -- 分区字段1（数据中包含）
+    region,                        -- 分区字段2（数据中包含）
+    current_timestamp() AS etl_time
+FROM source_table
+WHERE day_id BETWEEN '${start_day}' AND '${end_day}';
+
+-- ============================================================================
+-- 场景3：全表覆盖写入
+-- ============================================================================
+-- 适用：全量刷新、初始化数据
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+SELECT 
+    field1,
+    field2,
+    field3,
+    current_timestamp() AS etl_time
+FROM source_table;
+
+-- ============================================================================
+-- 场景4：追加写入（慎用）
+-- ============================================================================
+-- 适用：日志表、流水表（无分区或允许重复）
+
+INSERT INTO TABLE ${db_eda_env}.target_table
+SELECT 
+    field1,
+    field2,
+    field3,
+    current_timestamp() AS etl_time
+FROM source_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 场景5：从临时表写入目标表
+-- ============================================================================
+-- 适用：ETL 流程最后一步
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+PARTITION (day_id = '${day_id}')
+SELECT 
+    -- 业务字段（与目标表字段顺序一致）
+    user_id,
+    user_name,
+    order_count,
+    total_amount,
+    
+    -- 技术字段
+    current_timestamp() AS etl_time,
+    '${day_id}' AS stat_date
+FROM ${db_tmp_env}.tmp_xxx_final;
+
+-- ============================================================================
+-- 场景6：MERGE INTO（更新插入）
+-- ============================================================================
+-- 适用：增量更新、修正历史数据
+
+MERGE INTO ${db_eda_env}.target_table t
+USING ${db_tmp_env}.tmp_xxx_source s
+ON t.id = s.id AND t.day_id = s.day_id
+WHEN MATCHED THEN 
+    UPDATE SET 
+        t.name = s.name,
+        t.amount = s.amount,
+        t.etl_time = current_timestamp()
+WHEN NOT MATCHED THEN 
+    INSERT (id, day_id, name, amount, etl_time)
+    VALUES (s.id, s.day_id, s.name, s.amount, current_timestamp());
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. INSERT OVERWRITE vs INSERT INTO
+   - INSERT OVERWRITE：覆盖写入（推荐）
+   - INSERT INTO：追加写入（可能导致重复数据）
+
+2. 分区表写入必须指定分区
+   - 避免全表覆盖导致历史数据丢失
+   - 格式：PARTITION (day_id = '${day_id}')
+
+3. 字段顺序必须与目标表一致
+   - 目标表字段顺序：业务字段 → 技术字段 → 分区字段
+   - SELECT 字段顺序必须匹配
+
+4. 技术字段补全
+   - etl_time：数据写入时间
+   - stat_date：统计日期（可选）
+   - etl_remark：备注信息（可选）
+
+5. MERGE INTO 注意事项
+   - Spark 3.x+ 支持
+   - 目标表必须支持事务（如 Paimon/Delta）
+   - 关联字段必须唯一（避免多条匹配）
+*/

one-skill/smart-data-developer/references/sql/templates/spark/partition-template.sql

@@ -0,0 +1,179 @@
+-- =====================================================================
+-- @SparkSqlName:    PAIMONA-D-SQL-{表名}-PARTITION
+-- @Version:         1.0
+-- @Desc:            分区表操作模板
+-- @TargetTables:    {分区表名}
+-- @TargetDatabase:  Paimon
+-- =====================================================================
+
+-- ============================================================================
+-- 分区表创建
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.daily_partition_table (
+    id BIGINT COMMENT '主键ID',
+    user_id STRING COMMENT '用户ID',
+    amount DECIMAL(18,2) COMMENT '金额',
+    etl_time TIMESTAMP COMMENT '数据加工时间'
+)
+COMMENT '按日分区表'
+PARTITIONED BY (day_id STRING COMMENT '统计日期')
+STORED AS PARQUET;
+
+-- ============================================================================
+-- 分区写入操作
+-- ============================================================================
+
+-- 1. 静态分区写入（指定分区值）
+INSERT OVERWRITE TABLE ${db_eda_env}.daily_partition_table
+PARTITION (day_id = '2026-05-09')
+SELECT 
+    id,
+    user_id,
+    amount,
+    current_timestamp() AS etl_time
+FROM source_table
+WHERE day_id = '${day_id}';
+
+-- 2. 动态分区写入（数据中包含分区值）
+-- 需要先设置动态分区模式
+SET spark.sql.partitionOverwriteMode = dynamic;
+
+INSERT OVERWRITE TABLE ${db_eda_env}.daily_partition_table
+PARTITION (day_id)                    -- 动态分区字段
+SELECT 
+    id,
+    user_id,
+    amount,
+    current_timestamp() AS etl_time,
+    day_id                            -- 数据中包含分区值
+FROM source_table
+WHERE day_id BETWEEN '2026-05-01' AND '2026-05-09';
+
+-- ============================================================================
+-- 分区查询操作
+-- ============================================================================
+
+-- 3. 单分区查询
+SELECT *
+FROM ${db_eda_env}.daily_partition_table
+WHERE day_id = '2026-05-09';
+
+-- 4. 多分区查询
+SELECT *
+FROM ${db_eda_env}.daily_partition_table
+WHERE day_id IN ('2026-05-01', '2026-05-02', '2026-05-03');
+
+-- 5. 分区范围查询
+SELECT *
+FROM ${db_eda_env}.daily_partition_table
+WHERE day_id >= '2026-05-01'
+  AND day_id <= '2026-05-09';
+
+-- 6. 最近 N 天分区查询（动态计算）
+SELECT *
+FROM ${db_eda_env}.daily_partition_table
+WHERE day_id >= date_format(date_sub(current_date(), 30), 'yyyy-MM-dd');
+
+-- ============================================================================
+-- 分区管理操作
+-- ============================================================================
+
+-- 7. 查看分区列表
+SHOW PARTITIONS ${db_eda_env}.daily_partition_table;
+
+-- 8. 查看特定分区详情
+DESCRIBE EXTENDED ${db_eda_env}.daily_partition_table PARTITION (day_id = '2026-05-09');
+
+-- 9. 添加分区（手动创建空分区，部分表类型支持）
+ALTER TABLE ${db_eda_env}.daily_partition_table
+ADD IF NOT EXISTS PARTITION (day_id = '2026-05-10');
+
+-- 10. 删除分区（清理历史数据）
+ALTER TABLE ${db_eda_env}.daily_partition_table
+DROP IF EXISTS PARTITION (day_id = '2026-01-01');
+
+-- ============================================================================
+-- 多分区字段操作
+-- ============================================================================
+
+-- 11. 多分区字段表创建
+CREATE TABLE IF NOT EXISTS ${db_eda_env}.multi_partition_table (
+    id BIGINT,
+    name STRING,
+    amount DECIMAL(18,2),
+    etl_time TIMESTAMP
+)
+PARTITIONED BY (year_id STRING, month_id STRING)
+STORED AS PARQUET;
+
+-- 12. 多分区字段写入
+INSERT OVERWRITE TABLE ${db_eda_env}.multi_partition_table
+PARTITION (year_id = '2026', month_id = '05')
+SELECT 
+    id,
+    name,
+    amount,
+    current_timestamp() AS etl_time
+FROM source_table
+WHERE year_id = '2026' AND month_id = '05';
+
+-- 13. 多分区字段动态写入
+SET spark.sql.partitionOverwriteMode = dynamic;
+
+INSERT OVERWRITE TABLE ${db_eda_env}.multi_partition_table
+PARTITION (year_id, month_id)
+SELECT 
+    id,
+    name,
+    amount,
+    current_timestamp() AS etl_time,
+    year_id,
+    month_id
+FROM source_table;
+
+-- ============================================================================
+-- 分区数据清理
+-- ============================================================================
+
+-- 14. 清理指定分区数据
+INSERT OVERWRITE TABLE ${db_eda_env}.daily_partition_table
+PARTITION (day_id = '2026-05-09')
+SELECT * FROM ${db_eda_env}.daily_partition_table
+WHERE day_id = '2026-05-09'
+  AND status = 'valid';              -- 只保留有效数据
+
+-- 15. 清理 N 天前分区（批量）
+-- 使用脚本或程序循环执行
+-- ALTER TABLE xxx DROP PARTITION (day_id = '历史分区')
+
+-- ============================================================================
+-- 分区最佳实践
+-- ============================================================================
+/*
+1. 分区字段选择原则
+   - 查询高频过滤字段
+   - 数据量分布均匀的字段
+   - 时间字段最常用（day_id, month_id）
+
+2. 分区粒度选择
+   - 日增量数据 → day_id 分区
+   - 月增量数据 → month_id 分区
+   - 大数据量 → 可细分到 hour_id
+
+3. 分区数量控制
+   - 单表分区数建议 < 10000
+   - 过多分区影响元数据性能
+
+4. 查询必须带分区过滤
+   - 避免：SELECT * FROM table（全表扫描）
+   - 推荐：SELECT * FROM table WHERE day_id = '${day_id}'
+
+5. 动态分区写入设置
+   - SET spark.sql.partitionOverwriteMode = dynamic;
+   - 避免误覆盖其他分区
+
+6. 分区数据清理
+   - 定期清理历史分区（如保留近90天）
+   - 使用 ALTER TABLE DROP PARTITION
+*/

one-skill/smart-data-developer/references/sql/templates/spark/query-template.sql

@@ -0,0 +1,160 @@
+-- =====================================================================
+-- @SparkSqlName:    PAIMONA-D-SQL-{表名}-QUERY
+-- @Version:         1.0
+-- @Desc:            标准 SELECT 查询模板
+-- @TargetTables:    无（查询输出）
+-- @SourceTables:    {源表列表}
+-- @TargetDatabase:  Paimon
+-- @SourceDatabase:  Paimon
+-- =====================================================================
+
+-- ============================================================================
+-- 基础查询示例
+-- ============================================================================
+
+-- 1. 单表查询
+SELECT 
+    id,
+    name,
+    amount,
+    created_at
+FROM source_table
+WHERE day_id = '${day_id}'      -- 分区过滤
+  AND status = 'active'         -- 业务过滤
+ORDER BY created_at DESC
+LIMIT 1000;
+
+-- ============================================================================
+-- JOIN 查询示例
+-- ============================================================================
+
+-- 2. 两表 JOIN
+SELECT 
+    a.id,
+    a.name,
+    b.category_name
+FROM main_table a
+JOIN dim_table b ON a.category_id = b.id
+WHERE a.day_id = '${day_id}'
+  AND b.is_active = true;
+
+-- 3. 多表 JOIN（带别名）
+SELECT 
+    o.order_id,
+    u.user_name,
+    p.product_name,
+    oi.quantity,
+    oi.unit_price
+FROM orders o
+JOIN users u ON o.user_id = u.id
+JOIN order_items oi ON o.order_id = oi.order_id
+JOIN products p ON oi.product_id = p.id
+WHERE o.day_id = '${day_id}'
+  AND o.status IN ('completed', 'shipped');
+
+-- ============================================================================
+-- 聚合查询示例
+-- ============================================================================
+
+-- 4. GROUP BY 聚合
+SELECT 
+    department,
+    COUNT(*) AS employee_count,
+    SUM(salary) AS total_salary,
+    AVG(salary) AS avg_salary,
+    MAX(salary) AS max_salary,
+    MIN(salary) AS min_salary
+FROM employees
+WHERE day_id = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_salary DESC;
+
+-- 5. 多字段分组 + 去重计数
+SELECT 
+    date,
+    region,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(amount) AS total_amount
+FROM orders
+WHERE day_id = '${day_id}'
+GROUP BY date, region;
+
+-- ============================================================================
+-- 窗口函数示例
+-- ============================================================================
+
+-- 6. ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        name,
+        salary,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY salary DESC) AS rn
+    FROM employees
+    WHERE day_id = '${day_id}'
+) t
+WHERE rn <= 3;     -- 每个部门薪资前3名
+
+-- 7. 累计聚合
+SELECT 
+    date,
+    amount,
+    SUM(amount) OVER (ORDER BY date) AS cumulative_amount,
+    AVG(amount) OVER (
+        ORDER BY date
+        ROWS BETWEEN 6 PRECEDING AND CURRENT ROW
+    ) AS moving_avg_7d
+FROM daily_sales
+WHERE day_id = '${day_id}';
+
+-- 8. LAG/LEAD（环比计算）
+SELECT 
+    date,
+    amount,
+    LAG(amount, 1) OVER (ORDER BY date) AS prev_amount,
+    amount - LAG(amount, 1) OVER (ORDER BY date) AS daily_change,
+    ROUND((amount - LAG(amount, 1) OVER (ORDER BY date)) 
+        / LAG(amount, 1) OVER (ORDER BY date) * 100, 2) AS growth_rate_pct
+FROM daily_sales
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 子查询示例
+-- ============================================================================
+
+-- 9. IN 子查询
+SELECT *
+FROM orders
+WHERE user_id IN (
+    SELECT id FROM users WHERE vip_level >= 3
+)
+AND day_id = '${day_id}';
+
+-- 10. EXISTS 子查询
+SELECT *
+FROM products p
+WHERE EXISTS (
+    SELECT 1 FROM inventory i 
+    WHERE i.product_id = p.id 
+      AND i.quantity > 0
+)
+AND p.day_id = '${day_id}';
+
+-- ============================================================================
+-- 条件聚合示例
+-- ============================================================================
+
+-- 11. CASE WHEN + 聚合
+SELECT 
+    date,
+    COUNT(*) AS total_orders,
+    SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS completed_count,
+    SUM(CASE WHEN status = 'cancelled' THEN 1 ELSE 0 END) AS cancelled_count,
+    SUM(CASE WHEN status = 'pending' THEN 1 ELSE 0 END) AS pending_count,
+    SUM(CASE WHEN amount > 1000 THEN amount ELSE 0 END) AS high_value_amount
+FROM orders
+WHERE day_id = '${day_id}'
+GROUP BY date;