Add one-skill

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

@@ -0,0 +1,211 @@
+-- =====================================================================
+-- @Name:             HIVE-D-SQL-{表名}-CREATE
+-- @Version:          1.0
+-- @Desc:             Hive 建表模板（内部表/外部表/分区/分桶）
+-- @TargetDatabase:   Hive
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：内部表（Managed Table）
+-- ============================================================================
+-- 适用：Hive 管理数据和元数据，DROP TABLE 时数据一并删除
+
+CREATE TABLE IF NOT EXISTS db_name.managed_table (
+    id              BIGINT          COMMENT '主键ID',
+    name            STRING          COMMENT '名称',
+    category        STRING          COMMENT '类别',
+    amount          DECIMAL(18,2)   COMMENT '金额',
+    status          STRING          COMMENT '状态',
+    created_at      TIMESTAMP       COMMENT '创建时间',
+    updated_at      TIMESTAMP       COMMENT '更新时间',
+    etl_time        TIMESTAMP       COMMENT '数据加工时间',
+    etl_remark      STRING          COMMENT '备注信息'
+)
+COMMENT '内部表示例'
+STORED AS ORC;                        -- 推荐存储格式
+
+-- ============================================================================
+-- 场景2：外部表（External Table）
+-- ============================================================================
+-- 适用：数据由外部系统管理，DROP TABLE 只删元数据不删数据
+
+CREATE EXTERNAL TABLE IF NOT EXISTS db_name.external_table (
+    id              BIGINT          COMMENT '主键ID',
+    user_id         STRING          COMMENT '用户ID',
+    action          STRING          COMMENT '操作类型',
+    page_url        STRING          COMMENT '页面URL',
+    ip_address      STRING          COMMENT 'IP地址',
+    event_time      TIMESTAMP       COMMENT '事件时间'
+)
+COMMENT '日志外部表'
+ROW FORMAT DELIMITED
+    FIELDS TERMINATED BY '\t'
+    LINES TERMINATED BY '\n'
+STORED AS TEXTFILE
+LOCATION '/data/external/logs/';
+
+-- ============================================================================
+-- 场景3：分区表（单分区）
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.partitioned_table (
+    id              BIGINT          COMMENT '主键ID',
+    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',
+    department      STRING          COMMENT '部门',
+    region          STRING          COMMENT '地区',
+    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 ORC;
+
+-- ============================================================================
+-- 场景4：多分区字段
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.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 ORC;
+
+-- ============================================================================
+-- 场景5：分桶表
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.bucketed_table (
+    id              BIGINT          COMMENT '主键ID',
+    user_id         BIGINT          COMMENT '用户ID',
+    user_name       STRING          COMMENT '用户姓名',
+    amount          DECIMAL(18,2)   COMMENT '金额'
+)
+COMMENT '分桶表示例'
+PARTITIONED BY (day_id STRING)
+CLUSTERED BY (user_id)              -- 分桶列
+SORTED BY (amount DESC)             -- 桶内排序
+INTO 16 BUCKETS                     -- 桶数量
+STORED AS ORC;
+
+-- ============================================================================
+-- 场景6：ORC 格式 + 表属性
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.orc_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 'ORC格式带属性配置'
+PARTITIONED BY (day_id STRING)
+STORED AS ORC
+TBLPROPERTIES (
+    'orc.compress' = 'SNAPPY',                      -- 压缩格式
+    'orc.create.index' = 'true',                    -- 创建索引
+    'transactional' = 'false'                       -- 非事务表
+);
+
+-- ============================================================================
+-- 场景7：Parquet 格式
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.parquet_table (
+    id              BIGINT          COMMENT '主键ID',
+    name            STRING          COMMENT '名称',
+    amount          DECIMAL(18,2)   COMMENT '金额',
+    tags            ARRAY<STRING>   COMMENT '标签数组',
+    props           MAP<STRING,STRING> COMMENT '属性映射'
+)
+COMMENT 'Parquet格式表示例'
+PARTITIONED BY (day_id STRING)
+STORED AS PARQUET
+TBLPROPERTIES (
+    'parquet.compression' = 'SNAPPY'
+);
+
+-- ============================================================================
+-- 场景8：临时表
+-- ============================================================================
+
+-- 会话级临时表（会话结束自动删除）
+CREATE TEMPORARY TABLE tmp_processing (
+    id              BIGINT,
+    name            STRING,
+    amount          DECIMAL(18,2)
+);
+
+-- CTAS 快速创建临时表
+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               |
+|-------------------|----------------|------------------------|
+| TINYINT           | 1字节整数      | 小范围数值             |
+| SMALLINT          | 2字节整数      | 小范围数值             |
+| INT               | 4字节整数      | 数量、等级             |
+| BIGINT            | 8字节整数      | ID、计数               |
+| FLOAT             | 4字节浮点      | 近似计算               |
+| DOUBLE            | 8字节浮点      | 科学计算               |
+| DECIMAL(p,s)      | 定点数         | 金额、精确数值         |
+| BOOLEAN           | 布尔           | 状态标志               |
+| STRING            | 变长字符串     | 名称、描述（最常用）   |
+| VARCHAR(n)        | 变长字符串     | 限定长度字符串         |
+| CHAR(n)           | 定长字符串     | 固定长度编码           |
+| DATE              | 日期           | 日期字段               |
+| TIMESTAMP         | 时间戳         | 时间字段               |
+| BINARY            | 二进制         | 二进制数据             |
+| ARRAY<type>       | 数组           | 多值字段               |
+| MAP<k,v>          | 映射           | 属性字典               |
+| STRUCT<f1:t1,...> | 结构体         | 嵌套结构               |
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 内部表 vs 外部表
+   - 内部表：Hive 管理数据，DROP 删数据和元数据
+   - 外部表：外部管理数据，DROP 只删元数据
+   - 生产推荐：原始数据用外部表，加工结果用内部表
+
+2. 存储格式选择
+   - ORC（推荐）：压缩好，列存储，支持谓词下推
+   - PARQUET：跨平台兼容好，列存储
+   - TEXTFILE：原始数据导入，性能最差
+
+3. 分区设计
+   - 按时间分区最常用（day_id, month_id）
+   - 分区列不能出现在表定义的列中（Hive 特有）
+   - 查询时分区列作为普通字段使用
+
+4. 分桶设计
+   - 选择高基数列做分桶列
+   - 用于优化 JOIN（分桶列相同可做 map-side join）
+   - 用于数据抽样（TABLESAMPLE）
+
+5. 字段命名规范
+   - snake_case 格式：user_id, total_amount
+   - 主键：id 或 {业务}_id
+   - 技术字段：etl_time, etl_remark
+   - 分区字段：day_id, month_id, year_id
+
+6. COMMENT 必须添加
+   - 每个字段必须有 COMMENT
+   - 表必须有 COMMENT
+*/

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

@@ -0,0 +1,138 @@
+-- =====================================================================
+-- @Name:             HIVE-D-SQL-{表名}-ETL
+-- @Version:          1.0
+-- @Desc:             Hive ETL 数据处理模板（临时表链式处理）
+-- @TargetDatabase:   Hive
+-- @说明:             和 Spark 类似，禁止 CTE，每步物化为临时表
+-- =====================================================================
+
+-- ============================================================================
+-- 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：tmp_etl_01
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_01;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    id,
+    name,
+    amount,
+    status,
+    dept_id,
+    category_id,
+    created_at,
+    day_id
+FROM db_name.source_table
+WHERE day_id = '${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：tmp_xxx_01, dim_department, dim_category
+-- 输出：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.dept_name,                        -- 维度补全：部门名称
+    c.category_name,                    -- 维度补全：类别名称
+    a.created_at,
+    a.day_id
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN db_name.dim_department b 
+    ON a.dept_id = b.dept_id
+    AND b.day_id = '${day_id}'          -- 维度表分区过滤
+LEFT JOIN db_name.dim_category c 
+    ON a.category_id = c.category_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：tmp_xxx_02
+-- 输出：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,
+    dept_name,
+    category_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, dept_name, category_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：tmp_xxx_03
+-- 输出：目标表
+
+INSERT OVERWRITE TABLE ${db_eda_env}.target_table
+PARTITION (day_id = '${day_id}')
+SELECT 
+    -- 业务字段
+    dept_name,
+    category_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：Hive CTE 可能在某些版本有性能问题
+   - 物化临时表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 TABLE IF EXISTS
+   - 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，幂等）
+   - 明确指定分区
+   - 补全技术字段（etl_time 等）
+
+7. 存储格式建议
+   - 临时表：默认格式即可（中间结果不需要优化存储）
+   - 如需优化：STORED AS ORC
+*/

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

@@ -0,0 +1,141 @@
+-- =====================================================================
+-- @Name:             HIVE-D-SQL-{表名}-INSERT
+-- @Version:          1.0
+-- @Desc:             Hive 数据插入模板
+-- @TargetDatabase:   Hive
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：分区表覆盖写入（最常用）
+-- ============================================================================
+-- 适用：每日/每周/每月增量写入分区表
+
+INSERT OVERWRITE TABLE db_name.target_table
+PARTITION (day_id = '${day_id}')
+SELECT 
+    user_id,
+    user_name,
+    order_count,
+    total_amount,
+    current_timestamp() AS etl_time
+FROM db_name.source_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 场景2：动态分区写入
+-- ============================================================================
+-- 适用：数据中包含分区值，自动写入对应分区
+
+-- 先启用动态分区
+SET hive.exec.dynamic.partition = true;
+SET hive.exec.dynamic.partition.mode = nonstrict;
+
+INSERT OVERWRITE TABLE db_name.target_table
+PARTITION (day_id, region)            -- 动态分区字段
+SELECT 
+    user_id,
+    user_name,
+    order_count,
+    total_amount,
+    current_timestamp() AS etl_time,
+    day_id,                            -- 分区字段1（数据中包含）
+    region                             -- 分区字段2（数据中包含）
+FROM db_name.source_table
+WHERE day_id BETWEEN '${start_day}' AND '${end_day}';
+
+-- ============================================================================
+-- 场景3：追加写入
+-- ============================================================================
+-- 适用：日志表、流水表（允许追加）
+
+INSERT INTO TABLE db_name.target_table
+SELECT 
+    field1,
+    field2,
+    field3,
+    current_timestamp() AS etl_time
+FROM db_name.source_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 场景4：多分区插入（Multi-Insert）
+-- ============================================================================
+-- 适用：一次扫描，写入多个目标（提高效率）
+
+FROM db_name.source_table
+INSERT OVERWRITE TABLE db_name.target_summary
+    PARTITION (day_id = '${day_id}')
+    SELECT 
+        department,
+        COUNT(*) AS record_count,
+        SUM(amount) AS total_amount
+    WHERE day_id = '${day_id}'
+    GROUP BY department
+
+INSERT OVERWRITE TABLE db_name.target_detail
+    PARTITION (day_id = '${day_id}')
+    SELECT 
+        id,
+        name,
+        amount,
+        department
+    WHERE day_id = '${day_id}'
+      AND amount > 1000;
+
+-- ============================================================================
+-- 场景5：导出到文件
+-- ============================================================================
+
+INSERT OVERWRITE DIRECTORY '/output/data/export/'
+ROW FORMAT DELIMITED
+FIELDS TERMINATED BY ','
+STORED AS TEXTFILE
+SELECT 
+    id,
+    name,
+    amount,
+    day_id
+FROM db_name.target_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 场景6：CTAS（Create Table As Select）
+-- ============================================================================
+
+-- 从查询结果创建新表
+CREATE TABLE db_name.new_table AS
+SELECT 
+    department,
+    COUNT(*) AS employee_count,
+    AVG(salary) AS avg_salary
+FROM db_name.employees
+WHERE day_id = '${day_id}'
+GROUP BY department;
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. INSERT OVERWRITE vs INSERT INTO
+   - INSERT OVERWRITE：覆盖分区/表数据（推荐，幂等）
+   - INSERT INTO：追加数据（可能产生重复）
+
+2. 分区表写入必须指定分区
+   - 静态分区：PARTITION (day_id = '${day_id}')
+   - 动态分区：需先 SET 配置，PARTITION (day_id)
+   - 混合分区：PARTITION (day_id = '2026-05-01', region)
+
+3. 动态分区配置
+   SET hive.exec.dynamic.partition = true;
+   SET hive.exec.dynamic.partition.mode = nonstrict;  -- 允许全动态
+   SET hive.exec.max.dynamic.partitions = 1000;       -- 最大动态分区数
+
+4. 字段顺序
+   - SELECT 字段顺序必须与目标表列定义一致
+   - 分区字段在 SELECT 最后（动态分区时）
+
+5. 性能优化
+   - 多分区插入（Multi-Insert）：一次扫描多次写入
+   - INSERT OVERWRITE 比 INSERT INTO 更安全（幂等性）
+   - 大数据量写入时注意 reducer 数量设置
+*/

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

@@ -0,0 +1,235 @@
+-- =====================================================================
+-- @Name:             HIVE-D-SQL-{表名}-QUERY
+-- @Version:          1.0
+-- @Desc:             Hive 查询模板
+-- @TargetDatabase:   Hive
+-- =====================================================================
+
+-- ============================================================================
+-- 1. 单表查询
+-- ============================================================================
+
+SELECT 
+    id,
+    name,
+    amount,
+    created_at
+FROM db_name.source_table
+WHERE day_id = '${day_id}'              -- 分区过滤（必须）
+  AND status = 'active'
+ORDER BY created_at DESC
+LIMIT 1000;
+
+-- ============================================================================
+-- 2. JOIN 查询
+-- ============================================================================
+
+-- 两表 JOIN
+SELECT 
+    a.id,
+    a.name,
+    a.amount,
+    b.category_name
+FROM db_name.main_table a
+JOIN db_name.dim_table b ON a.category_id = b.id
+WHERE a.day_id = '${day_id}';
+
+-- 多表 JOIN（带别名）
+SELECT 
+    o.order_id,
+    u.user_name,
+    p.product_name,
+    oi.quantity,
+    oi.unit_price
+FROM db_name.orders o
+JOIN db_name.users u ON o.user_id = u.id
+JOIN db_name.order_items oi ON o.order_id = oi.order_id
+JOIN db_name.products p ON oi.product_id = p.id
+WHERE o.day_id = '${day_id}'
+  AND o.status IN ('completed', 'shipped');
+
+-- ============================================================================
+-- 3. 聚合查询
+-- ============================================================================
+
+-- GROUP BY + HAVING
+SELECT 
+    department,
+    COUNT(*) AS employee_count,
+    SUM(salary) AS total_salary,
+    AVG(salary) AS avg_salary,
+    MAX(salary) AS max_salary
+FROM db_name.employees
+WHERE day_id = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_salary DESC;
+
+-- 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 db_name.orders
+WHERE day_id = '${day_id}'
+GROUP BY date, region;
+
+-- ============================================================================
+-- 4. 窗口函数
+-- ============================================================================
+
+-- ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        name,
+        salary,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY salary DESC) AS rn
+    FROM db_name.employees
+    WHERE day_id = '${day_id}'
+) t
+WHERE rn <= 3;
+
+-- 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 = '${day_id}';
+
+-- LAG/LEAD（环比）
+SELECT 
+    date,
+    amount,
+    LAG(amount, 1) OVER (ORDER BY date) AS prev_amount,
+    amount - LAG(amount, 1) OVER (ORDER BY date) AS daily_change
+FROM daily_sales
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 5. 子查询
+-- ============================================================================
+
+-- IN 子查询
+SELECT *
+FROM db_name.orders
+WHERE user_id IN (
+    SELECT id FROM db_name.users WHERE vip_level >= 3
+)
+AND day_id = '${day_id}';
+
+-- EXISTS 子查询
+SELECT *
+FROM db_name.products p
+WHERE EXISTS (
+    SELECT 1 FROM db_name.inventory i 
+    WHERE i.product_id = p.id 
+      AND i.quantity > 0
+)
+AND p.day_id = '${day_id}';
+
+-- ============================================================================
+-- 6. 条件聚合（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 amount > 1000 THEN amount ELSE 0 END) AS high_value_amount
+FROM db_name.orders
+WHERE day_id = '${day_id}'
+GROUP BY date;
+
+-- ============================================================================
+-- 7. LATERAL VIEW + explode（Hive 特有）
+-- ============================================================================
+
+-- 展开数组字段
+SELECT 
+    id,
+    name,
+    tag
+FROM db_name.articles
+LATERAL VIEW explode(tags) t AS tag
+WHERE day_id = '${day_id}';
+
+-- 展开数组并统计
+SELECT 
+    tag,
+    COUNT(*) AS article_count
+FROM db_name.articles
+LATERAL VIEW explode(tags) t AS tag
+WHERE day_id = '${day_id}'
+GROUP BY tag;
+
+-- 展开 Map
+SELECT 
+    id,
+    map_key,
+    map_value
+FROM db_name.data_table
+LATERAL VIEW explode(props) m AS map_key, map_value
+WHERE day_id = '${day_id}';
+
+-- posexplode（带索引展开）
+SELECT 
+    id,
+    pos,
+    tag
+FROM db_name.articles
+LATERAL VIEW posexplode(tags) t AS pos, tag
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 8. 复杂类型查询
+-- ============================================================================
+
+-- ARRAY 操作
+SELECT 
+    id,
+    size(tags) AS tag_count,                       -- 数组长度
+    array_contains(tags, '大数据') AS has_tag,     -- 包含判断
+    tags[0] AS first_tag                            -- 取第一个元素
+FROM db_name.articles
+WHERE day_id = '${day_id}';
+
+-- MAP 操作
+SELECT 
+    id,
+    props['city'] AS city,                          -- 取值
+    map_keys(props) AS all_keys,                    -- 所有 key
+    map_values(props) AS all_values                 -- 所有 value
+FROM db_name.user_table
+WHERE day_id = '${day_id}';
+
+-- STRUCT 操作
+SELECT 
+    id,
+    user_info.name AS user_name,                    -- 结构体字段访问
+    user_info.age AS user_age
+FROM db_name.data_table
+WHERE day_id = '${day_id}';
+
+-- ============================================================================
+-- 9. 集合聚合
+-- ============================================================================
+
+-- collect_list / collect_set
+SELECT 
+    department,
+    collect_list(name) AS all_names,               -- 收集为数组（不去重）
+    collect_set(name) AS unique_names,              -- 收集为数组（去重）
+    size(collect_set(name)) AS unique_count
+FROM db_name.employees
+WHERE day_id = '${day_id}'
+GROUP BY department;