Add one-skill

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

@@ -0,0 +1,209 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-CREATE
+-- @Version:          1.0
+-- @Desc:             Apache Doris 建表模板（OLAP 多模型）
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：Duplicate Key 模型（明细表）
+-- ============================================================================
+-- 适用：保留原始明细数据，不做预聚合，数据无冗余
+-- 特点：数据按 Key 排序存储，支持所有列的查询和聚合
+
+CREATE TABLE IF NOT EXISTS db_name.detail_table (
+    -- Key 列（排序字段）
+    order_id        BIGINT          COMMENT '订单ID',
+    order_date      DATE            COMMENT '订单日期',
+    user_id         BIGINT          COMMENT '用户ID',
+
+    -- Value 列
+    user_name       VARCHAR(50)     COMMENT '用户姓名',
+    product_id      BIGINT          COMMENT '商品ID',
+    product_name    VARCHAR(200)    COMMENT '商品名称',
+    quantity        INT             COMMENT '购买数量',
+    unit_price      DECIMAL(18,2)   COMMENT '单价',
+    total_amount    DECIMAL(18,2)   COMMENT '总金额',
+    status          VARCHAR(20)     COMMENT '订单状态',
+    create_time     DATETIME        COMMENT '创建时间'
+)
+DUPLICATE KEY(order_id, order_date, user_id)
+COMMENT '订单明细表'
+PARTITION BY RANGE(order_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01'),
+    PARTITION p202603 VALUES LESS THAN ('2026-04-01')
+)
+DISTRIBUTED BY HASH(order_id) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'storage_format' = 'V2'
+);
+
+-- ============================================================================
+-- 场景2：Aggregate Key 模型（聚合表）
+-- ============================================================================
+-- 适用：预聚合场景，相同 Key 的数据自动合并
+-- 特点：Value 列必须指定聚合函数（SUM, REPLACE, MAX, MIN, HLL_UNION, BITMAP_UNION）
+
+CREATE TABLE IF NOT EXISTS db_name.agg_table (
+    -- Key 列（聚合维度）
+    stat_date       DATE            COMMENT '统计日期',
+    department      VARCHAR(100)    COMMENT '部门名称',
+    region          VARCHAR(100)    COMMENT '地区',
+
+    -- Value 列（带聚合函数）
+    order_count     BIGINT          SUM         COMMENT '订单总数',
+    total_amount    DECIMAL(18,2)   SUM         COMMENT '总金额',
+    unique_users    BIGINT          REPLACE     COMMENT '去重用户数（预计算值）',
+    max_amount      DECIMAL(18,2)   MAX         COMMENT '最大金额',
+    last_update     DATETIME        REPLACE     COMMENT '最后更新时间'
+)
+AGGREGATE KEY(stat_date, department, region)
+COMMENT '部门销售聚合表'
+PARTITION BY RANGE(stat_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01')
+)
+DISTRIBUTED BY HASH(department) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'storage_format' = 'V2'
+);
+
+-- ============================================================================
+-- 场景3：Unique Key 模型（唯一主键表）
+-- ============================================================================
+-- 适用：需要按主键更新/去重的场景
+-- 特点：相同主键的数据保留最新一条（整行替换）
+
+CREATE TABLE IF NOT EXISTS db_name.unique_table (
+    -- Key 列（主键，必须唯一）
+    user_id         BIGINT          COMMENT '用户ID',
+
+    -- Value 列
+    user_name       VARCHAR(50)     COMMENT '用户姓名',
+    phone           VARCHAR(20)     COMMENT '手机号',
+    email           VARCHAR(100)    COMMENT '邮箱',
+    vip_level       INT             COMMENT 'VIP等级',
+    register_date   DATE            COMMENT '注册日期',
+    last_login      DATETIME        COMMENT '最后登录时间',
+    status          VARCHAR(10)     COMMENT '状态'
+)
+UNIQUE KEY(user_id)
+COMMENT '用户信息表（按主键更新）'
+DISTRIBUTED BY HASH(user_id) BUCKETS 16
+PROPERTIES (
+    'replication_num' = '3',
+    'enable_unique_key_merge_based_on_replica' = 'true'
+);
+
+-- ============================================================================
+-- 场景4：带动态分区属性
+-- ============================================================================
+-- 适用：按日自动创建和管理分区
+
+CREATE TABLE IF NOT EXISTS db_name.auto_partition_table (
+    stat_date       DATE            COMMENT '统计日期',
+    department      VARCHAR(100)    COMMENT '部门',
+    metric_value    DECIMAL(18,2)   SUM         COMMENT '指标值',
+    record_count    BIGINT          SUM         COMMENT '记录数'
+)
+AGGREGATE KEY(stat_date, department)
+COMMENT '自动分区示例表'
+PARTITION BY RANGE(stat_date) ()
+DISTRIBUTED BY HASH(department) BUCKETS 8
+PROPERTIES (
+    'replication_num' = '3',
+    'dynamic_partition.enable' = 'true',
+    'dynamic_partition.time_unit' = 'DAY',
+    'dynamic_partition.start' = '-30',          -- 保留30天历史
+    'dynamic_partition.end' = '3',              -- 预创建3天
+    'dynamic_partition.prefix' = 'p',
+    'dynamic_partition.buckets' = '8'
+);
+
+-- ============================================================================
+-- 场景5：多分区 + 多分桶
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.multi_partition_table (
+    stat_date       DATE            COMMENT '统计日期',
+    region          VARCHAR(50)     COMMENT '地区',
+    city            VARCHAR(50)     COMMENT '城市',
+    user_id         BIGINT          COMMENT '用户ID',
+    amount          DECIMAL(18,2)   SUM         COMMENT '金额'
+)
+AGGREGATE KEY(stat_date, region, city, user_id)
+COMMENT '多维度分区示例'
+PARTITION BY RANGE(stat_date) (
+    PARTITION p202601 VALUES LESS THAN ('2026-02-01'),
+    PARTITION p202602 VALUES LESS THAN ('2026-03-01')
+)
+DISTRIBUTED BY HASH(user_id) BUCKETS 32
+PROPERTIES (
+    'replication_num' = '3',
+    'in_memory' = 'false',
+    'storage_format' = 'V2',
+    'compression' = 'LZ4'
+);
+
+-- ============================================================================
+-- 字段类型速查
+-- ============================================================================
+/*
+| 类型          | 说明           | 适用场景               |
+|---------------|----------------|------------------------|
+| BOOLEAN       | 布尔           | 状态标志               |
+| TINYINT       | 1字节整数      | 小范围枚举             |
+| 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、大数值       |
+| LARGEINT      | 16字节整数     | 超大数值               |
+| 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         |
+| DATE          | 日期           | 日期字段（无时间）     |
+| DATETIME      | 日期时间       | 时间戳（精确到秒）     |
+| CHAR(n)       | 定长字符串     | 固定长度编码           |
+| VARCHAR(n)    | 变长字符串     | 名称、描述             |
+| STRING        | 变长字符串     | 大文本（无长度限制）   |
+| BITMAP        | 位图           | 精确去重（仅聚合模型） |
+| HLL           | HyperLogLog    | 近似去重（仅聚合模型） |
+| JSON          | JSON           | JSON数据存储           |
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 模型选择
+   - Duplicate Key：保留原始明细，不做预聚合
+   - Aggregate Key：预聚合，相同 Key 的 Value 自动合并
+   - Unique Key：按主键去重，保留最新数据
+
+2. 分区设计
+   - 按时间字段 RANGE 分区（最常用）
+   - 支持动态分区自动管理
+   - 单分区数据量建议 1GB~10GB
+
+3. 分桶设计
+   - 使用高基数列做 HASH 分桶
+   - 分桶数 = BE节点数 × CPU核数（参考值）
+   - 单桶数据量建议 100MB~1GB
+
+4. 副本数
+   - 生产环境建议 3 副本
+   - 测试环境可设 1 副本
+
+5. Key 列选择
+   - Duplicate Key：高频过滤/排序字段
+   - Aggregate Key：聚合维度字段
+   - Unique Key：业务主键
+
+6. 注意事项
+   - Key 列必须在 Value 列之前
+   - 分区列必须是 Key 列
+   - 分桶列必须是 Key 列
+   - BITMAP/HLL 仅用于 Aggregate 模型的 Value 列
+*/

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

@@ -0,0 +1,128 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-ETL
+-- @Version:          2.0
+-- @Desc:             Apache Doris ETL 数据处理模板（临时表链式处理）
+-- @TargetDatabase:   Apache Doris
+-- @说明:             统一规范：禁止 CTE，每步物化为临时表，先 DROP 再 CREATE
+-- =====================================================================
+
+-- ============================================================================
+-- 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_xxx_01
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_01;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    order_id,
+    user_id,
+    dept_id,
+    total_amount,
+    status,
+    order_date
+FROM db_name.source_table
+WHERE order_date = '${day_id}'
+  AND status IN ('completed', 'shipped')     -- 业务过滤
+  AND total_amount > 0                       -- 数据质量过滤
+  AND user_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：${db_tmp_env}.tmp_xxx_01, dim_department, dim_category
+-- 输出：${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.order_id,
+    a.user_id,
+    a.total_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.order_date
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN db_name.dim_department b 
+    ON a.dept_id = b.dept_id
+LEFT JOIN db_name.dim_category c 
+    ON a.category_id = c.category_id;
+
+-- ============================================================================
+-- Step03: 聚合计算与指标生成
+-- ============================================================================
+-- 说明：按业务维度聚合，计算统计指标
+-- 输入：${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 
+    order_date,
+    dept_name,
+    category_name,
+    COUNT(*) AS record_count,                -- 记录数
+    COUNT(DISTINCT user_id) AS unique_users, -- 去重用户数
+    SUM(total_amount) AS total_amount,       -- 总金额
+    AVG(total_amount) AS avg_amount,         -- 平均金额
+    MAX(total_amount) AS max_amount          -- 最大金额
+FROM ${db_tmp_env}.tmp_xxx_02
+GROUP BY order_date, dept_name, category_name;
+
+-- ============================================================================
+-- Step04: 最终输出写入目标表
+-- ============================================================================
+-- 说明：补全目标表标准字段，写入结果表
+-- 输入：${db_tmp_env}.tmp_xxx_03
+-- 输出：目标表
+
+INSERT INTO ${db_eda_env}.target_table
+SELECT 
+    -- 业务字段
+    dept_name,
+    category_name,
+    record_count,
+    unique_users,
+    total_amount,
+    avg_amount,
+    max_amount,
+    
+    -- 技术字段
+    NOW() AS etl_time,                       -- 数据加工时间
+    '${day_id}' AS stat_date                 -- 统计日期
+FROM ${db_tmp_env}.tmp_xxx_03;
+
+-- ============================================================================
+-- 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：便于调试、断点续跑、统一编码规范
+
+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. Doris 写入方式
+   - 默认使用 INSERT INTO
+   - Aggregate Key 表：自动合并相同 Key 的数据
+   - Unique Key 表：自动按主键去重，保留最新数据
+   - Doris 2.0+ 也支持 INSERT OVERWRITE
+
+4. 过滤条件前置
+   - 所有过滤在最早阶段应用
+   - 减少中间数据量
+
+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. Doris 特有注意事项
+   - 不支持 LEFT SEMI JOIN / LEFT ANTI JOIN
+   - 日期函数用 MySQL 风格：DATE_FORMAT, DATE_ADD(INTERVAL)
+   - 不支持 collect_list/collect_set，用 GROUP_CONCAT 替代
+*/

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

@@ -0,0 +1,147 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-INSERT
+-- @Version:          1.0
+-- @Desc:             Apache Doris 数据插入模板
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：INSERT INTO（追加写入）
+-- ============================================================================
+-- 适用：向 Doris 表追加数据，不会删除已有数据
+
+INSERT INTO db_name.target_table
+SELECT 
+    stat_date,
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table
+WHERE stat_date = '${day_id}';
+
+-- ============================================================================
+-- 场景2：INSERT OVERWRITE（覆盖写入）
+-- ============================================================================
+-- 适用：覆盖目标表（或指定分区）的全部数据
+-- 注意：Doris 2.0+ 支持，且仅适用于 Partition 表
+
+-- 覆盖整表
+INSERT OVERWRITE db_name.target_table
+SELECT 
+    stat_date,
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table;
+
+-- 覆盖指定分区（推荐）
+INSERT OVERWRITE db_name.target_table
+PARTITION(p202605)
+SELECT 
+    department,
+    region,
+    order_count,
+    total_amount
+FROM db_name.source_table
+WHERE stat_date >= '2026-05-01'
+  AND stat_date < '2026-06-01';
+
+-- ============================================================================
+-- 场景3：从查询结果写入（ETL 场景）
+-- ============================================================================
+
+-- 简单转换后写入
+INSERT INTO db_name.target_table
+SELECT 
+    order_date,
+    department,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(total_amount) AS total_amount,
+    AVG(total_amount) AS avg_amount
+FROM db_name.source_orders o
+LEFT JOIN db_name.dim_department d ON o.dept_id = d.dept_id
+WHERE o.order_date = '${day_id}'
+GROUP BY order_date, department;
+
+-- ============================================================================
+-- 场景4：批量 VALUES 写入
+-- ============================================================================
+
+INSERT INTO db_name.target_table (stat_date, department, amount)
+VALUES 
+    ('2026-05-01', '市场部', 10000.00),
+    ('2026-05-01', '技术部', 25000.00),
+    ('2026-05-01', '运营部', 18000.00);
+
+-- ============================================================================
+-- 场景5：Stream Load（数据导入）
+-- ============================================================================
+-- 适用：大批量数据导入（百万级以上）
+-- 注意：Stream Load 通过 HTTP 协议提交，不是 SQL 语法
+
+/*
+-- curl 命令示例
+curl --location-trusted -u user:password \
+    -H "label:load_order_20260501" \
+    -H "column_separator:," \
+    -H "columns:order_id,order_date,user_id,total_amount" \
+    -T data.csv \
+    http://fe_host:8030/api/db_name/orders/_stream_load
+*/
+
+-- ============================================================================
+-- 场景6：Broker Load（外部数据源导入）
+-- ============================================================================
+
+/*
+LOAD LABEL db_name.load_label_20260501
+(
+    DATA INFILE('hdfs://namenode:8020/path/to/data/*')
+    INTO TABLE target_table
+    COLUMNS TERMINATED BY ','
+    (stat_date, department, region, amount)
+    SET (amount = amount * 1.0)
+)
+WITH BROKER 'broker_name'
+(
+    'username' = 'hdfs_user',
+    'password' = 'hdfs_password'
+)
+PROPERTIES
+(
+    'timeout' = '3600',
+    'max_filter_ratio' = '0.01'
+);
+*/
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. INSERT INTO vs INSERT OVERWRITE
+   - INSERT INTO：追加数据，不删除已有数据
+   - INSERT OVERWRITE：覆盖数据（Doris 2.0+ 支持）
+   - 日常增量推荐 INSERT INTO，全量刷新推荐 INSERT OVERWRITE
+
+2. Doris 不使用临时表链式处理
+   - 与 Spark 不同，Doris 通常用单条 SQL 或 CTE 完成 ETL
+   - 直接 INSERT INTO ... SELECT ... 即可
+
+3. 字段顺序
+   - SELECT 字段顺序必须与目标表列定义顺序一致
+   - 或显式指定列名：INSERT INTO table (col1, col2) SELECT ...
+
+4. 数据导入方式选择
+   - 少量数据：INSERT INTO ... SELECT ... 或 INSERT INTO ... VALUES ...
+   - 大批量导入：Stream Load（HTTP PUT，最高性能）
+   - HDFS 导入：Broker Load
+   - 外部数据源：Routine Load（Kafka 等）
+
+5. 性能建议
+   - 批量写入优于逐条写入
+   - Stream Load 是最高性能的导入方式
+   - 建议攒批后一次性写入，避免频繁小批量导入
+*/

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

@@ -0,0 +1,189 @@
+-- =====================================================================
+-- @Name:             DORIS-D-SQL-{表名}-QUERY
+-- @Version:          1.0
+-- @Desc:             Apache Doris 查询模板
+-- @TargetDatabase:   Apache Doris
+-- =====================================================================
+
+-- ============================================================================
+-- 1. 单表查询
+-- ============================================================================
+
+SELECT 
+    order_id,
+    user_name,
+    total_amount,
+    create_time
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+  AND status = 'completed'
+ORDER BY total_amount DESC
+LIMIT 100;
+
+-- ============================================================================
+-- 2. JOIN 查询
+-- ============================================================================
+
+-- 两表 JOIN
+SELECT 
+    o.order_id,
+    o.total_amount,
+    u.user_name,
+    u.vip_level
+FROM db_name.orders o
+JOIN db_name.users u ON o.user_id = u.user_id
+WHERE o.order_date = '${day_id}'
+  AND o.status = 'completed';
+
+-- 多表 JOIN
+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.user_id
+JOIN db_name.order_items oi ON o.order_id = oi.order_id
+JOIN db_name.products p ON oi.product_id = p.product_id
+WHERE o.order_date BETWEEN '${start_date}' AND '${end_date}';
+
+-- ============================================================================
+-- 3. 聚合查询
+-- ============================================================================
+
+-- GROUP BY + HAVING
+SELECT 
+    department,
+    COUNT(*) AS order_count,
+    SUM(total_amount) AS total_amount,
+    AVG(total_amount) AS avg_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_amount DESC;
+
+-- 多字段分组 + 去重计数
+SELECT 
+    order_date,
+    region,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(total_amount) AS total_amount
+FROM db_name.orders
+WHERE order_date BETWEEN '${start_date}' AND '${end_date}'
+GROUP BY order_date, region;
+
+-- ============================================================================
+-- 4. 窗口函数
+-- ============================================================================
+
+-- ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        user_name,
+        total_amount,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY total_amount DESC) AS rn
+    FROM db_name.orders
+    WHERE order_date = '${day_id}'
+) t
+WHERE rn <= 3;
+
+-- 累计聚合
+SELECT 
+    order_date,
+    daily_amount,
+    SUM(daily_amount) OVER (ORDER BY order_date) AS cumulative_amount,
+    AVG(daily_amount) OVER (
+        ORDER BY order_date
+        ROWS BETWEEN 6 PRECEDING AND CURRENT ROW
+    ) AS moving_avg_7d
+FROM (
+    SELECT order_date, SUM(total_amount) AS daily_amount
+    FROM db_name.orders
+    GROUP BY order_date
+) t;
+
+-- LAG/LEAD（环比计算）
+SELECT 
+    order_date,
+    daily_amount,
+    LAG(daily_amount, 1) OVER (ORDER BY order_date) AS prev_amount,
+    daily_amount - LAG(daily_amount, 1) OVER (ORDER BY order_date) AS daily_change,
+    ROUND(
+        (daily_amount - LAG(daily_amount, 1) OVER (ORDER BY order_date)) 
+        / LAG(daily_amount, 1) OVER (ORDER BY order_date) * 100, 2
+    ) AS growth_rate_pct
+FROM (
+    SELECT order_date, SUM(total_amount) AS daily_amount
+    FROM db_name.orders
+    GROUP BY order_date
+) t;
+
+-- ============================================================================
+-- 5. 分页查询
+-- ============================================================================
+
+-- LIMIT OFFSET 分页（Doris 原生支持）
+SELECT 
+    order_id, user_name, total_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+ORDER BY order_id
+LIMIT 20 OFFSET 0;          -- 第1页，每页20条
+
+-- ============================================================================
+-- 6. 子查询
+-- ============================================================================
+
+-- IN 子查询
+SELECT *
+FROM db_name.orders
+WHERE user_id IN (
+    SELECT user_id FROM db_name.users WHERE vip_level >= 3
+)
+AND order_date = '${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.product_id 
+      AND i.quantity > 0
+);
+
+-- ============================================================================
+-- 7. 条件聚合（CASE WHEN + 聚合）
+-- ============================================================================
+
+SELECT 
+    order_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 total_amount > 1000 THEN total_amount ELSE 0 END) AS high_value_amount
+FROM db_name.orders
+WHERE order_date = '${day_id}'
+GROUP BY order_date;
+
+-- ============================================================================
+-- 8. Bitmap 精确去重（Doris 特有）
+-- ============================================================================
+
+-- 使用 bitmap 做精确去重（需要在 Aggregate Key 模型中定义 BITMAP 类型列）
+-- 注意：bitmap 函数只能用于包含 BITMAP 类型列的表
+
+-- 精确去重计数（预计算场景，在 Aggregate Key 表中使用 BITMAP_UNION）
+-- 建表时 Value 列定义：user_id_bitmap BITMAP BITMAP_UNION
+-- 查询时：
+-- SELECT date, bitmap_union_count(user_id_bitmap) AS uv FROM table GROUP BY date;
+
+-- HLL 近似去重
+-- 建表时 Value 列定义：user_id_hll HLL HLL_UNION
+-- 查询时：
+-- SELECT date, hll_union_agg(user_id_hll) AS approx_uv FROM table GROUP BY date;

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;

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

@@ -0,0 +1,211 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-CREATE
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 建表模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             Kudu 通过 Impala 访问，使用 Impala DDL 操作 Kudu 表
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：基础表创建（Hash 分区）
+-- ============================================================================
+-- 适用：按主键 Hash 分布数据，写入和点查性能好
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_basic (
+    -- 主键列（Kudu 表必须有主键）
+    id              BIGINT          NOT NULL 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',
+    created_at      TIMESTAMP       COMMENT '创建时间',
+    updated_at      TIMESTAMP       COMMENT '更新时间'
+)
+PRIMARY KEY (id)
+PARTITION BY HASH(id) PARTITIONS 8
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景2：Hash + Range 组合分区
+-- ============================================================================
+-- 适用：按时间范围 + Hash 组合，兼顾范围查询和写入性能
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_range_hash (
+    -- 主键列（必须包含分区列）
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    stat_date       STRING          NOT NULL COMMENT '统计日期 yyyy-MM-dd',
+    
+    -- 业务字段
+    department      STRING          COMMENT '部门',
+    metric_name     STRING          COMMENT '指标名称',
+    metric_value    DECIMAL(18,2)   COMMENT '指标值',
+    etl_time        TIMESTAMP       COMMENT '加工时间'
+)
+PRIMARY KEY (id, stat_date)
+PARTITION BY 
+    HASH(id) PARTITIONS 4,
+    RANGE(stat_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01',
+        PARTITION '2026-03-01' <= VALUES < '2026-04-01',
+        PARTITION '2026-04-01' <= VALUES < '2026-05-01',
+        PARTITION '2026-05-01' <= VALUES < '2026-06-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3',
+    'kudu.compression' = 'LZ4'
+);
+
+-- ============================================================================
+-- 场景3：多列主键
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_composite_pk (
+    user_id         BIGINT          NOT NULL COMMENT '用户ID',
+    order_date      STRING          NOT NULL COMMENT '订单日期',
+    order_seq       INT             NOT NULL COMMENT '当日订单序号',
+    
+    user_name       STRING          COMMENT '用户姓名',
+    product_name    STRING          COMMENT '商品名称',
+    quantity        INT             COMMENT '数量',
+    total_amount    DECIMAL(18,2)   COMMENT '总金额',
+    status          STRING          COMMENT '状态',
+    create_time     TIMESTAMP       COMMENT '创建时间'
+)
+PRIMARY KEY (user_id, order_date, order_seq)
+PARTITION BY 
+    HASH(user_id) PARTITIONS 8,
+    RANGE(order_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01',
+        PARTITION '2026-03-01' <= VALUES < '2026-04-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景4：纯 Range 分区
+-- ============================================================================
+-- 适用：按时间顺序写入，范围查询多
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_range_only (
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    stat_date       STRING          NOT NULL COMMENT '统计日期',
+    metric_value    DECIMAL(18,2)   COMMENT '指标值',
+    dimension       STRING          COMMENT '维度',
+    etl_time        TIMESTAMP       COMMENT '加工时间'
+)
+PRIMARY KEY (id, stat_date)
+PARTITION BY RANGE(stat_date) (
+    PARTITION '2026-01-01' <= VALUES < '2026-04-01',
+    PARTITION '2026-04-01' <= VALUES < '2026-07-01',
+    PARTITION '2026-07-01' <= VALUES < '2026-10-01',
+    PARTITION '2026-10-01' <= VALUES < '2027-01-01'
+)
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3'
+);
+
+-- ============================================================================
+-- 场景5：外部表映射已有 Kudu 表
+-- ============================================================================
+
+CREATE EXTERNAL TABLE IF NOT EXISTS db_name.kudu_external
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.master_addresses' = 'kudu-master-1:7051,kudu-master-2:7051,kudu-master-3:7051',
+    'kudu.table_name' = 'impala.db_name.existing_table'
+);
+
+-- ============================================================================
+-- 场景6：带压缩和副本配置
+-- ============================================================================
+
+CREATE TABLE IF NOT EXISTS db_name.kudu_with_props (
+    id              BIGINT          NOT NULL COMMENT '主键ID',
+    data_date       STRING          NOT NULL COMMENT '数据日期',
+    content         STRING          COMMENT '内容',
+    value           DOUBLE          COMMENT '数值'
+)
+PRIMARY KEY (id, data_date)
+PARTITION BY 
+    HASH(id) PARTITIONS 8,
+    RANGE(data_date) (
+        PARTITION '2026-01-01' <= VALUES < '2026-02-01',
+        PARTITION '2026-02-01' <= VALUES < '2026-03-01'
+    )
+STORED AS KUDU
+TBLPROPERTIES (
+    'kudu.num_tablet_replicas' = '3',
+    'kudu.compression' = 'LZ4',                        -- 压缩算法
+    'kudu.encryption' = 'false'                        -- 加密
+);
+
+-- ============================================================================
+-- 字段类型速查（Kudu 支持的类型）
+-- ============================================================================
+/*
+| 类型          | 说明           | 适用场景               |
+|---------------|----------------|------------------------|
+| BOOLEAN       | 布尔           | 状态标志               |
+| TINYINT       | 1字节整数      | 小范围枚举             |
+| 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         |
+| STRING        | 变长字符串     | 名称、描述             |
+| 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           |
+| TIMESTAMP     | 时间戳         | 时间字段（微秒精度）   |
+| DATE          | 日期           | 日期字段               |
+| BINARY        | 二进制         | 二进制数据             |
+
+注意：Kudu 不支持 ARRAY, MAP, STRUCT 等复杂类型
+*/
+
+-- ============================================================================
+-- 建表规范说明
+-- ============================================================================
+/*
+1. 主键约束（Kudu 特有）
+   - 每张 Kudu 表必须有 PRIMARY KEY
+   - 主键列不能为 NULL（必须 NOT NULL）
+   - 主键值不可 UPDATE（只能删除后重新插入）
+   - 主键列必须包含在分区列中
+
+2. 分区策略
+   - Hash 分区：均匀分布，适合写入和点查
+   - Range 分区：按范围查询，适合时间序列
+   - Hash + Range 组合：兼顾两者优势（推荐）
+   - 分区数 = tablet 数量，影响并行度
+
+3. 分区设计建议
+   - Hash 分区数：建议 4 的倍数，参考数据量
+   - Range 分区：按时间维度，定期添加新分区
+   - 单个 tablet 建议 1GB~10GB
+
+4. 副本数
+   - 生产环境建议 3 副本（默认）
+   - Raft 协议保证一致性
+
+5. 压缩
+   - 推荐 LZ4（速度和压缩比平衡）
+   - 可选：SNAPPY, ZLIB, LZ4
+
+6. 与 Hive/Spark 表的区别
+   - Kudu 表支持 UPDATE 和 DELETE
+   - Kudu 表不支持 INSERT OVERWRITE
+   - Kudu 表不支持复杂类型（ARRAY, MAP, STRUCT）
+   - Kudu 表主键有约束，Hive/Spark 无约束
+*/

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

@@ -0,0 +1,146 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-ETL
+-- @Version:          2.0
+-- @Desc:             Kudu (via Impala) ETL 数据处理模板（临时表链式处理）
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             统一规范：禁止 CTE，每步物化为临时表，先 DROP 再 CREATE
+--                   最后一步用 UPSERT INTO 写入 Kudu 目标表
+-- =====================================================================
+
+-- ============================================================================
+-- 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：${db_tmp_env}.tmp_xxx_01
+
+DROP TABLE IF EXISTS ${db_tmp_env}.tmp_xxx_01;
+CREATE TABLE ${db_tmp_env}.tmp_xxx_01 AS
+SELECT 
+    order_id,
+    user_id,
+    dept_id,
+    product_id,
+    quantity,
+    amount,
+    status,
+    stat_date
+FROM db_name.source_table
+WHERE stat_date = '${day_id}'
+  AND status IN ('completed', 'shipped')     -- 业务过滤
+  AND amount > 0                             -- 数据质量过滤
+  AND user_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：${db_tmp_env}.tmp_xxx_01, dim_department, dim_product
+-- 输出：${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.order_id,
+    a.user_id,
+    a.amount,
+    a.quantity,
+    b.dept_name,                             -- 维度补全：部门名称
+    c.category_name,                         -- 维度补全：类别名称
+    a.stat_date
+FROM ${db_tmp_env}.tmp_xxx_01 a
+LEFT JOIN db_name.dim_department b 
+    ON a.dept_id = b.dept_id
+LEFT JOIN db_name.dim_product c 
+    ON a.product_id = c.product_id;
+
+-- ============================================================================
+-- Step03: 聚合计算与指标生成
+-- ============================================================================
+-- 说明：按业务维度聚合，计算统计指标
+-- 输入：${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 
+    stat_date,
+    dept_name,
+    category_name,
+    COUNT(*) AS record_count,                -- 记录数
+    COUNT(DISTINCT user_id) AS unique_users, -- 去重用户数
+    SUM(amount) AS total_amount,             -- 总金额
+    SUM(quantity) AS total_quantity,         -- 总数量
+    AVG(amount) AS avg_amount,               -- 平均金额
+    MAX(amount) AS max_amount                -- 最大金额
+FROM ${db_tmp_env}.tmp_xxx_02
+GROUP BY stat_date, dept_name, category_name;
+
+-- ============================================================================
+-- Step04: 最终输出写入 Kudu 目标表
+-- ============================================================================
+-- 说明：使用 UPSERT 写入 Kudu 目标表
+-- 输入：${db_tmp_env}.tmp_xxx_03
+-- 输出：Kudu 目标表
+
+-- 方式1：UPSERT（推荐，主键存在则更新，不存在则插入）
+UPSERT INTO ${db_eda_env}.target_table
+SELECT 
+    -- 主键字段（Kudu 表必须有主键）
+    dept_name,
+    category_name,
+    stat_date,
+    
+    -- 指标字段
+    record_count,
+    unique_users,
+    total_amount,
+    total_quantity,
+    avg_amount,
+    max_amount,
+    
+    -- 技术字段
+    NOW() AS etl_time                        -- 数据加工时间
+FROM ${db_tmp_env}.tmp_xxx_03;
+
+-- 方式2：需要全量刷新时（先删后插）
+-- DELETE FROM ${db_eda_env}.target_table WHERE stat_date = '${day_id}';
+-- INSERT INTO ${db_eda_env}.target_table
+-- SELECT ... FROM ${db_tmp_env}.tmp_xxx_03;
+
+-- ============================================================================
+-- 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：便于调试、断点续跑、统一编码规范
+
+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. Kudu 写入方式
+   - 推荐 UPSERT INTO（Kudu 核心优势）
+   - 主键存在 → 更新（整行替换）
+   - 主键不存在 → 插入新行
+   - 需要全量刷新 → 先 DELETE 再 INSERT
+
+4. Kudu 表约束
+   - 不支持 INSERT OVERWRITE（用 UPSERT 或 DELETE + INSERT 替代）
+   - 必须有 PRIMARY KEY
+   - 主键列不能为 NULL
+   - 支持 UPDATE 和 DELETE
+
+5. 过滤条件前置
+   - 所有过滤在最早阶段应用
+   - 减少中间数据量
+
+6. 临时表命名规范
+   - 格式：tmp_{业务简称}_{步骤序号}
+
+7. Kudu 特有注意事项
+   - CONCAT 只接受 2 个参数，多参数用 CONCAT_WS
+   - 不支持 collect_list/collect_set，用 GROUP_CONCAT 替代
+   - 近似去重用 NDV() 函数
+*/

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

@@ -0,0 +1,160 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-INSERT
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 数据插入模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- @说明:             Kudu 表不支持 INSERT OVERWRITE，支持 INSERT INTO 和 UPSERT
+-- =====================================================================
+
+-- ============================================================================
+-- 场景1：INSERT INTO（追加写入）
+-- ============================================================================
+-- 适用：向 Kudu 表追加新数据
+
+INSERT INTO db_name.kudu_table
+SELECT 
+    id,
+    stat_date,
+    name,
+    department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.source_table
+WHERE stat_date = '${day_id}';
+
+-- ============================================================================
+-- 场景2：UPSERT INTO（更新插入，Kudu 特有）
+-- ============================================================================
+-- 适用：如果主键存在则更新，不存在则插入
+-- 这是 Kudu 的核心优势，其他 Hive/Spark 表不支持
+
+-- 基础 UPSERT
+UPSERT INTO db_name.kudu_table
+SELECT 
+    id,
+    stat_date,
+    name,
+    department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.staging_table
+WHERE stat_date = '${day_id}';
+
+-- 聚合后 UPSERT（增量更新指标表）
+UPSERT INTO db_name.kudu_metrics
+SELECT 
+    department,
+    '${day_id}' AS stat_date,
+    COUNT(*) AS order_count,
+    SUM(amount) AS total_amount,
+    current_timestamp() AS etl_time
+FROM db_name.incremental_orders
+WHERE stat_date = '${day_id}'
+GROUP BY department;
+
+-- ============================================================================
+-- 场景3：UPDATE（Kudu 表特有）
+-- ============================================================================
+-- 适用：修改已有数据
+-- 注意：主键列不能被 UPDATE
+
+-- 单条更新
+UPDATE db_name.kudu_table
+SET status = 'processed',
+    updated_at = current_timestamp()
+WHERE id = 12345;
+
+-- 批量条件更新
+UPDATE db_name.kudu_table
+SET status = 'expired',
+    updated_at = current_timestamp()
+WHERE stat_date < '2026-01-01'
+  AND status = 'active';
+
+-- 关联更新（用子查询）
+UPDATE db_name.kudu_table t
+SET t.department = d.new_dept_name
+FROM db_name.dept_mapping d
+WHERE t.department = d.old_dept_name;
+
+-- ============================================================================
+-- 场景4：DELETE（Kudu 表特有）
+-- ============================================================================
+-- 适用：删除数据
+-- 注意：Kudu 的 DELETE 比 Hive/Spark 方便得多
+
+-- 条件删除
+DELETE FROM db_name.kudu_table
+WHERE stat_date < '2026-01-01';
+
+-- 按主键删除
+DELETE FROM db_name.kudu_table
+WHERE id IN (1001, 1002, 1003);
+
+-- 关联删除（用子查询）
+DELETE FROM db_name.kudu_table
+WHERE user_id IN (
+    SELECT user_id FROM db_name.blacklist
+);
+
+-- ============================================================================
+-- 场景5：从查询结果写入
+-- ============================================================================
+
+-- 简单 ETL：清洗后写入
+INSERT INTO db_name.kudu_target
+SELECT 
+    id,
+    '${day_id}' AS stat_date,
+    name,
+    COALESCE(department, '未知') AS department,
+    amount,
+    current_timestamp() AS etl_time
+FROM db_name.raw_data
+WHERE stat_date = '${day_id}'
+  AND id IS NOT NULL
+  AND amount > 0;
+
+-- ============================================================================
+-- 场景6：批量 VALUES 写入
+-- ============================================================================
+
+INSERT INTO db_name.kudu_table (id, stat_date, name, amount)
+VALUES 
+    (1, '2026-05-01', '测试1', 100.00),
+    (2, '2026-05-01', '测试2', 200.00),
+    (3, '2026-05-01', '测试3', 300.00);
+
+-- ============================================================================
+-- 关键规则说明
+-- ============================================================================
+/*
+1. Kudu 表与 Hive/Spark 表的核心区别
+   - 支持 INSERT INTO：✅
+   - 支持 INSERT OVERWRITE：❌（不支持！）
+   - 支持 UPSERT：✅（Kudu 独有，核心能力）
+   - 支持 UPDATE：✅（Kudu 独有）
+   - 支持 DELETE：✅（Kudu 独有）
+
+2. UPSERT 是 Kudu 的核心优势
+   - 主键存在 → 更新（整行替换）
+   - 主键不存在 → 插入新行
+   - 适用于：增量更新、数据修正、指标回填
+
+3. INSERT INTO 注意事项
+   - 如果主键冲突会报错（不会自动去重）
+   - 需要确保写入数据的主键不重复，或使用 UPSERT
+
+4. UPDATE 限制
+   - 主键列不能被 UPDATE
+   - WHERE 条件建议包含主键或分区列（性能）
+
+5. DELETE 建议
+   - 删除大量数据时按分区范围删除
+   - 定期清理历史数据
+
+6. 性能建议
+   - 批量写入优于逐条写入
+   - UPSERT 比 DELETE + INSERT 更高效
+   - 利用主键做点查，避免全表扫描
+*/

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

@@ -0,0 +1,179 @@
+-- =====================================================================
+-- @Name:             KUDU-D-SQL-{表名}-QUERY
+-- @Version:          1.0
+-- @Desc:             Kudu (via Impala) 查询模板
+-- @TargetDatabase:   Apache Kudu (via Impala)
+-- =====================================================================
+
+-- ============================================================================
+-- 1. 单表查询
+-- ============================================================================
+
+SELECT 
+    id,
+    name,
+    amount,
+    created_at
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+  AND status = 'active'
+ORDER BY created_at DESC
+LIMIT 1000;
+
+-- ============================================================================
+-- 2. JOIN 查询
+-- ============================================================================
+
+-- 两表 JOIN（Kudu 表 JOIN 非 Kudu 表也支持）
+SELECT 
+    k.id,
+    k.name,
+    k.amount,
+    d.dept_name
+FROM db_name.kudu_table k
+JOIN db_name.dim_department d ON k.dept_id = d.dept_id
+WHERE k.stat_date = '${day_id}';
+
+-- 多表 JOIN
+SELECT 
+    k.id,
+    k.user_name,
+    p.product_name,
+    k.quantity,
+    k.total_amount
+FROM db_name.kudu_orders k
+JOIN db_name.dim_users u ON k.user_id = u.user_id
+JOIN db_name.dim_products p ON k.product_id = p.product_id
+WHERE k.stat_date BETWEEN '${start_date}' AND '${end_date}';
+
+-- ============================================================================
+-- 3. 聚合查询
+-- ============================================================================
+
+SELECT 
+    department,
+    COUNT(*) AS record_count,
+    SUM(amount) AS total_amount,
+    AVG(amount) AS avg_amount,
+    MAX(amount) AS max_amount,
+    MIN(amount) AS min_amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+GROUP BY department
+HAVING COUNT(*) >= 5
+ORDER BY total_amount DESC;
+
+-- 多字段分组 + 去重计数
+SELECT 
+    stat_date,
+    region,
+    COUNT(*) AS order_count,
+    COUNT(DISTINCT user_id) AS unique_users,
+    SUM(amount) AS total_amount
+FROM db_name.kudu_table
+WHERE stat_date BETWEEN '${start_date}' AND '${end_date}'
+GROUP BY stat_date, region;
+
+-- ============================================================================
+-- 4. 窗口函数
+-- ============================================================================
+
+-- ROW_NUMBER（分组取Top N）
+SELECT *
+FROM (
+    SELECT 
+        department,
+        user_name,
+        amount,
+        ROW_NUMBER() OVER (PARTITION BY department ORDER BY amount DESC) AS rn
+    FROM db_name.kudu_table
+    WHERE stat_date = '${day_id}'
+) t
+WHERE rn <= 3;
+
+-- 累计聚合
+SELECT 
+    stat_date,
+    daily_amount,
+    SUM(daily_amount) OVER (ORDER BY stat_date) AS cumulative_amount
+FROM (
+    SELECT stat_date, SUM(amount) AS daily_amount
+    FROM db_name.kudu_table
+    GROUP BY stat_date
+) t;
+
+-- LAG/LEAD（环比）
+SELECT 
+    stat_date,
+    daily_amount,
+    LAG(daily_amount, 1) OVER (ORDER BY stat_date) AS prev_amount,
+    daily_amount - LAG(daily_amount, 1) OVER (ORDER BY stat_date) AS daily_change
+FROM (
+    SELECT stat_date, SUM(amount) AS daily_amount
+    FROM db_name.kudu_table
+    GROUP BY stat_date
+) t;
+
+-- ============================================================================
+-- 5. 子查询
+-- ============================================================================
+
+-- IN 子查询
+SELECT *
+FROM db_name.kudu_table
+WHERE user_id IN (
+    SELECT user_id FROM db_name.vip_users WHERE vip_level >= 3
+)
+AND stat_date = '${day_id}';
+
+-- EXISTS 子查询
+SELECT *
+FROM db_name.kudu_products p
+WHERE EXISTS (
+    SELECT 1 FROM db_name.kudu_inventory i 
+    WHERE i.product_id = p.product_id 
+      AND i.quantity > 0
+);
+
+-- ============================================================================
+-- 6. 条件聚合（CASE WHEN + 聚合）
+-- ============================================================================
+
+SELECT 
+    stat_date,
+    COUNT(*) AS total_count,
+    SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS completed_count,
+    SUM(CASE WHEN status = 'cancelled' THEN 1 ELSE 0 END) AS cancelled_count,
+    SUM(CASE WHEN amount > 1000 THEN amount ELSE 0 END) AS high_value_amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+GROUP BY stat_date;
+
+-- ============================================================================
+-- 7. LIMIT / OFFSET（分页）
+-- ============================================================================
+
+SELECT id, name, amount
+FROM db_name.kudu_table
+WHERE stat_date = '${day_id}'
+ORDER BY id
+LIMIT 20 OFFSET 0;
+
+-- ============================================================================
+-- 8. Kudu 特有：通过主键高效点查
+-- ============================================================================
+-- Kudu 主键查询可跳过扫描，直接定位 tablet
+
+-- 单主键点查
+SELECT * FROM db_name.kudu_table
+WHERE id = 12345;
+
+-- 复合主键点查
+SELECT * FROM db_name.kudu_composite_pk
+WHERE user_id = 1001
+  AND order_date = '2026-05-01'
+  AND order_seq = 1;
+
+-- 主键 IN 查询
+SELECT * FROM db_name.kudu_table
+WHERE id IN (1001, 1002, 1003, 1004, 1005);

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;